Similar Journals
|
Algorithms
Journal Prestige (SJR): 0.217  Citation Impact (citeScore): 1 Number of Followers: 15  Open Access journalISSN (Print) 1999-4893 Published by MDPI  [258 journals]
|
- Algorithms, Vol. 18, Pages 119: Using Optimization Algorithms for
Effective Missing-Data Imputation: A Case Study of Tabular Data Derived
from Video Surveillance
Authors: Mahmoud M. Eid, Kamal ElDahshan, Abdelatif H. Abouali, Alaa Tharwat
First page: 119
Abstract: Data are crucial components of machine learning and deep learning in real-world applications. However, when collecting data from actual systems, we often encounter issues with missing information, which can harm accuracy and lead to biased results. In the context of video surveillance, missing data may arise due to obstructions, varying camera angles, or technical issues, resulting in incomplete information about the observed scene. This paper introduces a method for handling missing data in tabular formats, specifically focusing on video surveillance. The core idea is to fill in the missing values for a specific feature using values from other related features rather than relying on all available features, which we refer to as the imputation approach based on informative features. The paper presents three sets of experiments. The first set uses synthetic datasets to compare four optimization algorithms—Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), and the Sine–Cosine Algorithm (SCA)—to determine which one best identifies features related to the target feature. The second set works with real-world datasets, while the third focuses on video-surveillance datasets. Each experiment compares the proposed method, utilizing the best optimizer from the first set, against leading imputation methods. The experiments evaluate different types of data and various missing-data rates, ensuring that randomness does not introduce bias. In the first experiment, using only synthetic data, the results indicate that the WOA-based approach outperforms PSO, GWO, and SCA optimization algorithms. The second experiment used real datasets, while the third used tabular data extracted from a video-surveillance system. Both experiments show that our WOA-based imputation method produces promising results, outperforming other state-of-the-art imputation methods.
Citation: Algorithms
PubDate: 2025-02-20
DOI: 10.3390/a18030119
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 120: Fidex and FidexGlo: From Local
Explanations to Global Explanations of Deep Models
Authors: Guido Bologna, Jean-Marc Boutay, Damian Boquete, Quentin Leblanc, Deniz Köprülü, Ludovic Pfeiffer
First page: 120
Abstract: Deep connectionist models are characterized by many neurons grouped together in many successive layers. As a result, their data classifications are difficult to understand. We present two novel algorithms which explain the responses of several black-box machine learning models. The first is Fidex, which is local and thus applied to a single sample. The second, called FidexGlo, is global and uses Fidex. Both algorithms generate explanations by means of propositional rules. In our framework, the discriminative boundaries are parallel to the input variables and their location is precisely determined. Fidex is a heuristic algorithm that, at each step, establishes where the best hyperplane is that has increased fidelity the most. The algorithmic complexity of Fidex is proportional to the maximum number of steps, the number of possible hyperplanes, which is finite, and the number of samples. We first used FidexGlo with ensembles and support vector machines (SVMs) to show that its performance on three benchmark problems is competitive in terms of complexity, fidelity and accuracy. The most challenging part was then to apply it to convolutional neural networks. We achieved this with three classification problems based on images. We obtained accurate results and described the characteristics of the rules generated, as well as several examples of explanations illustrated with their corresponding images. To the best of our knowledge, this is one of the few works showing a global rule extraction technique applied to both ensembles, SVMs and deep neural networks.
Citation: Algorithms
PubDate: 2025-02-20
DOI: 10.3390/a18030120
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 121: A Data-Driven State Estimation Based on
Sample Migration for Low-Observable Distribution Networks
Authors: Hao Jiao, Chen Wu, Lei Wei, Jinming Chen, Yang Xu, Manyun Huang
First page: 121
Abstract: This paper proposes a data-driven state estimation based on sample migration for low-observable distribution networks, addressing the challenge of traditional state estimators being unsuitable for distribution networks with low observability. The state estimation model is trained using historical measurement data from distribution networks with high observability. Measurements updated for low-observable distribution networks are supplemented by transferring samples from high-observable distribution networks using sample migration techniques, resulting in a state estimation model suitable for low-observable distribution networks. Test results demonstrate that the proposed algorithm outperforms traditional algorithms in both estimation accuracy and robustness aspects, such as the Weighted Least Squares (WLS) and Weighted Least Absolute Value (WLAV) methods. Furthermore, sample migration enhances the generalization ability of the state estimation model.
Citation: Algorithms
PubDate: 2025-02-20
DOI: 10.3390/a18030121
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 122: Automata and Arithmetics in Canonical
Number Systems
Authors: Tamás Herendi, Viktória Padányi
First page: 122
Abstract: In this paper, we discuss canonical number systems (CNSs), which are generalizations of positional number systems to polynomials over the integers. We defined the information quantity of a polynomial A∈Z[x] relative to the base of the CNS and proved that it has a strong relation with the length of the representation in the number system. Based on this result, we showed that for every CNS polynomial P, there exists a finite transducer automaton executing the addition operation of polynomials in canonical representation of base P. Finally, we observed the size—i.e., the number of states—of such automata.
Citation: Algorithms
PubDate: 2025-02-20
DOI: 10.3390/a18030122
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 123: Simplified Integrity Checking for an
Expressive Class of Denial Constraints
Authors: Davide Martinenghi
First page: 123
Abstract: Data integrity is crucial for ensuring data correctness and quality and is maintained through integrity constraints that must be continuously checked, especially in data-intensive systems like OLTP. While DBMSs handle very simple cases of constraints (such as primary key and foreign key constraints) well, more complex constraints often require ad hoc solutions. Research since the 1980s has focused on automatic and simplified integrity constraint checking, leveraging the assumption that databases are consistent before updates. This paper presents program transformation operators to generate simplified integrity constraints, focusing on complex constraints expressed in denial form. In particular, we target a class of integrity constraints, called extended denials, which are more general than tuple-generating dependencies and equality-generating dependencies. One of the main contributions of this study consists in the automatic treatment of such a general class of constraints, encompassing the all the most useful and common cases of constraints adopted in practice. Another contribution is the applicability of the proposed technique with a “preventive” approach; unlike all other methods for integrity maintenance, we check whether an update will violate the constraints before executing it, so we never have to undo any work, with potentially huge savings in terms of execution overhead. These techniques can be readily applied to standard database practices and can be directly translated into SQL.
Citation: Algorithms
PubDate: 2025-02-20
DOI: 10.3390/a18030123
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 124: Transforming Medical Data Access: The Role
and Challenges of Recent Language Models in SQL Query Automation
Authors: Tanković, Šajina, Lorencin
First page: 124
Abstract: Generating accurate SQL queries from natural language is critical for enabling non-experts to interact with complex databases, particularly in high-stakes domains like healthcare. This paper presents an extensive evaluation of state-of-the-art large language models (LLM), including LLaMA 3.3, Mixtral, Gemini, Claude 3.5, GPT-4o, and Qwen for transforming medical questions into executable SQL queries using the MIMIC-3 and TREQS datasets. Our approach employs LLMs with various prompts across 1000 natural language questions. The experiments are repeated multiple times to assess performance consistency, token efficiency, and cost-effectiveness. We explore the impact of prompt design on model accuracy through an ablation study, focusing on the role of table data samples and one-shot learning examples. The results highlight substantial trade-offs between accuracy, consistency, and computational cost between the models. This study also underscores the limitations of current models in handling medical terminology and provides insights to improve SQL query generation in the healthcare domain. Future directions include implementing RAG pipelines based on embeddings and reranking models, integrating ICD taxonomies, and refining evaluation metrics for medical query performance. By bridging these gaps, language models can become reliable tools for medical database interaction, enhancing accessibility and decision-making in clinical settings.
Citation: Algorithms
PubDate: 2025-02-21
DOI: 10.3390/a18030124
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 125: Spatial Shape-Aware Network for Elongated
Target Detection
Authors: Shaowen Xu, Der-Horng Lee
First page: 125
Abstract: In remote sensing detection, targets often exhibit unique characteristics such as elongated shapes, multi-directional rotations, and significant scale variations. Traditional convolutional networks extract features using convolution kernels and rely on predefined anchor boxes and sample selection to frame the targets. However, this approach leads to several issues, including imprecise regional feature extraction, the neglect of object shape information, and variations in the potential of positive samples, all stemming from shape variations, ultimately impacting the detector’s performance. To overcome these challenges, we propose a novel Spatial Shape-Aware Network for Elongated Target Detection. Specifically, we introduce three key modules: a Boundary-Guided Spatial Feature Perception Module (BGSF), a Shape-Sensing Module (SSM), and a Potential Evaluation Module (PEM). The Boundary-Guided Spatial Feature Perception Module adjusts the sampling positions and weights of convolution kernels, aligning the feature maps produced by the backbone network to the actual shape and location of the target, while reducing feature responses to irrelevant noise. The Shape-Sensing Module incorporates shape information into the sample selection process, allowing high-potential anchor boxes—which may have low IoU but capture critical target features—to be temporarily retained for further training. The Potential Evaluation Module integrates the potential information of positive samples into the loss function, providing stronger training feedback for high-potential positive samples. Experiments demonstrate that, compared with existing detection networks, our proposed network structure achieves superior detection performance on two widely used datasets, UCAS-AOD and HRSC2016.
Citation: Algorithms
PubDate: 2025-02-21
DOI: 10.3390/a18030125
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 126: Incremental Delayed Subgradient Method for
Decentralized Nonsmooth Convex–Concave Minimax Optimization
Authors: Thipagon Feesantia, Tipsuda Arunrat, Nimit Nimana
First page: 126
Abstract: In this paper, we propose an incremental-type subgradient scheme for solving a nonsmooth convex–concave minimax optimization problem in the setting of Euclidean spaces. We investigate convergence results by deriving an upper bound for the absolute value of the difference between the function value of the averaged iterates and the saddle value, provided that the step size is a constant. By assuming that the step-size sequence is diminishing, we prove the convergences of both the averaged sequence of function values and the sequence of function values of averaged iterates to the saddle value. Finally, we also show some numerical examples for illustrating the obtained theoretical result.
Citation: Algorithms
PubDate: 2025-02-24
DOI: 10.3390/a18030126
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 127: Road Event Detection and Classification
Algorithm Using Vibration and Acceleration Data
Authors: Abiel Aguilar-González, Alejandro Medina Santiago
First page: 127
Abstract: Road event detection is critical for tasks such as monitoring, anomaly detection, and optimization. Traditional approaches often require complex feature engineering or the use of machine learning models, which can be computationally intensive, especially when dealing with real-time data from high-frequency vibration and acceleration sensors. In this work, we propose a Random Forest-based event classification algorithm designed to handle the unique patterns of vibration and acceleration data in road event detection for an urban traffic scenario. Our method utilizes vibration and acceleration data in three axes (x, y, z) to classify events in a robust and scalable manner. The Random Forest model is trained to identify patterns in the sensor data and assign them to predefined event categories, providing an efficient and accurate classification mechanism. Experimental results prove the effectiveness of our approach: it reaches an accuracy of 91.99%, with a precision of 80% and a recall of 75%, demonstrating reliable event classification. Additionally, the Area Under the Curve (AUC) score of 0.9468 confirms the model’s strong discriminative capability. Further, compared to a rule-based approach, our method offers greater generalization and adaptability, reducing the need for manual parameter tuning. While the rule-based approach attains a higher precision of 92%, it requires frequent adjustments for each dataset and lacks robustness across different road conditions.
Citation: Algorithms
PubDate: 2025-02-24
DOI: 10.3390/a18030127
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 128: Using Coherent Hemodynamic Spectroscopy
Model to Investigate Cardiac Arrest
Authors: Vladislav Toronov, Nima Soltani, Leeanne Leung, Rohit Mohindra, Steve Lin
First page: 128
Abstract: The Coherent Hemodynamic Spectroscopy (CHS) model provides a quantitative framework for modeling cerebral hemodynamics and metabolism, particularly in response to small physiological perturbations. However, in its original approximate formulation it was limited to conditions where parameter changes were constrained to 10–20%, making it unsuitable for modeling extreme physiological disruptions such as cardiac arrest. In this study, we present a detailed discussion of the algorithm using the complete CHS model, which extends the original framework by solving partial differential equations without approximations to handle large non-periodic perturbations. This model was applied to data from a previously published cardiac arrest and cardiopulmonary resuscitation (CPR) study in pigs, where cerebral blood flow changed by 100%. While our prior work demonstrated the utility of this approach for analyzing cerebral microvascular and metabolic parameters, it did not include the algorithmic details necessary for reproducibility and broader application. Here, we address this gap by describing the algorithm’s workflow, including the use of non-linear multivariate optimization, and its ability to recover multiple physiological variables, such as the capillary and venule oxygen saturations, and parameters, such as the capillary oxygen diffusion rate, and arterial oxygen saturation. The latter can be valuable when the pulse oximetry measurements are unavailable due to unstable, weak or absent pulse. This study underscores the importance of non-linear modeling in advancing the application of CHS to extreme physiological conditions and highlights its potential for translational research and clinical innovation.
Citation: Algorithms
PubDate: 2025-02-25
DOI: 10.3390/a18030128
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 129: Means and Issues for Adjusting Principal
Component Analysis Results
Authors: Tomokazu Konishi
First page: 129
Abstract: Background: Principal component analysis (PCA) is a method that identifies common directions within multivariate data and presents the data in as few dimensions as possible. One of the advantages of PCA is its objectivity, as the same results can be obtained regardless of who performs the analysis. However, PCA is not a robust method and is sensitive to noise. Consequently, the directions identified by PCA may deviate slightly. If we can teach PCA to account for this deviation and correct it, the results should become more comprehensible. Methods: The top two PCA results were rotated using a rotation unitary matrix. Results: These contributions were determined and compared with the original. At smaller rotations, the change in contribution was also small and the effect on independence was not severe. The rotation made the data considerably more comprehensible. Conclusions: The methods for achieving this and an issue with this are presented. However, care should be taken not to detract from the superior objectivity of PCA.
Citation: Algorithms
PubDate: 2025-02-25
DOI: 10.3390/a18030129
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 130: Incremental Pyraformer–Deep
Canonical Correlation Analysis: A Novel Framework for Effective Fault
Detection in Dynamic Nonlinear Processes
Authors: Yucheng Ding, Yingfeng Zhang, Jianfeng Huang, Shitong Peng
First page: 130
Abstract: Smart manufacturing systems aim to enhance the efficiency, adaptability, and reliability of industrial operations through advanced data-driven approaches. Achieving these objectives hinges on accurate fault detection and timely maintenance, especially in highly dynamic industrial environments. However, capturing nonlinear and temporal dependencies in dynamic nonlinear industrial processes poses significant challenges for traditional data-driven fault detection methods. To address these limitations, this study presents an Incremental Pyraformer–Deep Canonical Correlation Analysis (DCCA) framework that integrates the Pyramidal Attention Mechanism of the Pyraformer with the Broad Learning System for incremental learning in a DCCA basis. The Pyraformer model effectively captures multi-scale temporal features, while the BLS-based incremental learning mechanism adapts to evolving data without full retraining. The proposed framework enhances both spatial and temporal representation, enabling robust fault detection in high-dimensional and continuously changing industrial environments. Experimental validation on the Tennessee Eastman (TE) process, Continuous Stirred-Tank Reactor (CSTR) system, and injection molding process demonstrated superior detection performance. In the TE scenario, our framework achieved a 100% Fault Detection Rate with a 4.35% False Alarm Rate, surpassing DCCA variants. Similarly, in the CSTR case, the approach reached a perfect 100% Fault Detection Rate (FDR) and 3.48% False Alarm Rate (FAR), while in the injection molding process, it delivered a 97.02% FDR with 0% FAR. The findings underline the framework’s effectiveness in handling complex and dynamic data streams, thereby providing a powerful approach for real-time monitoring and proactive maintenance.
Citation: Algorithms
PubDate: 2025-02-25
DOI: 10.3390/a18030130
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 131: Fine-Grained Mapping Between Daily
Activity Features in Smart Homes
Authors: Yahui Wang, Yaqing Liu
First page: 131
Abstract: For daily activity recognition in smart homes, it is possible to reduce the effort required for labeling by transferring a trained model. This involves utilizing a labeled daily activity dataset from one smart home to recognize other activities in another. The foundation of this transfer lies in establishing a shared common feature space between the two smart homes, achieved through a feature mapping approach for daily activities. However, existing heuristic feature mapping methods are often coarse, resulting in only moderate recognition performance. In this paper, we propose a fine-grained daily activity feature mapping approach. Sensors are ranked by their significance using the PageRank algorithm, and a novel alignment algorithm is introduced for sensor mapping. Experiments conducted on the publicly available CASAS dataset demonstrate that the proposed method significantly outperforms existing daily activity feature mapping approaches.
Citation: Algorithms
PubDate: 2025-02-26
DOI: 10.3390/a18030131
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 132: Adaptive Machine Learning for Automatic
Load Optimization in Connected Smart Green Townhouses
Authors: Seyed Morteza Moghimi, Thomas Aaron Gulliver, Ilamparithi Thirumarai Chelvan, Hossen Teimoorinia
First page: 132
Abstract: This paper presents an adaptive Machine Learning (ML)-based framework for automatic load optimization in Connected Smart Green Townhouses (CSGTs) The system dynamically optimizes load consumption and transitions between grid-connected and island modes. Automatic mode transitions reduce the need for manual changes, ensuring reliable operation. Actual occupancy, load demand, weather, and energy price data are used to manage loads which improves efficiency, cost savings, and sustainability. An adaptive framework is employed that combines data processing and ML. A hybrid Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN) model is used to analyze time series and spatial data. Multi-Objective Particle Swarm Optimization (MOPSO) is employed to balance costs, carbon emissions, and efficiency. The results obtained show a 3–5% improvement in efficiency for grid-connected mode and 10–12% for island mode, as well as a 4–6% reduction in carbon emissions.
Citation: Algorithms
PubDate: 2025-03-02
DOI: 10.3390/a18030132
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 133: A Lightweight and Efficient Detection
Transformer for Highway Abandoned Objects
Authors: Biao Zhang, Chishe Wang, Jie Wang
First page: 133
Abstract: Abandoned objects on highways seriously threaten traffic safety, and their prompt identification and removal are crucial. Existing methods struggle to balance computational cost and detection accuracy due to the significant scale differences of abandoned objects on highways. To address these problems, we propose a Lightweight and Efficient Detection Transformer for highway abandoned objects (LE-DETR). This study first designs a real-time feature extraction module that effectively captures essential information and accelerates information flow. Building on this module, we construct a lightweight backbone network for feature extraction, enhancing parameter utilization. A Triple Fusion (TFusion) module is proposed, integrating high-level semantic information with low-level spatial information to increase detailed information. A Cross-Layer Multi-Scale Interaction (CMI) module is designed, utilizing large-kernel depth-wise convolutions of various sizes to extract features from different receptive fields, enhancing the multi-scale representation of abandoned objects. The LE-DETR model is trained and evaluated using a constructed Highway Abandoned Object Dataset (HAOD). The experimental results indicate that compared to the suboptimal RT-DETR-R18, LE-DETR improves accuracy by 6.5%, reduces the number of parameters by 27.1%, and decreases floating-point operations (FLOPs) by 21.1%. These improvements demonstrate the great potential of LE-DETR for detecting abandoned objects on highways.
Citation: Algorithms
PubDate: 2025-03-02
DOI: 10.3390/a18030133
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 134: Edge Detection Attention Module in Pure
Authors: Luella Marcos, Paul Babyn, Javad Alirezaie
First page: 134
Abstract: X-ray computed tomography (CT) is vital for medical diagnostics, but frequent radiation exposure raises concerns, driving the adoption of low-dose CT (LDCT) to mitigate risks. However, LDCT often introduces noise, compromising diagnostic accuracy. This paper proposes a pure vision transformer (PViT) for LDCT denoising, enhanced with a gradient–Laplacian attention module (GLAM) to improve edge preservation and fine structural detail reconstruction. The model’s robustness was validated across five diverse datasets (piglet, head, abdomen, chest, thoracic), demonstrating consistent performance in preserving anatomical structures. Extensive ablation studies on attention configurations and loss functions further substantiated the contributions of each module. Quantitative evaluation using PSNR and SSIM, alongside radiologist assessment, confirmed significant noise suppression and sharper anatomical boundaries, particularly in regions with fine details such as organ interfaces and bone structures. Additionally, in benchmark comparisons against state-of-the-art LDCT models (RED-CNN, TED-Net, DSC-GAN, DRL-EMP) and traditional methods (BM3D), the model exhibited lower parameter and stable training performance. These findings highlight the model’s robustness, efficiency, and clinical applicability, making it a promising solution for improving LDCT image quality while maintaining computational efficiency.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030134
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 135: Data Compression with a Time Limit
Authors: Bruno Carpentieri
First page: 135
Abstract: In this paper, we explore a framework to identify an optimal choice of compression algorithms that enables the best allocation of computing resources in a large-scale data storage environment: our goal is to maximize the efficiency of data compression given a time limit that must be observed by the compression process. We tested this approach with lossless compression of one-dimensional data (text) and two-dimensional data (images) and the experimental results demonstrate its effectiveness. We also extended this technique to lossy compression and successfully applied it to the lossy compression of two-dimensional data.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030135
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 136: Breast Cancer Classification Using an
Adapted Bump-Hunting Algorithm
Authors: Rym Nassih, Abdelaziz Berrado
First page: 136
Abstract: The Patient Rule Induction Method is a data mining technique used for identifying patterns in datasets, particularly focusing on discovering regions of the chosen input space where the response variable is unusually high or low. It falls in the subgroup discovery field, where finding small groups is more relevant for the explainability of the results, although it is not a classification technique, per se. In this paper, we introduce a new framework for breast cancer classification based on the PRIM. This new method involves, first, the random choice of different input spaces for each class label; second, the organization and pruning of the rules using metarules; and finally, it also includes the proposition of a way to handle the class overlapping and, hence, define the final classifier. The framework is tested on five real-life breast cancer datasets compared to three often-used algorithms for breast cancer classification: XG Boost, Logistic Regression, and Random Forest. Across the four metrics and datasets, both our PRIM-based framework and Random Forest demonstrate robust performance, with our framework showing notable accuracy and recall. XGBoost maintains strong F1-scores across the board, indicating balanced precision and recall. On the other hand, Logistic Regression, while competent, generally underperforms compared to the other algorithms, especially in terms of accuracy and recall, achieving 94.1% accuracy against 96.8% and 85.4% recall against 94.2% for the PRIM-based framework on the Wisconsin dataset.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030136
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 137: Computing Idle Times in Fuzzy Flexible Job
Shop Scheduling
Authors: Pablo García Gómez, Inés González-Rodríguez, Camino R. Vela
First page: 137
Abstract: The flexible job shop scheduling problem is relevant in many different areas. However, the usual deterministic approach sees its usefulness limited, as uncertainty plays a paramount role in real-world processes. Considering processing times in the form of fuzzy numbers is a computationally affordable way to model uncertainty that enhances the applicability of obtained solutions. Unfortunately, fuzzy processing times add an extra layer of complexity to otherwise straightforward operations. For example, in energy-aware environments, measuring the idle times of resources is of the utmost importance, but it goes from a trivial calculation in the deterministic setting to a critical modelling decision in fuzzy scenarios, where different approaches are possible. In this paper, we analyse the drawbacks of the existing translation of the deterministic approach to a fuzzy context and propose two alternative ways of computing the idle times in a schedule. We show that, unlike in the deterministic setting, the different definitions are not equivalent when fuzzy processing times are considered, and results are directly affected, depending on which one is used. We conclude that the new ways of computing idle times under uncertainty provide more reliable values and, hence, better schedules.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030137
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 138: LSTGINet: Local Attention Spatio-Temporal
Graph Inference Network for Age Prediction
Authors: Yi Lei, Xin Wen, Yanrong Hao, Ruochen Cao, Chengxin Gao, Peng Wang, Yuanyuan Guo, Rui Cao
First page: 138
Abstract: There is a close correlation between brain aging and age. However, traditional neural networks cannot fully capture the potential correlation between age and brain aging due to the limited receptive field. Furthermore, they are more concerned with deep spatial semantics, ignoring the fact that effective temporal information can enrich the representation of low-level semantics. To address these limitations, a local attention spatio-temporal graph inference network (LSTGINet) was developed to explore the details of the association between age and brain aging, taking into account both spatio-temporal and temporal perspectives. First, multi-scale temporal and spatial branches are used to increase the receptive field and model the age information simultaneously, achieving the perception of static correlation. Second, these spatio-temporal feature graphs are reconstructed, and large topographies are constructed. The graph inference node aggregation and transfer functions fully capture the hidden dynamic correlation between brain aging and age. A new local attention module is embedded in the graph inference component to enrich the global context semantics, establish dependencies and interactivity between different spatio-temporal features, and balance the differences in the spatio-temporal distribution of different semantics. We use a newly designed weighted loss function to supervise the learning of the entire prediction framework to strengthen the inference process of spatio-temporal correlation. The final experimental results show that the MAE on baseline datasets such as CamCAN and NKI are 6.33 and 6.28, respectively, better than the current state-of-the-art age prediction methods, and provides a basis for assessing the state of brain aging in adults.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030138
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 139: Automated Measurement of Grid Cell Firing
Characteristics
Authors: Nate M. Sutton, Blanca E. Gutiérrez-Guzmán, Holger Dannenberg, Giorgio A. Ascoli
First page: 139
Abstract: We describe GridMet as open-source software that automatically measures the spatial tuning parameters of grid cells, such as firing field size, spacing, and orientation angles. Applying these metrics to experimental data can help quantify changes in the geometric characteristics of grid cell firing across experimental conditions. GridMet uses clustering and other advanced methods to detect and characterize fields, increasing accuracy compared to alternative methods such as those based on peak firing. Novel contributions of this work include an effective approach for automated field size estimation and an original method for estimating field spacing that can overcome challenges encountered in other software. The user-friendly yet flexible design of GridMet aims to facilitate widespread community adoption. Specifically, GridMet allows basic usage with default parameter settings while also enabling the expert configuration of many parameter values for more advanced applications. Free release of the MATLAB source code will encourage the development of custom variations or integration with other software packages. At the same time, we also provide a runtime version of GridMet, thus avoiding the requirement to purchase any separate licenses. We have optimized GridMet for batch scripting workflows to aid investigations of multi-trial data on multiple grid cells.
Citation: Algorithms
PubDate: 2025-03-03
DOI: 10.3390/a18030139
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 140: Finding Multiple Optimal Solutions to an
Integer Linear Program by Random Perturbations of Its Objective Function
Authors: Noah Schulhof, Pattara Sukprasert, Eytan Ruppin, Samir Khuller, Alejandro A. Schäffer
First page: 140
Abstract: Integer linear programs (ILPs) and mixed integer programs (MIPs) often have multiple distinct optimal solutions, yet the widely used Gurobi optimization solver returns certain solutions at disproportionately high frequencies. This behavior is disadvantageous, as, in fields such as biomedicine, the identification and analysis of distinct optima yields valuable domain-specific insights that inform future research directions. In the present work, we introduce MORSE (Multiple Optima via Random Sampling and careful choice of the parameter Epsilon), a randomized, parallelizable algorithm to efficiently generate multiple optima for ILPs. MORSE maps multiplicative perturbations to the coefficients in an instance’s objective function, generating a modified instance that retains an optimum of the original problem. We formalize and prove the above claim in some practical conditions. Furthermore, we prove that for 0/1 selection problems, MORSE finds each distinct optimum with equal probability. We evaluate MORSE using two measures; the number of distinct optima found in r independent runs, and the diversity of the list (with repetitions) of solutions by average pairwise Hamming distance and Shannon entropy. Using these metrics, we provide empirical results demonstrating that MORSE outperforms the Gurobi method and unweighted variations of the MORSE method on a set of 20 Mixed Integer Programming Library (MIPLIB) instances and on a combinatorial optimization problem in cancer genomics.
Citation: Algorithms
PubDate: 2025-03-04
DOI: 10.3390/a18030140
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 141: Partitioning Strategies for Parallel
Computation of Flexible Skylines
Authors: Emilio De Lorenzis, Davide Martinenghi
First page: 141
Abstract: While classical skyline queries identify interesting data within large datasets, flexible skylines introduce preferences through constraints on attribute weights, and further reduce the data returned. However, computing these queries can be time-consuming for large datasets. We propose and implement a parallel computation scheme consisting of a parallel phase followed by a sequential phase, and apply it to flexible skylines. We assess the additional effect of an initial filtering phase to reduce dataset size before parallel processing, and the elimination of the sequential part (the most time-consuming) altogether. All our experiments are executed in the PySpark framework for a number of different datasets of varying sizes and dimensions.
Citation: Algorithms
PubDate: 2025-03-04
DOI: 10.3390/a18030141
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 142: Uncertainty Feasible Region Analysis for
Microgrids in the Coordination with Distribution System Considering
Interactive Power Deviation
Authors: Hao Dong, Peng Lu, Xiang Jiang, Xu Chen, Puyan Wang, Junpeng Zhu
First page: 142
Abstract: The coordination of microgrid (MG) and distribution is an emerging trend for future development. This paper proposes an uncertainty feasible region (UFR) analysis method based on outer approximation cutting (OAC) under the coordination of MG and distribution. Firstly, an optimal economic dispatch scheduling is obtained. It serves as the basis for the intraday analysis of UFR. Drawing on the concepts of robust optimization, a method for determining the intra-day UFR is proposed. Subsequently, the problem is transformed using duality theory by identifying umbrella constraints, ultimately linearizing the problem to enable its solution by commercial software. In the intra-day analysis of the feasible region, the interactive power deviation between the MG and the upper-level grid (ULG) is allowed, which is represented by an interactive power deviation factor (IPDF). Different factors represent varying sizes of controllable resources, and a larger factor positively affects the size of the feasible region, and the volume is used to represent the size of the feasible region. The UFR defined in this paper provides a theoretical basis for renewable energy consumption capacity corresponding to the day-ahead dispatch scheduling. The effectiveness of the proposed method is validated by simulation results in a typical MG scenario.
Citation: Algorithms
PubDate: 2025-03-04
DOI: 10.3390/a18030142
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 143: A Hair Drawing Evaluation Algorithm for
Authors: Yue Zhang, Nobuo Funabiki, Erita Cicilia Febrianti, Amang Sudarsono, Chenchien Hsu
First page: 143
Abstract: Nowadays, portrait drawing has become increasingly popular as a means of developing artistic skills and nurturing emotional expression. However, it is challenging for novices to start learning it, as they usually lack a solid grasp of proportions and structural foundations of the five senses. To address this problem, we have studied Portrait Drawing Learning Assistant System (PDLAS) for guiding novices by providing auxiliary lines of facial features, generated by utilizing OpenPose and OpenCV libraries. For PDLAS, we have also presented the exactness assessment method to evaluate drawing accuracy using the Normalized Cross-Correlation (NCC) algorithm. It calculates the similarity score between the drawing result and the initial portrait photo. Unfortunately, the current method does not assess the hair drawing, although it occupies a large part of a portrait and often determines its quality. In this paper, we present a hair drawing evaluation algorithm for the exactness assessment method to offer comprehensive feedback to users in PDLAS. To emphasize hair lines, this algorithm extracts the texture of the hair region by computing the eigenvalues and eigenvectors of the hair image. For evaluations, we applied the proposal to drawing results by seven students from Okayama University, Japan and confirmed the validity. In addition, we observed the NCC score improvement in PDLAS by modifying the face parts with low similarity scores from the exactness assessment method.
Citation: Algorithms
PubDate: 2025-03-04
DOI: 10.3390/a18030143
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 144: Advancing AI in Higher Education: A
Comparative Study of Large Language Model-Based Agents for Exam Question
Generation, Improvement, and Evaluation
Authors: Vlatko Nikolovski, Dimitar Trajanov, Ivan Chorbev
First page: 144
Abstract: The transformative capabilities of large language models (LLMs) are reshaping educational assessment and question design in higher education. This study proposes a systematic framework for leveraging LLMs to enhance question-centric tasks: aligning exam questions with course objectives, improving clarity and difficulty, and generating new items guided by learning goals. The research spans four university courses—two theory-focused and two application-focused—covering diverse cognitive levels according to Bloom’s taxonomy. A balanced dataset ensures representation of question categories and structures. Three LLM-based agents—VectorRAG, VectorGraphRAG, and a fine-tuned LLM—are developed and evaluated against a meta-evaluator, supervised by human experts, to assess alignment accuracy and explanation quality. Robust analytical methods, including mixed-effects modeling, yield actionable insights for integrating generative AI into university assessment processes. Beyond exam-specific applications, this methodology provides a foundational approach for the broader adoption of AI in post-secondary education, emphasizing fairness, contextual relevance, and collaboration. The findings offer a comprehensive framework for aligning AI-generated content with learning objectives, detailing effective integration strategies, and addressing challenges such as bias and contextual limitations. Overall, this work underscores the potential of generative AI to enhance educational assessment while identifying pathways for responsible implementation.
Citation: Algorithms
PubDate: 2025-03-04
DOI: 10.3390/a18030144
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 145: Prediction of Diabetes Using Statistical
and Machine Learning Modelling Techniques
Authors: Entissar Almutairi, Maysam Abbod, Ziad Hunaiti
First page: 145
Abstract: Statistical and machine learning modelling techniques have been effectively used in the healthcare domain and the prediction of epidemiological chronic diseases such as diabetes, which is classified as an epidemic due to its high rates of global prevalence. These techniques are useful for the processes of description, prediction, and evaluation of various diseases, including diabetes. This paper models diabetes disease in Saudi Arabia using the most relevant risk factors, namely smoking, obesity, and physical inactivity for adults aged ≥25 years. The aim of this study is based on developing statistical and machine learning models for the purpose of studying the trends in incidence rates of diabetes over 15 years (1999–2013) and to obtain predictions for future levels of the disease up to 2025, to support health policy planning and resource allocation for controlling diabetes. Different models were developed, namely Multiple Linear Regression (MLR), Support Vector Regression (SVR), Bayesian Linear Regression (BLM), Adaptive Neuro-Fuzzy Inference model (ANFIS), and Artificial Neural Network (ANN). The performance of the developed models is evaluated using four statistical metrices: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination R-squared. Based on the results, it can be observed that the overall performance for all proposed models was reasonably good; however, the best results were achieved by the ANFIS model with RMSE = 0.04 and R2 = 0.99 for men’s training data, and RMSE = 0.02 and R2 = 0.99 for women’s training data.
Citation: Algorithms
PubDate: 2025-03-05
DOI: 10.3390/a18030145
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 146: Dynamic Path Planning for Vehicles Based
on Causal State-Masking Deep Reinforcement Learning
Authors: Xia Hua, Tengteng Zhang, Jun Cao
First page: 146
Abstract: Dynamic path planning enables vehicles to autonomously navigate in unknown or continuously changing environments, thereby reducing reliance on fixed maps. Deep reinforcement learning (DRL), with its superior performance in handling high-dimensional state spaces and complex dynamic environments, has been widely applied to dynamic path planning. Traditional DRL methods are prone to capturing unnecessary noise information and irrelevant features during the training process, leading to instability and decreased adaptability of models in complex dynamic environments. To address this challenge, we propose a dynamic path-planning method based on our Causal State-Masking Twin-delayed Deep Deterministic Policy Gradient (CSM-TD3) algorithm. CSM-TD3 integrates a causal inference mechanism by introducing dynamic state masks and intervention mechanisms, allowing the policy network to focus on genuine causal features for decision optimization and thereby enhancing the convergence speed and generalization capabilities of the agent. Furthermore, causal state-masking DRL allows the system to learn the optimal mask configurations through backpropagation, enabling the model to adaptively adjust the causal features of interest. Extensive experimental results demonstrate that this method significantly enhances the convergence of the TD3 algorithm and effectively improves its performance in dynamic path planning.
Citation: Algorithms
PubDate: 2025-03-05
DOI: 10.3390/a18030146
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 147: Parallel CUDA-Based Optimization of the
Intersection Calculation Process in the Greiner–Hormann Algorithm
Authors: Jiwei Zuo, Junfu Fan, Kuan Li, Qingyun Liu, Yuke Zhou, Yi Zhang
First page: 147
Abstract: The Greiner–Hormann algorithm is a commonly used polygon overlay analysis algorithm. It uses a double-linked list structure to store vertex data, and its intersection calculation step has a significant effect on the overall operating efficiency of the algorithm. To address the time-consuming intersection calculation process in the Greiner–Hormann algorithm, this paper presents two kernel functions that implement a GPU parallel improvement algorithm based on CUDA multi-threading. This method allocates a thread to each edge of the subject polygon, determines in parallel whether it intersects with each edge of the clipping polygon, transfers the number of intersection points back to the CPU for calculation, and opens up corresponding storage space on the GPU side on the basis of the total number of intersection points; then, information such as intersection coordinates is calculated in parallel. In addition, experiments are conducted on the data of eight polygons with different complexities, and the optimal thread mode, running time, and speedup ratio of the parallel algorithm are statistically analyzed. The experimental results show that when a single CUDA thread block contains 64 threads or 128 threads, the parallel transformation step of the Greiner–Hormann algorithm has the highest computational efficiency. When the complexity of the subject polygon exceeds 53,000, the parallel improvement algorithm can obtain a speedup ratio of approximately three times that of the serial algorithm. This shows that the design method in this paper can effectively improve the operating efficiency of the polygon overlay analysis algorithm in the current large-scale data context.
Citation: Algorithms
PubDate: 2025-03-05
DOI: 10.3390/a18030147
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 148: CEEMDAN-IHO-SVM: A Machine Learning
Research Model for Valve Leak Diagnosis
Authors: Ruixue Wang, Ning Zhao
First page: 148
Abstract: Due to the complex operating environment of valves, when a fault occurs inside a valve, the vibration signal generated by the fault is easily affected by the environmental noise, making the extraction of fault features difficult. To address this problem, this paper proposes a feature extraction method based on the combination of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Fuzzy Entropy (FN). Due to the slow convergence speed and the tendency to fall into local optimal solutions of the Hippopotamus Optimization Algorithm (HO), an improved Hippopotamus Optimization (IHO) algorithm-optimized Support Vector Machine (SVM) model for valve leakage diagnosis is introduced to further enhance the accuracy of valve leakage diagnosis. The improved Hippopotamus Optimization algorithm initializes the hippopotamus population with Tent chaotic mapping, designs an adaptive weight factor, and incorporates adaptive variation perturbation. Moreover, the performance of IHO was proven to be optimal compared to HO, Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), and Sparrow Search Algorithm (SSA) by calculating twelve test functions. Subsequently, the IHO-SVM classification model was established and applied to valve leakage diagnosis. The prediction effects of the seven models, IHO-SVM. HO-SVM, PSO-SVM, GWO-SVM, WOA-SVM, SSA-SVM, and SVM were compared and analyzed with actual data. As a result, the comparison indicated that IHO-SVM has desirable robustness and generalization, which successfully improves the classification efficiency and the recognition rate in fault diagnosis.
Citation: Algorithms
PubDate: 2025-03-05
DOI: 10.3390/a18030148
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 149: Simple Rules of a Discrete Stochastic
Process Leading to Catalan-like Recurrences
Authors: Mariusz Białecki
First page: 149
Abstract: A method for obtaining integer sequences is presented by defining simple rules for the evolution of a discrete dynamical system. This paper demonstrates that various Catalan-like recurrences of known integer sequences can be obtained from a single stochastic process defined by simple rules. The resulting exact equations that describe the stationary state of the process are derived using combinatorial analysis. A specific reduction of the process is applied, and the solvability of the reduced system of equations is demonstrated. Then, a procedure for providing appropriate parameters for a given sequence is formulated. The general method is illustrated with examples of Catalan, Motzkin, Schröder, and A064641 integer sequences. We also point out that by appropriately changing the parameters of the system, one can smoothly transition between distributions related to Motzkin numbers and shifted Catalan numbers.
Citation: Algorithms
PubDate: 2025-03-06
DOI: 10.3390/a18030149
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 150: Real-Time Fuzzy Record-Matching Similarity
Metric and Optimal Q-Gram Filter
Authors: Ondřej Rozinek, Jaroslav Marek, Jan Panuš, Jan Mareš
First page: 150
Abstract: In this paper, we introduce an advanced Fuzzy Record Similarity Metric (FRMS) that improves approximate record matching and models human perception of record similarity. The FRMS utilizes a newly developed similarity space with favorable properties combined with a metric space, employing a bag-of-words model with general applications in text mining and cluster analysis. To optimize the FRMS, we propose a two-stage method for approximate string matching and search that outperforms baseline methods in terms of average time complexity and F measure on various datasets. In the first stage, we construct an optimal Q-gram count filter as an optimal lower bound for fuzzy token similarities such as FRMS. The approximated Q-gram count filter achieves a high accuracy rate, filtering over 99% of dissimilar records, with a constant time complexity of ≈O(1). In the second stage, FRMS runs for a polynomial time of approximately ≈O(n4) and models human perception of record similarity by maximum weight matching in a bipartite graph. The FRMS architecture has widespread applications in structured document storage such as databases and has already been commercialized by one of the largest IT companies. As a side result, we explain the behavior of the singularity of the Q-gram filter and the advantages of a padding extension. Overall, our method provides a more accurate and efficient approach to approximate string matching and search with real-time runtime.
Citation: Algorithms
PubDate: 2025-03-06
DOI: 10.3390/a18030150
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 151: Diagnosis and Management of Sexually
Transmitted Infections Using Artificial Intelligence Applications Among
Key and General Populations in Sub-Saharan Africa: A Systematic Review and
Meta-Analysis
Authors: Claris Siyamayambo, Edith Phalane, Refilwe Nancy Phaswana-Mafuya
First page: 151
Abstract: The Fourth Industrial Revolution (4IR) has significantly impacted healthcare, including sexually transmitted infection (STI) management in Sub-Saharan Africa (SSA), particularly among key populations (KPs) with limited access to health services. This review investigates 4IR technologies, including artificial intelligence (AI) and machine learning (ML), that assist in diagnosing, treating, and managing STIs across SSA. By leveraging affordable and accessible solutions, 4IR tools support KPs who are disproportionately affected by STIs. Following systematic review guidelines using Covidence, this study examined 20 relevant studies conducted across 20 SSA countries, with Ethiopia, South Africa, and Zimbabwe emerging as the most researched nations. All the studies reviewed used secondary data and favored supervised ML models, with random forest and XGBoost frequently demonstrating high performance. These tools assist in tracking access to services, predicting risks of STI/HIV, and developing models for community HIV clusters. While AI has enhanced the accuracy of diagnostics and the efficiency of management, several challenges persist, including ethical concerns, issues with data quality, and a lack of expertise in implementation. There are few real-world applications or pilot projects in SSA. Notably, most of the studies primarily focus on the development, validation, or technical evaluation of the ML methods rather than their practical application or implementation. As a result, the actual impact of these approaches on the point of care remains unclear. This review highlights the effectiveness of various AI and ML methods in managing HIV and STIs through detection, diagnosis, treatment, and monitoring. The study strengthens knowledge on the practical application of 4IR technologies in diagnosing, treating, and managing STIs across SSA. Understanding this has potential to improve sexual health outcomes, address gaps in STI diagnosis, and surpass the limitations of traditional syndromic management approaches.
Citation: Algorithms
PubDate: 2025-03-07
DOI: 10.3390/a18030151
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 152: A Novel Equivariant Self-Supervised Vector
Network for Three-Dimensional Point Clouds
Authors: Kedi Shen, Jieyu Zhao, Min Xie
First page: 152
Abstract: For networks that process 3D data, estimating the orientation and position of 3D objects is a challenging task. This is because the traditional networks are not robust to the rotation of the data, and their internal workings are largely opaque and uninterpretable. To solve this problem, a novel equivariant self-supervised vector network for point clouds is proposed. The network can learn the rotation direction information of the 3D target and estimate the rotational pose change of the target, and the interpretability of the equivariant network is studied using information theory. The utilization of vector neurons within the network lifts the scalar data to vector representations, enabling the network to learn the pose information inherent in the 3D target. The network can perform complex rotation-equivariant tasks after pre-training, and it shows impressive performance in complex tasks like category-level pose change estimation and rotation-equivariant reconstruction. We demonstrate through experiments that our network can accurately detect the orientation and pose change of point clouds and visualize the latent features. Moreover, it performs well in invariant tasks such as classification and category-level segmentation.
Citation: Algorithms
PubDate: 2025-03-07
DOI: 10.3390/a18030152
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 153: The Euler-Type Universal Numerical
Integrator (E-TUNI) with Backward Integration
Authors: Paulo M. Tasinaffo, Gildárcio S. Gonçalves, Johnny C. Marques, Luiz A. V. Dias, Adilson M. da da Cunha
First page: 153
Abstract: The Euler-Type Universal Numerical Integrator (E-TUNI) is a discrete numerical structure that couples a first-order Euler-type numerical integrator with some feed-forward neural network architecture. Thus, E-TUNI can be used to model non-linear dynamic systems when the real-world plant’s analytical model is unknown. From the discrete solution provided by E-TUNI, the integration process can be either forward or backward. Thus, in this article, we intend to use E-TUNI in a backward integration framework to model autonomous non-linear dynamic systems. Three case studies, including the dynamics of the non-linear inverted pendulum, were developed to verify the computational and numerical validation of the proposed model.
Citation: Algorithms
PubDate: 2025-03-08
DOI: 10.3390/a18030153
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 154: An Adaptive Feature-Based Quantum Genetic
Algorithm for Dimension Reduction with Applications in Outlier Detection
Authors: Tin H. Pham, Bijan Raahemi
First page: 154
Abstract: Dimensionality reduction is essential in machine learning, reducing dataset dimensions while enhancing classification performance. Feature Selection, a key subset of dimensionality reduction, identifies the most relevant features. Genetic Algorithms (GA) are widely used for feature selection due to their robust exploration and efficient convergence. However, GAs often suffer from premature convergence, getting stuck in local optima. Quantum Genetic Algorithm (QGA) address this limitation by introducing quantum representations to enhance the search process. To further improve QGA performance, we propose an Adaptive Feature-Based Quantum Genetic Algorithm (FbQGA), which strengthens exploration and exploitation through quantum representation and adaptive quantum rotation. The rotation angle dynamically adjusts based on feature significance, optimizing feature selection. FbQGA is applied to outlier detection tasks and benchmarked against basic GA and QGA variants on five high-dimensional, imbalanced datasets. Performance is evaluated using metrics like classification accuracy, F1 score, precision, recall, selected feature count, and computational cost. Results consistently show FbQGA outperforming other methods, with significant improvements in feature selection efficiency and computational cost. These findings highlight FbQGA’s potential as an advanced tool for feature selection in complex datasets.
Citation: Algorithms
PubDate: 2025-03-08
DOI: 10.3390/a18030154
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 155: Text-Guided Synthesis in Medical
Multimedia Retrieval: A Framework for Enhanced Colonoscopy Image
Classification and Segmentation
Authors: Ojonugwa Oluwafemi Ejiga Peter, Opeyemi Taiwo Adeniran, Adetokunbo MacGregor John-Otumu, Fahmi Khalifa, Md Mahmudur Rahman
First page: 155
Abstract: The lack of extensive, varied, and thoroughly annotated datasets impedes the advancement of artificial intelligence (AI) for medical applications, especially colorectal cancer detection. Models trained with limited diversity often display biases, especially when utilized on disadvantaged groups. Generative models (e.g., DALL-E 2, Vector-Quantized Generative Adversarial Network (VQ-GAN)) have been used to generate images but not colonoscopy data for intelligent data augmentation. This study developed an effective method for producing synthetic colonoscopy image data, which can be used to train advanced medical diagnostic models for robust colorectal cancer detection and treatment. Text-to-image synthesis was performed using fine-tuned Visual Large Language Models (LLMs). Stable Diffusion and DreamBooth Low-Rank Adaptation produce images that look authentic, with an average Inception score of 2.36 across three datasets. The validation accuracy of various classification models Big Transfer (BiT), Fixed Resolution Residual Next Generation Network (FixResNeXt), and Efficient Neural Network (EfficientNet) were 92%, 91%, and 86%, respectively. Vision Transformer (ViT) and Data-Efficient Image Transformers (DeiT) had an accuracy rate of 93%. Secondly, for the segmentation of polyps, the ground truth masks are generated using Segment Anything Model (SAM). Then, five segmentation models (U-Net, Pyramid Scene Parsing Network (PSNet), Feature Pyramid Network (FPN), Link Network (LinkNet), and Multi-scale Attention Network (MANet)) were adopted. FPN produced excellent results, with an Intersection Over Union (IoU) of 0.64, an F1 score of 0.78, a recall of 0.75, and a Dice coefficient of 0.77. This demonstrates strong performance in terms of both segmentation accuracy and overlap metrics, with particularly robust results in balanced detection capability as shown by the high F1 score and Dice coefficient. This highlights how AI-generated medical images can improve colonoscopy analysis, which is critical for early colorectal cancer detection.
Citation: Algorithms
PubDate: 2025-03-09
DOI: 10.3390/a18030155
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 156: Quantum Computing and Machine Learning in
Medical Decision-Making: A Comprehensive Review
Authors: James C. L. Chow
First page: 156
Abstract: Medical decision-making is increasingly integrating quantum computing (QC) and machine learning (ML) to analyze complex datasets, improve diagnostics, and enable personalized treatments. While QC holds the potential to accelerate optimization, drug discovery, and genomic analysis as hardware capabilities advance, current implementations remain limited compared to classical computing in many practical applications. Meanwhile, ML has already demonstrated significant success in medical imaging, predictive modeling, and decision support. Their convergence, particularly through quantum machine learning (QML), presents opportunities for future advancements in processing high-dimensional healthcare data and improving clinical outcomes. This review examines the foundational concepts, key applications, and challenges of these technologies in healthcare, explores their potential synergy in solving clinical problems, and outlines future directions for quantum-enhanced ML in medical decision-making.
Citation: Algorithms
PubDate: 2025-03-09
DOI: 10.3390/a18030156
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 157: AI Under Attack: Metric-Driven Analysis of
Authors: Sarfraz Brohi, Qurat-ul-ain Mastoi
First page: 157
Abstract: Incorporating Artificial Intelligence (AI) in healthcare has transformed disease diagnosis and treatment by offering unprecedented benefits. However, it has also revealed critical cybersecurity vulnerabilities in Deep Learning (DL) models, which raise significant risks to patient safety and their trust in AI-driven applications. Existing studies primarily focus on theoretical vulnerabilities or specific attack types, leaving a gap in understanding the practical implications of multiple attack scenarios on healthcare AI. In this paper, we provide a comprehensive analysis of key attack vectors, including adversarial attacks, such as the gradient-based Fast Gradient Sign Method (FGSM), evasion attacks (perturbation-based), and data poisoning, which threaten the reliability of DL models, with a specific focus on breast cancer detection. We propose the Healthcare AI Vulnerability Assessment Algorithm (HAVA) that systematically simulates these attacks, calculates the Post-Attack Vulnerability Index (PAVI), and quantitatively evaluates their impacts. Our findings revealed that the adversarial FGSM and evasion attacks significantly reduced model accuracy from 97.36% to 61.40% (PAVI: 0.385965) and 62.28% (PAVI: 0.377193), respectively, demonstrating their severe impact on performance, but data poisoning had a milder effect, retaining 89.47% accuracy (PAVI: 0.105263). The confusion matrices also revealed a higher rate of false positives in the adversarial FGSM and evasion attacks than more balanced misclassification patterns observed in data poisoning. By proposing a unified framework for quantifying and analyzing these post-attack vulnerabilities, this research contributes to formulating resilient AI models for critical domains where accuracy and reliability are important.
Citation: Algorithms
PubDate: 2025-03-10
DOI: 10.3390/a18030157
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 158: Gradual Optimization of University Course
Scheduling Problem Using Genetic Algorithm and Dynamic Programming
Authors: Xu Han, Dian Wang
First page: 158
Abstract: The university course scheduling problem (UCSP) is a challenging combinatorial optimization problem that requires optimization of the quality of the schedule and resource utilization while meeting multiple constraints involving courses, teachers, students, and classrooms. Although various algorithms have been applied to solve the UCSP, most of the existing methods are limited to scheduling independent courses, neglecting the impact of joint courses on the overall scheduling results. To address this limitation, this paper proposed an innovative mixed-integer linear programming model capable of handling the complex constraints of both joint and independent courses simultaneously. To improve the computational efficiency and solution quality, a hybrid method combining a genetic algorithm and dynamic programming, named POGA-DP, was designed. Compared to the traditional algorithms, POGA-DP introduced exchange operations based on a judgment mechanism and mutation operations with a forced repair mechanism to effectively avoid local optima. Additionally, by incorporating a greedy algorithm for classroom allocation, the utilization of classroom resources was further enhanced. To verify the performance of the new method, this study not only tested it on real UCSP instances at Beijing Forestry University but also conducted comparative experiments with several classic algorithms, including a traditional GA, Ant Colony Optimization (ACO), the Producer–Scrounger Method (PSM), and particle swarm optimization (PSO). The results showed that POGA-DP improved the scheduling quality by 46.99% compared to that of the traditional GA and reduced classroom usage by up to 29.27%. Furthermore, POGA-DP increased the classroom utilization by 0.989% compared to that with the traditional GA and demonstrated an outstanding performance in solving joint course scheduling problems. This study also analyzed the stability of the scheduling results, revealing that POGA-DP maintained a high level of consistency in scheduling across adjacent weeks, proving its feasibility and stability in practical applications. In conclusion, POGA-DP outperformed the existing algorithms in the UCSP, making it particularly suitable for efficient scheduling under complex constraints.
Citation: Algorithms
PubDate: 2025-03-10
DOI: 10.3390/a18030158
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 159: Total Outer-Independent Domination Number:
Bounds and Algorithms
Authors: Paul Bosch, Ernesto Parra Inza, Ismael Rios Villamar, José Luis Sánchez-Santiesteban
First page: 159
Abstract: In graph theory, the study of domination sets has garnered significant interest due to its applications in network design and analysis. Consider a graph G(V,E); a subset of its vertices is a total dominating set (TDS) if, for each x∈V(G), there exists an edge in E(G) connecting x to at least one vertex within this subset. If the subgraph induced by the vertices outside the TDS has no edges, the set is called a total outer-independent dominating set (TOIDS). The total outer-independent domination number, denoted as γtoi(G), represents the smallest cardinality of such a set. Deciding if a given graph has a TOIDS with at most r vertices is an NP-complete problem. This study introduces new lower and upper bounds for γtoi(G) and presents an exact solution approach using integer linear programming (ILP). Additionally, we develop a heuristic and a procedure to efficiently obtain minimal TOIDS.
Citation: Algorithms
PubDate: 2025-03-10
DOI: 10.3390/a18030159
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 160: Hybrid Optimization Algorithm for Solving
Attack-Response Optimization and Engineering Design Problems
Authors: Ahmad K. Al Hwaitat, Hussam N. Fakhouri, Jamal Zraqou, Najem Sirhan
First page: 160
Abstract: This paper presents JADEDO, a hybrid optimization method that merges the dandelion optimizer’s (DO) dispersal-inspired stages with JADE’s (adaptive differential evolution) dynamic mutation and crossover operators. By integrating these complementary mechanisms, JADEDO effectively balances global exploration and local exploitation for both unimodal and multimodal search spaces. Extensive benchmarking against classical and cutting-edge metaheuristics on the IEEE CEC2022 functions—encompassing unimodal, multimodal, and hybrid landscapes—demonstrates that JADEDO achieves highly competitive results in terms of solution accuracy, convergence speed, and robustness. Statistical analysis using Wilcoxon sum-rank tests further underscores JADEDO’s consistent advantage over several established optimizers, reflecting its proficiency in navigating complex, high-dimensional problems. To validate its real-world applicability, JADEDO was also evaluated on three engineering design problems (pressure vessel, spring, and speed reducer). Notably, it achieved top-tier or near-optimal designs in constrained, high-stakes environments. Moreover, to demonstrate suitability for security-oriented tasks, JADEDO was applied to an attack-response optimization scenario, efficiently identifying cost-effective, low-risk countermeasures under stringent time constraints. These collective findings highlight JADEDO as a robust, flexible, and high-performing framework capable of tackling both benchmark-oriented and practical optimization challenges.
Citation: Algorithms
PubDate: 2025-03-10
DOI: 10.3390/a18030160
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 161: Deep Learning in Financial Modeling:
Predicting European Put Option Prices with Neural Networks
Authors: Zakaria Elbayed, Abdelmjid Qadi EI Idrissi
First page: 161
Abstract: This paper explores the application of deep neural networks (DNNs) as an alternative to the traditional Black–Scholes model for predicting European put option prices. Using synthetic datasets generated under the Black–Scholes framework, the proposed DNN achieved strong predictive performance, with a Mean Squared Error (MSE) of 0.0021 and a coefficient of determination (R2) of 0.9533. This study highlights the scalability and adaptability of DNNs to complex financial systems, offering potential applications in real-time risk management and the pricing of exotic derivatives. While synthetic datasets provide a controlled environment, this study acknowledges the challenges of extending the model to real-world financial data, paving the way for future research to address these limitations.
Citation: Algorithms
PubDate: 2025-03-11
DOI: 10.3390/a18030161
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 162: Control of High-Power Slip Ring Induction
Generator Wind Turbines at Variable Wind Speeds in Optimal and Reliable
Modes
Authors: Mircea-Bogdan Radac, Valentin-Dan Muller, Samuel Ciucuriță
First page: 162
Abstract: This work analyzes high-power wind turbines (WTs) from the Oravita region, Romania. These WTs are based on slip ring induction generator with wound rotor and we propose a modified architecture with two power converters on both the stator and on the rotor, functioning at variable wind speeds spanning a large interval. Investigations developed around a realistic WT model with doubly fed induction generator show how WT control enables variable wind speed operations at optimal mechanical angular speed (MAS), guaranteeing maximal power point (MPP), but only up to a critical wind speed value, after which the electrical power must saturate for reliable operation. In this reliable operating region, blade pitch angle control must be enforced. Variable wind speed acts as a time-varying parameter disturbance but also imposes the MPP operation setpoint in one of the two analyzed regions. To achieve null tracking errors, a double integrator must appear within the MAS controller when the wind speed disturbance is realistically modeled as a ramp-like input; however, inspecting the linearized model reveals several difficulties as described in the paper, together with the proposed solution tradeoff. The study developed around the Fuhrlander-FL-MD-70 1.5[MW] WT model shows that several competitive controllers are designed and tested in the identified operating regions of interest, as they validate the reliable and performant functioning specifications.
Citation: Algorithms
PubDate: 2025-03-11
DOI: 10.3390/a18030162
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 163: Explainable MRI-Based Ensemble Learnable
Architecture for Alzheimer’s Disease Detection
Authors: Opeyemi Taiwo Adeniran, Blessing Ojeme, Temitope Ezekiel Ajibola, Ojonugwa Oluwafemi Ejiga Peter, Abiola Olayinka Ajala, Md Mahmudur Rahman, Fahmi Khalifa
First page: 163
Abstract: With the advancements in deep learning methods, AI systems now perform at the same or higher level than human intelligence in many complex real-world problems. The data and algorithmic opacity of deep learning models, however, make the task of comprehending the input data information, the model, and model’s decisions quite challenging. This lack of transparency constitutes both a practical and an ethical issue. For the present study, it is a major drawback to the deployment of deep learning methods mandated with detecting patterns and prognosticating Alzheimer’s disease. Many approaches presented in the AI and medical literature for overcoming this critical weakness are sometimes at the cost of sacrificing accuracy for interpretability. This study is an attempt at addressing this challenge and fostering transparency and reliability in AI-driven healthcare solutions. The study explores a few commonly used perturbation-based interpretability (LIME) and gradient-based interpretability (Saliency and Grad-CAM) approaches for visualizing and explaining the dataset, models, and decisions of MRI image-based Alzheimer’s disease identification using the diagnostic and predictive strengths of an ensemble framework comprising Convolutional Neural Networks (CNNs) architectures (Custom multi-classifier CNN, VGG-19, ResNet, MobileNet, EfficientNet, DenseNet), and a Vision Transformer (ViT). The experimental results show the stacking ensemble achieving a remarkable accuracy of 98.0% while the hard voting ensemble reached 97.0%. The findings present a valuable contribution to the growing field of explainable artificial intelligence (XAI) in medical imaging, helping end users and researchers to gain deep understanding of the backstory behind medical image dataset and deep learning model’s decisions.
Citation: Algorithms
PubDate: 2025-03-13
DOI: 10.3390/a18030163
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 164: A Two-Stage Multi-Objective Optimization
Algorithm for Solving Large-Scale Optimization Problems
Authors: Jiaqi Liu, Tianyu Liu
First page: 164
Abstract: For large-scale multi-objective optimization, it is particularly challenging for evolutionary algorithms to converge to the Pareto Front. Most existing multi-objective evolutionary algorithms (MOEAs) handle convergence and diversity in a mutually dependent manner during the evolution process. In this case, the performance degradation of one solution may lead to the deterioration of the performance of the other solution. This paper proposes a two-stage multi-objective optimization algorithm based on decision variable clustering (LSMOEA-VT) to solve large-scale optimization problems. In LSMOEA-VT, decision variables are divided into two categories and use dimensionality reduction methods to optimize the variables that affect evolutionary convergence. Following this, we performed an interdependence analysis to break down the convergence variables into multiple subcomponents that are more tractable. Furthermore, a non-dominated dynamic weight aggregation method is used to enhance the diversity of the population. To evaluate the performance of our proposed algorithm, we performed extensive comparative experiments against four optimization algorithms across a diverse set of benchmark problems, including eight multi-objective optimization problems and nine large-scale optimization problems. The experimental results show that our proposed algorithm performs well on some test functions and has certain competitiveness.
Citation: Algorithms
PubDate: 2025-03-13
DOI: 10.3390/a18030164
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 165: Where to Split in Hybrid Genetic Search
for the Capacitated Vehicle Routing Problem
Authors: Lars Magnus Hvattum
First page: 165
Abstract: One of the best heuristic algorithms for solving the capacitated vehicle routing problem is a hybrid genetic search. A critical component of the search is a splitting procedure, where a solution encoded as a giant tour of nodes is optimally split into vehicle routes using dynamic programming. However, the current state-of-the-art implementation of the splitting procedure assumes that the start of the giant tour is fixed as a part of the encoded solution. This paper examines whether the fixed starting point is a significant drawback. Results indicate that simple adjustments of the starting point for the splitting procedure can improve the performance of the genetic search, as measured by the average primal gaps of the final solutions obtained, by 3.9%.
Citation: Algorithms
PubDate: 2025-03-13
DOI: 10.3390/a18030165
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 166: A GNN-Based False Data Detection Scheme
for Smart Grids
Authors: Junhong Qiu, Xinxin Zhang, Tao Wang, Huiying Hou, Siyuan Wang, Tiejun Yang
First page: 166
Abstract: A Cyber-Physical System (CPS) incorporates communication dynamics and software into phsical processes, providing abstractions, modeling, design, and analytical techniques for the system. Based on spatial temporal graph neural networks (STGNNs), anomaly detection technology has been presented to detect anomaly data in smart grids with good performance. However, since topological changes of power networks in smart grids often already predict the occurrence of anomalies, traditional models based on STGNNs to portray network evolution cannot be directly utilized in smart grids. Our research proposed a smart grid anomaly detection method on the grounds of STGNNs, which used evolution in the information of several attributes that affected the power network to represent the evolution of the power network, subsequently used STGNNs to obtain the time-space dependencies of nodes in several information networks, and used a cross-domain method to help the anomaly detection of the power network through anomaly information of other related networks. Laboratory findings reveal that the abnormal data detection rate of our scheme reaches 90% in the initial stage of data transmission and outperforms other comparative methods, and as time goes by, the detection rate becomes higher and higher.
Citation: Algorithms
PubDate: 2025-03-14
DOI: 10.3390/a18030166
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 167: Decoding PM2.5 Prediction in Nanning Urban
Area, China: Unraveling Model Superiorities and Drawbacks Through SARIMA,
Prophet, and LightGBM
Authors: Minru Chen, Binglin Liu, Mingzhi Liang, Nini Yao
First page: 167
Abstract: With the rapid development of industrialization and urbanization, air pollution is becoming increasingly serious. Accurate prediction of PM2.5 concentration is of great significance to environmental protection and public health. Our study takes Nanning urban area, which has unique geographical, climatic and pollution source characteristics, as the object. Based on the dual-time resolution raster data of the China High-resolution and High-quality PM2.5 Dataset (CHAP) from 2012 to 2023, the PM2.5 concentration prediction study is carried out using SARIMA, Prophet and LightGBM models. The study systematically compares the performance of each model from the spatial and temporal dimensions using indicators such as mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2). The results show that the LightGBM model has a strong ability to mine complex nonlinear relationships, but its stability is poor. The Prophet model has obvious advantages in dealing with seasonality and trend of time series, but it lacks adaptability to complex changes. The SARIMA model is based on time series prediction theory and performs well in some scenarios, but has limitations in dealing with non-stationary data and spatial heterogeneity. Our research provides a multi-dimensional model performance reference for subsequent PM2.5 concentration predictions, helps researchers select models reasonably according to different scenarios and needs, provides new ideas for analyzing concentration change patterns, and promotes the development of related research in the field of environmental science.
Citation: Algorithms
PubDate: 2025-03-14
DOI: 10.3390/a18030167
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 168: Chinese Story Generation Based on Style
Control of Transformer Model and Content Evaluation Method
Authors: Jhe-Wei Lin, Tang-Wei Su, Che-Cheng Chang
First page: 168
Abstract: Natural language processing (NLP) has numerous applications and has been extensively developed in deep learning. In recent years, language models such as Transformer, BERT, and GPT have frequently been the foundation for related research. However, relatively few studies have focused on evaluating the quality of generated sentences. While traditional evaluation methods like BLEU can be applied, the challenge is that there is no ground truth reference for generated sentences, making it difficult to establish a reliable evaluation criterion. Therefore, this study examines the content generated by Bidirectional Encoder Representations and related recurrent methods based on the Transformer model. Specifically, we focus on analyzing sentence fluency by assessing the degree of part-of-speech (PoS) matching and the coherence of PoS context ordering. Determining whether the generated sentences align with the expected PoS structure of the model is crucial, as it significantly impacts the readability of the generated text.
Citation: Algorithms
PubDate: 2025-03-14
DOI: 10.3390/a18030168
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 169: An Alternative Estimator for
Poisson–Inverse-Gaussian Regression: The Modified
Kibria–Lukman Estimator
Authors: Rasha A. Farghali, Adewale F. Lukman, Zakariya Algamal, Murat Genc, Hend Attia
First page: 169
Abstract: Poisson regression is used to model count response variables. The method has a strict assumption that the mean and variance of the response variable are equal, while, in practice, the case of overdispersion is common. Also, in multicollinearity, the model parameter estimates obtained with the maximum likelihood estimator are adversely affected. This paper introduces a new biased estimator that extends the modified Kibria–Lukman estimator to the Poisson–Inverse-Gaussian regression model to deal with overdispersion and multicollinearity in the data. The superiority of the proposed estimator over the existing biased estimators is presented in terms of matrix and scalar mean square error. Moreover, the performance of the proposed estimator is examined through a simulation study. Finally, on a real dataset, the superiority of the proposed estimator over other estimators is demonstrated.
Citation: Algorithms
PubDate: 2025-03-14
DOI: 10.3390/a18030169
Issue No: Vol. 18, No. 3 (2025)
- Algorithms, Vol. 18, Pages 70: Advantages of Density in Tensor Network
Geometries for Gradient-Based Training
Authors: Sergi Masot-Llima, Artur Garcia-Saez
First page: 70
Abstract: Tensor networks are a very powerful data structure tool originating from simulations of quantum systems. In recent years, they have seen increased use in machine learning, mostly in trainings with gradient-based techniques, due to their flexibility and performance achieved by exploiting hardware acceleration. As ansatzes, tensor networks can be used with flexible geometries, and it is known that for highly regular ones, their dimensionality has a large impact on performance and representation power. For heterogeneous structures, however, these effects are not completely characterized. In this article, we train tensor networks with different geometries to encode a random quantum state, and see that densely connected structures achieve better infidelities than more sparse structures, with higher success rates and less time. Additionally, we give some general insight on how to improve the memory requirements of these sparse structures and the impact of such improvement on the trainings. Finally, as we use HPC resources for the calculations, we discuss the requirements for this approach and showcase performance improvements with GPU acceleration on a last-generation supercomputer.
Citation: Algorithms
PubDate: 2025-01-31
DOI: 10.3390/a18020070
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 71: EGSDK-Net: Edge-Guided Stepwise Dual Kernel
Update Network for Panoptic Segmentation
Authors: Pengyu Mu, Hongwei Zhao, Ke Ma
First page: 71
Abstract: In recent years, panoptic segmentation has garnered increasing attention from researchers aiming to better understand scenes in images. Although many excellent studies have been proposed, they share some common unresolved issues. Firstly, panoptic segmentation, as a novel task, is still confined within inherent frameworks. Secondly, the prevalent kernel update strategies do not adequately utilize the information from each stage. To address these two issues, redwe propose an edge-guided stepwise dual kernel update network (EGSDK-Net) for panoptic segmentation; the core components are the real-time edge guidance module and the stepwise dual kernel update module. The first component, after extracting and positioning edge features through an extra branch, applies these features to the normally transmitted feature maps within the network to highlight the edges. The input image is initially processed with the Canny edge detector to generate and store the predicted edge map, which acts as the ground truth for supervising the extracted edge feature map. The stepwise dual kernel update module enhances the utilization of information by allowing each stage to update both its own kernel and that of the subsequent stage, thereby improving the judgment capabilities of the kernels. redEGSDK-Net achieves a PQ of 60.6, representing a 2.19% improvement over RT-K-Net.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020071
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 72: Do What You Say—Computing Personal
Values Associated with Professions Based on the Words They Use
Authors: Aditya Jha, Peter A. Gloor
First page: 72
Abstract: Members of a profession frequently show similar personality characteristics. In this research, we leverage recent advances in NLP to compute personal values using a moral values framework, distinguishing between four different personas that assist in categorizing different professions by personal values: “fatherlanders”—valuing tradition and authority, “nerds”—valuing scientific achievements, “spiritualists”—valuing compassion and non-monetary achievements, and “treehuggers”—valuing sustainability and the environment. We collected 200 YouTube videos and podcasts for each professional category of lawyers, academics, athletes, engineers, creatives, managers, and accountants, converting their audio to text. We also categorize these professions by team player personas into “bees”—collaborative creative team players, “ants”—competitive hard workers, and “leeches”—selfish egoists using pre-trained models. We find distinctive personal value profiles for each of our seven professions computed from the words that members of each profession use.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020072
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 73: Intelligent Multi-Fault Diagnosis for a
Simplified Aircraft Fuel System
Authors: Jiajin Li, Steve King, Ian Jennions
First page: 73
Abstract: Machine learning (ML) techniques are increasingly used to diagnose faults in aerospace applications, but diagnosing multiple faults in aircraft fuel systems (AFSs) remains challenging due to complex component interactions. This paper evaluates the accuracy and introduces an innovative approach to quantify and compare the interpretability of four ML classification methods—artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs), and logistic regressions (LRs)—for diagnosing fault combinations present in AFSs. While the ANN achieved the highest diagnostic accuracy at 90%, surpassing other methods, its interpretability was limited. By contrast, the decision tree model showed an 82% consistency between global explanations and engineering insights, highlighting its advantage in interpretability despite the lower accuracy. Interpretability was assessed using two widely accepted tools, LIME and SHAP, alongside engineering understanding. These findings underscore a trade-off between prediction accuracy and interpretability, which is critical for trust in ML applications in aerospace. Although an ANN can deliver high diagnostic accuracy, a decision tree offers more transparent results, facilitating better alignment with engineering expectations even at a slight cost to accuracy.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020073
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 74: Optimizing Apache Spark MLlib: Predictive
Performance of Large-Scale Models for Big Data Analytics
Authors: Leonidas Theodorakopoulos, Aristeidis Karras, George A. Krimpas
First page: 74
Abstract: In this study, we analyze the performance of the machine learning operators in Apache Spark MLlib for K-Means, Random Forest Regression, and Word2Vec. We used a multi-node Spark cluster along with collected detailed execution metrics computed from the data of diverse datasets and parameter settings. The data were used to train predictive models that had up to 98% accuracy in forecasting performance. By building actionable predictive models, our research provides a unique treatment for key hyperparameter tuning, scalability, and real-time resource allocation challenges. Specifically, the practical value of traditional models in optimizing Apache Spark MLlib workflows was shown, achieving up to 30% resource savings and a 25% reduction in processing time. These models enable system optimization, reduce the amount of computational overheads, and boost the overall performance of big data applications. Ultimately, this work not only closes significant gaps in predictive performance modeling, but also paves the way for real-time analytics over a distributed environment.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020074
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 75: A Novel Model for Noninvasive Haemoglobin
Detection Based on Visibility Network and Clustering Network for
Multi-Wavelength PPG Signals
Authors: Lei Liu, Ziyi Wang, Xiaohan Zhang, Yan Zhuang, Yongbo Liang
First page: 75
Abstract: Non-invasive haemoglobin (Hb) testing devices enable large-scale haemoglobin screening, but their accuracy is not comparable to traditional blood tests. To this end, this paper aims to design a non-invasive haemoglobin testing device and propose a classification-regression prediction framework for non-invasive testing of haemoglobin using visibility graphs (VG) with network clustering of multi-sample pulse-wave-weighted undirected graphs as the features to optimize the detection accuracy of non-invasive haemoglobin measurements. Different prediction methods were compared by analyzing 608 segments of multiwavelength fingertip PPG signal data from 152 volunteers and analyzing and comparing the data and methods. The results showed that the classification using NVG with complex network clustering as features in the interval classification model was the best, with its classification accuracy (acc) of 93.35% and model accuracy of 88.28%. Among the regression models, the classification regression stack: SVM-Light Gradient Boosting Machine (LGBM) was the most effective, with a Mean Absolute Error (MAE) of 6.67 g/L, a Root Mean Square Error (RMSE) of 8.21 g/L, and an R-Square (R2) of 0.64. The results of this study indicate that the use of complex network technology in non-invasive haemoglobin detection can effectively improve its accuracy, and the detector designed in this study is promising to carry out a more accurate large-scale haemoglobin screening.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020075
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 76: Broadcasting in Stars of Cliques and
Path-Connected Cliques
Authors: Akash Ambashankar, Hovhannes A. Harutyunyan
First page: 76
Abstract: Broadcasting is a fundamental information dissemination problem in a connected network where one node, referred to as the originator, must distribute a message to all other nodes through a series of calls along the network’s links. Once informed, nodes assist the originator by forwarding the message to their neighbors. Determining the broadcast time for a node in an arbitrary network is NP-complete. While polynomial-time algorithms exist for specific network topologies, the problem remains open for many others. In this paper, we focus on addressing the broadcasting problem in network topologies represented by specialized clique-based structures. Specifically, we investigate the windmill graph Wdk,l, which consists of k cliques of size l connected to a universal node, and extend our study to the star of cliques, a generalization of the windmill graph with cliques of arbitrary sizes. Our primary objective is to propose an efficient algorithm for determining the broadcast time of any node in an arbitrary star of cliques and to rigorously prove its optimality. Additionally, we broaden the scope by examining the broadcasting problem in path-connected cliques, a topology featuring k cliques of varying sizes sequentially connected along a path. For this structure, we develop a computationally efficient algorithm that leverages clique sizes and adjacency to optimize broadcast strategies, with broader implications for understanding communication in block graphs.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020076
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 77: Seizure Detection in Medical IoT: Hybrid
CNN-LSTM-GRU Model with Data Balancing and XAI Integration
Authors: Hanaa Torkey, Sonia Hashish, Samia Souissi, Ezz El-Din Hemdan, Amged Sayed
First page: 77
Abstract: The brain acts as the body’s central command, overseeing diverse functions including thought, memory, speech, movement, and the regulation of various organs. When healthy, the brain functions seamlessly and automatically; however, disruptions can lead to serious conditions such as Alzheimer’s Disease, Brain Cancer, Stroke, and Epilepsy. Epilepsy, a neurological disorder marked by recurrent seizures, results from irregular electrical activity in the brain. These seizures, which can strain both patients and neurologists, are characterized by symptoms like the loss of awareness, unusual behavior, and confusion. This study presents an efficient EEG-based epileptic seizure detection framework utilizing a hybrid Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models approach to support automated and accurate diagnosis. Handling imbalanced EEG data, which can otherwise bias model outcomes and reduce predictive accuracy, is a key focus. Experimental results indicate that the proposed framework generally outperforms other Deep Learning and Machine Learning techniques with the highest accuracy at 99.13%. Likewise, an Explainable Artificial Intelligence (XAI) called SHAP (SHapley Additive exPlanations) is utilized to analyze the results and to improve the interpretability of the models from medical decision-making. This framework aligns with the objectives of the Medical Internet of Things (MIoT), advancing smart medical applications and services for effective epileptic seizure detection.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020077
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 78: Three-Dimensional Object Recognition Using
Orthogonal Polynomials: An Embedded Kernel Approach
Authors: Aqeel Abdulazeez Mohammed, Ahlam Hanoon Al-sudani, Alaa M. Abdul-Hadi, Almuntadher Alwhelat, Basheera M. Mahmmod, Sadiq H. Abdulhussain, Muntadher Alsabah, Abir Hussain
First page: 78
Abstract: Computer vision seeks to mimic the human visual system and plays an essential role in artificial intelligence. It is based on different signal reprocessing techniques; therefore, developing efficient techniques becomes essential to achieving fast and reliable processing. Various signal preprocessing operations have been used for computer vision, including smoothing techniques, signal analyzing, resizing, sharpening, and enhancement, to reduce reluctant falsifications, segmentation, and image feature improvement. For example, to reduce the noise in a disturbed signal, smoothing kernels can be effectively used. This is achievedby convolving the distributed signal with smoothing kernels. In addition, orthogonal moments (OMs) are a crucial technique in signal preprocessing, serving as key descriptors for signal analysis and recognition. OMs are obtained by the projection of orthogonal polynomials (OPs) onto the signal domain. However, when dealing with 3D signals, the traditional approach of convolving kernels with the signal and computing OMs beforehand significantly increases the computational cost of computer vision algorithms. To address this issue, this paper develops a novel mathematical model to embed the kernel directly into the OPs functions, seamlessly integrating these two processes into a more efficient and accurate approach. The proposed model allows the computation of OMs for smoothed versions of 3D signals directly, thereby reducing computational overhead. Extensive experiments conducted on 3D objects demonstrate that the proposed method outperforms traditional approaches across various metrics. The average recognition accuracy improves to 83.85% when the polynomial order is increased to 10. Experimental results show that the proposed method exhibits higher accuracy and lower computational costs compared to the benchmark methods in various conditions for a wide range of parameter values.
Citation: Algorithms
PubDate: 2025-02-01
DOI: 10.3390/a18020078
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 79: Analytical MPC Algorithm Using Steady-State
Process Model
Authors: Piotr M. Marusak
First page: 79
Abstract: For some classes of control plants (e.g., large time delay or inverse response), the PID controllers may offer unsatisfactory results; on the other hand, a Model Predictive Control (MPC) algorithm based on a linear model may offer insufficient control quality when applied to nonlinear control plants. To improve the MPC algorithm operation, one can use a steady-state process model; this paper describes how to do this skillfully. The obtained algorithm, based on the popular Dynamic Matrix Control (DMC) algorithm, is detailed. The proposed approach consists in modifying the analytical version of the DMC algorithm in such a way that it can still be expressed as the control law. Thus, the algorithm can still be applied to fast control plants, requiring short sampling times. Though the proposed approach does not modify the DMC algorithm much, it offers improvement in the control quality when the algorithm is employed in a nonlinear control plant. Experiments illustrating the efficiency of the proposed approach were conducted in the control system of a nonlinear chemical reactor. The results show improvement in the control quality compared to a case when the classical MPC algorithm is used.
Citation: Algorithms
PubDate: 2025-02-02
DOI: 10.3390/a18020079
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 80: Energy Scheduling of Hydrogen Hybrid UAV
Based on Model Predictive Control and Deep Deterministic Policy Gradient
Algorithm
Authors: Haitao Li, Chenyu Wang, Shufu Yuan, Hui Zhu, Bo Li, Yuexin Liu, Li Sun
First page: 80
Abstract: Energy scheduling for hybrid unmanned aerial vehicles (UAVs) is of critical importance to their safe and stable operation. However, traditional approaches, predominantly rule-based, often lack the dynamic adaptability and stability necessary to address the complexities of changing operational environments. To overcome these limitations, this paper proposes a novel energy scheduling framework that integrates the Model Predictive Control (MPC) with a Deep Reinforcement Learning algorithm, specifically the Deep Deterministic Policy Gradient (DDPG). The proposed method is designed to optimize energy management in hydrogen-powered UAVs across diverse flight missions. The energy system comprises a proton exchange membrane fuel cell (PEMFC), a lithium-ion battery, and a hydrogen storage tank, enabling robust optimization through the synergistic application of MPC and DDPG. The simulation results demonstrate that the MPC effectively minimizes electric power consumption under various flight conditions, while the DDPG achieves convergence and facilitates efficient scheduling. By leveraging advanced mechanisms, including continuous action space representation, efficient policy learning, experience replay, and target networks, the proposed approach significantly enhances optimization performance and system stability in complex, continuous decision-making scenarios.
Citation: Algorithms
PubDate: 2025-02-02
DOI: 10.3390/a18020080
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 81: Machine Learning Models to Predict Google
Stock Prices
Authors: Cosmina Elena Bucura, Paolo Giudici
First page: 81
Abstract: The aim of this paper is to predict Google stock price using different datasets and machine learning models, and understand which models perform better. The novelty of our approach is that we compare models not only by predictive accuracy but also by explainability and robustness. Our findings show that the choice of the best model to employ to predict Google stock prices depends on the desired objective. If the goal is accuracy, the recurrent neural network is the best model, while, for robustness, the Ridge regression model is the most resilient to changes and, for explainability, the Gradient Boosting model is the best choice.
Citation: Algorithms
PubDate: 2025-02-03
DOI: 10.3390/a18020081
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 82: Pneumonia Disease Detection Using Chest
X-Rays and Machine Learning
Authors: Cathryn Usman, Saeed Ur Rehman, Anwar Ali, Adil Mehmood Khan, Baseer Ahmad
First page: 82
Abstract: Pneumonia is a deadly disease affecting millions worldwide, caused by microorganisms and environmental factors. It leads to lung fluid build-up, making breathing difficult, and is a leading cause of death. Early detection and treatment are crucial for preventing severe outcomes. Chest X-rays are commonly used for diagnoses due to their accessibility and low costs; however, detecting pneumonia through X-rays is challenging. Automated methods are needed, and machine learning can solve complex computer vision problems in medical imaging. This research develops a robust machine learning model for the early detection of pneumonia using chest X-rays, leveraging advanced image processing techniques and deep learning algorithms that accurately identify pneumonia patterns, enabling prompt diagnosis and treatment. The research develops a CNN model from the ground up and a ResNet-50 pretrained model This study uses the RSNA pneumonia detection challenge original dataset comprising 26,684 chest array images collected from unique patients (56% male, 44% females) to build a machine learning model for the early detection of pneumonia. The data are made up of pneumonia (31.6%) and non-pneumonia (68.8%), providing an effective foundation for the model training and evaluation. A reduced size of the dataset was used to examine the impact of data size and both versions were tested with and without the use of augmentation. The models were compared with existing works, the model’s effectiveness in detecting pneumonia was compared with one another, and the impact of augmentation and the dataset size on the performance of the models was examined. The overall best accuracy achieved was that of the CNN model from scratch, with no augmentation, an accuracy of 0.79, a precision of 0.76, a recall of 0.73, and an F1 score of 0.74. However, the pretrained model, with lower overall accuracy, was found to be more generalizable.
Citation: Algorithms
PubDate: 2025-02-03
DOI: 10.3390/a18020082
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 83: Process Discovery for Event Logs with
Multi-Occurrence Event Types
Authors: László Kovács, Ali Jlidi
First page: 83
Abstract: One of the most actively researched areas in the field of process mining is process discovery, which aims to construct a schema that aligns with existing event trace sequences. Current standard industrial workflow schema induction methods impose certain limitations on the system being examined. To address the shortcomings, this article proposes a novel solution that employs graph neural networks and convolutional neural networks to perform schema discovery. In the first phase of schema generation, we perform equivalence prediction, implemented as an edge prediction task. From the obtained equivalence network, we identify the target schema nodes, which correspond to the maximal quasi-cliques of this network. The results of the performed efficiency tests demonstrate that the proposed method can manage such complex cases that are not covered by standard process discovery methods, and it provides more compact and more precise schema graphs.
Citation: Algorithms
PubDate: 2025-02-04
DOI: 10.3390/a18020083
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 84: Algorithms for Plant Monitoring
Applications: A Comprehensive Review
Authors: Giovanni Paolo Colucci, Paola Battilani, Marco Camardo Leggieri, Daniele Trinchero
First page: 84
Abstract: Many sciences exploit algorithms in a large variety of applications. In agronomy, large amounts of agricultural data are handled by adopting procedures for optimization, clustering, or automatic learning. In this particular field, the number of scientific papers has significantly increased in recent years, triggered by scientists using artificial intelligence, comprising deep learning and machine learning methods or bots, to process field, crop, plant, or leaf images. Moreover, many other examples can be found, with different algorithms applied to plant diseases and phenology. This paper reviews the publications which have appeared in the past three years, analyzing the algorithms used and classifying the agronomic aims and the crops to which the methods are applied. Starting from a broad selection of 6060 papers, we subsequently refined the search, reducing the number to 358 research articles and 30 comprehensive reviews. By summarizing the advantages of applying algorithms to agronomic analyses, we propose a guide to farming practitioners, agronomists, researchers, and policymakers regarding best practices, challenges, and visions to counteract the effects of climate change, promoting a transition towards more sustainable, productive, and cost-effective farming and encouraging the introduction of smart technologies.
Citation: Algorithms
PubDate: 2025-02-05
DOI: 10.3390/a18020084
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 85: Open and Extensible Benchmark for
Explainable Artificial Intelligence Methods
Authors: Ilia Moiseev, Ksenia Balabaeva, Sergey Kovalchuk
First page: 85
Abstract: The interpretability requirement is one of the largest obstacles when deploying machine learning models in various practical fields. Methods of eXplainable Artificial Intelligence (XAI) address those issues. However, the growing number of different solutions in this field creates a demand to assess the quality of explanations and compare them. In recent years, several attempts have been made to consolidate scattered XAI quality assessment methods into a single benchmark. Those attempts usually suffered from a focus on feature importance only, a lack of customization, and the absence of an evaluation framework. In this work, the eXplainable Artificial Intelligence Benchmark (XAIB) is proposed. Compared to existing benchmarks, XAIB is more universal, extensible, and has a complete evaluation ontology in the form of the Co-12 Framework. Due to its special modular design, it is easy to add new datasets, models, explainers, and quality metrics. Furthermore, an additional abstraction layer built with an inversion of control principle makes them easier to use. The benchmark will contribute to artificial intelligence research by providing a platform for evaluation experiments and, at the same time, will contribute to engineering by providing a way to compare explainers using custom datasets and machine learning models, which brings evaluation closer to practice.
Citation: Algorithms
PubDate: 2025-02-05
DOI: 10.3390/a18020085
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 86: Development and External Validation of
[18F]FDG PET-CT-Derived Radiomic Models for Prediction of Abdominal Aortic
Aneurysm Growth Rate
Authors: Simran Singh Dhesi, Pratik Adusumilli, Nishant Ravikumar, Mohammed A. Waduud, Russell Frood, Alejandro F. Frangi, Garry McDermott, James H. F. Rudd, Yuan Huang, Jonathan R. Boyle, Maysoon Elkhawad, David E. Newby, Nikhil Joshi, Jing Yi Kwan, Patrick Coughlin, Marc A. Bailey, Andrew F. Scarsbrook
First page: 86
Abstract: Objective (1): To develop and validate a machine learning (ML) model using radiomic features (RFs) extracted from [18F]FDG PET-CT to predict abdominal aortic aneurysm (AAA) growth rate. Methods (2): This retrospective study included 98 internal and 55 external AAA patients undergoing [18F]FDG PET-CT. RFs were extracted from manual segmentations of AAAs using PyRadiomics. Recursive feature elimination (RFE) reduced features for model optimisation. A multi-layer perceptron (MLP) was developed for AAA growth prediction and compared against Random Forest (RF), XGBoost, and Support Vector Machine (SVM). Accuracy was evaluated via cross-validation, with uncertainty quantified using dropout (MLP), standard deviation (RF), and 95% prediction intervals (XGBoost). External validation used independent data from two centres. Ground truth growth rates were calculated from serial ultrasound (US) measurements or CT volumes. Results (3): From 93 initial RFs, 29 remained after RFE. The MLP model achieved an MAE ± SEM of 1.35 ± 3.2e−4 mm/year with the full feature set and 1.35 ± 2.5e−4 mm/year with RFE. External validation yielded 1.8 ± 8.9e−8 mm/year. RF, XGBoost, and SVM models produced comparable accuracies internally (1.4–1.5 mm/year) but showed higher errors during external validation (1.9–1.97 mm/year). The MLP model demonstrated reduced uncertainty with the full feature set across all datasets. Conclusions (4): An MLP model leveraging [18F]FDG PET-CT radiomics accurately predicted AAA growth rates and generalised well to external data. In the future, more sophisticated stratification could guide individualised patient care, facilitating risk-tailored management of AAAs.
Citation: Algorithms
PubDate: 2025-02-05
DOI: 10.3390/a18020086
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 87: Batch-to-Batch Optimization Control of
Fed-Batch Fermentation Process Based on Recursively Updated Extreme
Learning Machine Models
Authors: Alex Moore, Jie Zhang
First page: 87
Abstract: This paper presents a new method of batch-to-batch optimization control for a fed-batch fermentation process. A recursively updated extreme learning machine (ELM) neural network model is used to model a fed-batch fermentation process. ELM models have advantages over other neural networks in that they can be trained very fast and have good generalization performance. However, the ELM model loses its predictive abilities in the presence of batch-to-batch process variations or disturbances, which lead to a process–model mismatch. The recursive least squares (RLS) technique takes the model prediction error from the previous batch and uses it to update the model parameters for the next batch. This improves the performance of the model and helps it to respond to any changes in process conditions or disturbances. The updated model is used in an optimization control procedure, which generates an improved control profile for the next batch. The update of the RLS model enables the optimization control strategy to maintain a high final product quality in the presence of disturbances. The proposed batch-to-batch optimization control method is demonstrated on a simulated fed-batch fermentation process.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020087
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 88: Nonparametric Probability Density Function
Estimation Using the Padé Approximation
Authors: Hamid Reza Aghamiri, S. Abolfazl Hosseini, James R. Green, B. John Oommen
First page: 88
Abstract: Estimating the Probability Density Function (PDF) of observed data is crucial as a problem in its own right, and also for diverse engineering applications. This paper utilizes two powerful mathematical tools, the concept of moments and the relatively little-known Padé approximation to achieve this. On the one hand, moments encapsulate crucial information that is central to both the “time-” and “frequency-”domain representations of the data. On the other hand, the Padé approximation provides an effective means of obtaining a convergent series from the data. In this paper, we invoke these established tools to estimate the PDF. As far as we know, the theoretical results that we have proven, and the experimental results that confirm them, are novel and rather pioneering. The method we propose is nonparametric. It leverages the concept of using the moments of the sample data—drawn from the unknown PDF that we aim to estimate—to reconstruct the original PDF. This is achieved through the application of the Padé approximation. Apart from the theoretical analysis, we have also experimentally evaluated the validity and efficiency of our scheme. The Padé approximation is asymmetric. The most unique facet of our work is that we have utilized this asymmetry to our advantage by working with two mirrored versions of the data to obtain two different versions of the PDF. We have then effectively “superimposed” them to yield the final composite PDF. We are not aware of any other research that utilizes such a composite strategy, in any signal processing domain. To evaluate the performance of the proposed method, we have employed synthetic samples obtained from various well-known distributions, including mixture densities. The accuracy of the proposed method has also been compared with that gleaned by several State-Of-The-Art (SOTA) approaches. The results that we have obtained underscore the robustness and effectiveness of our method, particularly in scenarios where the sample sizes are considerably reduced. Thus, this research confirms how the SOTA of estimating nonparametric PDFs can be enhanced by the Padé approximation, offering notable advantages over existing methods in terms of accuracy when faced with limited data.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020088
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 89: GATransformer: A Graph Attention
Network-Based Transformer Model to Generate Explainable Attentions for
Brain Tumor Detection
Authors: Sara Tehsin, Inzamam Mashood Nasir, Robertas Damaševičius
First page: 89
Abstract: Brain tumors profoundly affect human health owing to their intricacy and the difficulties associated with early identification and treatment. Precise diagnosis is essential for effective intervention; nevertheless, the resemblance among tumor forms often complicates the identification of brain tumor types, particularly in the early stages. The latest deep learning systems offer very high classification accuracy but lack explainability to help patients understand the prediction process. GATransformer, a graph attention network (GAT)-based Transformer, uses the attention mechanism, GAT, and Transformer to identify and preserve key neural network channels. The channel attention module extracts deeper properties from weight-channel connections to improve model representation. Integrating these elements results in a reduction in model size and enhancement in computing efficiency, while preserving adequate model performance. The proposed model is assessed using two publicly accessible datasets, FigShare and Kaggle, and is cross-validated using the BraTS2019 and BraTS2020 datasets, demonstrating high accuracy and explainability. Notably, GATransformer generates interpretable attention maps, visually highlighting tumor regions to aid clinical understanding in medical imaging.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020089
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 90: ECG Signal Classification Using
Interpretable KAN: Towards Predictive Diagnosis of Arrhythmias
Authors: Hongzhen Cui, Shenhui Ning, Shichao Wang, Wei Zhang, Yunfeng Peng
First page: 90
Abstract: To address the need for accurate classification of electrocardiogram (ECG) signals, we employ an interpretable KAN to classify arrhythmia diseases. Experimental evaluation of the MIT-BIH and PTB datasets demonstrates the significant superiority of the KAN in classifying arrhythmia diseases. Specifically, preprocessing steps such as sample balancing and variance sorting effectively optimized the feature distribution and significantly enhanced the model’s classification performance. In the MIT-BIH, the KAN achieved classification accuracy and precision rates of 99.08% and 99.07%, respectively. Similarly, on the PTB dataset, both metrics reached 99.11%. In addition, experimental results indicate that compared to the traditional multi-layer perceptron (MLP), the KAN demonstrates higher classification accuracy and better fitting stability and adaptability to complex data scenarios. Applying three clustering methods demonstrates that the features extracted by the KAN exhibit clearer cluster boundaries, thereby verifying its effectiveness in ECG signal classification. Additionally, convergence analysis reveals that the KAN’s training process exhibits a smooth and stable loss decline curve, confirming its robustness under complex data conditions. The findings of this study validate the applicability and superiority of the KAN in classifying ECG signals for arrhythmia and other diseases, offering a novel technical approach to the classification and diagnosis of arrhythmias. Finally, potential future research directions are discussed, including the KAN in early warning and rapid diagnosis of arrhythmias. This study establishes a theoretical foundation and practical basis for advancing interpretable networks in clinical applications.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020090
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 91: Advanced Dynamic Vibration of Terfenol-D
Control Law on Functionally Graded Material Plates/Cylindrical Shells in
Unsteady Supersonic Flow
Authors: Chih-Chiang Hong
First page: 91
Abstract: The thermal vibration of thick Terfenol-D control law on functionally graded material (FGM) plates/cylindrical shells in nonlinear unsteady supersonic flow with third-order shear deformation theory (TSDT) is investigated by using the generalized differential quadrature (GDQ) method. The effects of the coefficient term of TSDT displacement models on the thermal stress and center displacement of Terfenol-D control law on FGM plates/cylindrical shells in nonlinear unsteady supersonic flow are investigated. The coefficient term of TSDT models of thick Terfenol-D control law on FGM plates/cylindrical shells provide an additional effect on the values of displacements and stresses.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020091
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 92: Optimization of Multimodal Transport Paths
Considering a Low-Carbon Economy Under Uncertain Demand
Authors: Zhiwei Liu, Sihui Zhou, Song Liu
First page: 92
Abstract: Aiming at the uncertainty in cargo demand in the transportation process, the multimodal transportation path optimization problem is studied from the perspective of a low-carbon economy, and the robust optimization modeling method is introduced. Firstly, a robust optimization model for multimodal transportation is built using the multimodal transportation path optimization model under demand certainty, and the total transportation cost is then calculated by taking into account not just only the cost of transportation and trans-shipment but, additionally, the price of waiting because of schedule restrictions on trains and airplanes. Secondly, carbon emissions are added into the model as a constraint or cost by converting four different low-carbon policies. Then, the simulated annealing mechanism is introduced to improve the ACO algorithm. Finally, solomon calculus is used for the solution. The outcomes demonstrate that the improved annealing ant colony hybrid algorithm simulation can essentially improve the multimodal transportation path optimization problem with uncertain demand and promote multimodal transportation emission reduction. Among the four carbon emission policies, the mandatory carbon emission policy means are tough, and the greatest impact comes from reducing emissions and using less energy. Energy conservation and emission reduction have the second-best impact, while the three policy tools of carbon taxes, carbon trading and carbon payment are more modest.
Citation: Algorithms
PubDate: 2025-02-06
DOI: 10.3390/a18020092
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 93: Advancing Real-Estate Forecasting: A Novel
Approach Using Kolmogorov–Arnold Networks
Authors: Iosif Viktoratos, Athanasios Tsadiras
First page: 93
Abstract: Accurately estimating house values is a critical challenge for real-estate stakeholders, including homeowners, buyers, sellers, agents, and policymakers. This study introduces a novel approach to this problem using Kolmogorov–Arnold networks (KANs), a type of neural network based on the Kolmogorov–Arnold theorem. The proposed KAN model was tested on two datasets and demonstrated superior performance compared to existing state-of-the-art methods for predicting house prices. By delivering more precise price forecasts, the model supports improved decision-making for real-estate stakeholders. Additionally, the results highlight the broader potential of KANs for addressing complex prediction tasks in data science. This study aims to provide an innovative and effective solution for accurate house price estimation, offering significant benefits for the real-estate industry and beyond.
Citation: Algorithms
PubDate: 2025-02-07
DOI: 10.3390/a18020093
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 94: Encoding-Based Machine Learning Approach
for Health Status Classification and Remote Monitoring of Cardiac Patients
Authors: Sohaib R. Awad, Faris S. Alghareb
First page: 94
Abstract: Remote monitoring of a patient’s vital activities has become increasingly important in dealing with various medical applications. In particular, machine learning (ML) techniques have been extensively utilized to analyze electrocardiogram (ECG) signals in cardiac patients to classify heart health status. This trend is largely driven by the growing interest in computer-aided diagnosis based on ML algorithms. However, there has been inadequate investigation into the impact of risk factors on heart health, which hinders the ability to identify heart-related issues and predict the conditions of cardiac patients. In this context, developing a GUI-based classification approach can significantly facilitate online monitoring and provide real-time warnings by predicting potential complications. In this paper, a general framework structure for medical real-time monitoring systems is proposed for modeling the vital signs of cardiac patients in order to predict the patient’s status. The proposed approach analyzes AI-driven interventions to provide a more accurate cardiac diagnosis and real-time monitoring system. To further demonstrate the validity of the presented approach, we employ it in a LabVIEW-based remote tracking system to predict three healthcare statuses (stable, unstable non-critical, and unstable critical). The developed monitoring system receives various information about patients’ vital signs, and then it leverages a novel encoding-based machine learning algorithm to pre-process, analyze, and classify patient status. The developed ANN classifier and proposed encoding-based ML model are compared to other conventional ML-based models, such as Naive Bayes, SVM, and KNN for model accuracy evaluation. The obtained outcomes demonstrate the efficacy of the presented ANN and encoding-based ML approaches by achieving an accuracy of 98.4% and 98.8% for the developed ANN classifier and the proposed encoding-based technique, respectively, whereas Naive Bayes and quadratic SVM algorithms realize 94.8% and 96%, respectively. In short, this study aims to explore how ML algorithms can enhance diagnostic accuracy, improve real-time monitoring, and optimize treatment outcomes. Meanwhile, the proposed tracking system outperforms most existing monitoring systems by offering high classification accuracy of the heart health status and a user-friendly interactive interface. Therefore, it can potentially be utilized to improve the performance of remote healthcare monitoring for cardiac patients.
Citation: Algorithms
PubDate: 2025-02-07
DOI: 10.3390/a18020094
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 95: Enhancing Non-Invasive Blood Glucose
Prediction from Photoplethysmography Signals via Heart Rate
Variability-Based Features Selection Using Metaheuristic Algorithms
Authors: Saifeddin Alghlayini, Mohammed Azmi Al-Betar, Mohamed Atef
First page: 95
Abstract: Diabetes requires effective monitoring of the blood glucose level (BGL), traditionally achieved through invasive methods. This study addresses the non-invasive estimation of BGL by utilizing heart rate variability (HRV) features extracted from photoplethysmography (PPG) signals. A systematic feature selection methodology was developed employing advanced metaheuristic algorithms, specifically the Improved Dragonfly Algorithm (IDA), Binary Grey Wolf Optimizer (bGWO), Binary Harris Hawks Optimizer (BHHO), and Genetic Algorithm (GA). These algorithms were integrated with machine learning (ML) models, including Random Forest (RF), Extra Trees Regressor (ETR), and Light Gradient Boosting Machine (LightGBM), to enhance predictive accuracy and optimize feature selection. The IDA-LightGBM combination exhibited superior performance, achieving a mean absolute error (MAE) of 13.17 mg/dL, a root mean square error (RMSE) of 15.36 mg/dL, and 94.74% of predictions falling within the clinically acceptable Clarke error grid (CEG) zone A, with none in dangerous zones. This research underscores the efficiency of utilizing HRV and PPG for non-invasive glucose monitoring, demonstrating the effectiveness of integrating metaheuristic and ML approaches for enhanced diabetes monitoring.
Citation: Algorithms
PubDate: 2025-02-08
DOI: 10.3390/a18020095
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 96: The Diagnostic Classification of the
Pathological Image Using Computer Vision
Authors: Yasunari Matsuzaka, Ryu Yashiro
First page: 96
Abstract: Computer vision and artificial intelligence have revolutionized the field of pathological image analysis, enabling faster and more accurate diagnostic classification. Deep learning architectures like convolutional neural networks (CNNs), have shown superior performance in tasks such as image classification, segmentation, and object detection in pathology. Computer vision has significantly improved the accuracy of disease diagnosis in healthcare. By leveraging advanced algorithms and machine learning techniques, computer vision systems can analyze medical images with high precision, often matching or even surpassing human expert performance. In pathology, deep learning models have been trained on large datasets of annotated pathology images to perform tasks such as cancer diagnosis, grading, and prognostication. While deep learning approaches show great promise in diagnostic classification, challenges remain, including issues related to model interpretability, reliability, and generalization across diverse patient populations and imaging settings.
Citation: Algorithms
PubDate: 2025-02-08
DOI: 10.3390/a18020096
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 97: Preamble-Based Signal-to-Noise Ratio
Estimation for Adaptive Modulation in Space–Time Block
Coding-Assisted Multiple-Input Multiple-Output Orthogonal Frequency
Division Multiplexing System
Authors: Shahid Manzoor, Noor Shamsiah Othman, Mohammed W. Muhieldeen
First page: 97
Abstract: This paper presents algorithms to estimate the signal-to-noise ratio (SNR) in the time domain and frequency domain that employ a modified Constant Amplitude Zero Autocorrelation (CAZAC) synchronization preamble, denoted as CAZAC-TD and CAZAC-FD SNR estimators, respectively. These SNR estimators are invoked in a space–time block coding (STBC)-assisted multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system. These SNR estimators are compared to the benchmark frequency domain preamble-based SNR estimator referred to as the Milan-FD SNR estimator when used in a non-adaptive 2×2 STBC-assisted MIMO-OFDM system. The performance of the CAZAC-TD and CAZAC-FD SNR estimators is further investigated in the non-adaptive 4×4 STBC-assisted MIMO-OFDM system, which shows improved bit error rate (BER) and normalized mean square error (NMSE) performance. It is evident that the non-adaptive 2×2 and 4×4 STBC-assisted MIMO-OFDM systems that invoke the CAZAC-TD SNR estimator exhibit superior performance and approach closer to the normalized Cramer–Rao bound (NCRB). Subsequently, the CAZAC-TD SNR estimator is invoked in an adaptive modulation scheme for a 2×2 STBC-assisted MIMO-OFDM system employing M-PSK, denoted as the AM-CAZAC-TD-MIMO system. The AM-CAZAC-TD-MIMO system outperformed the non-adaptive STBC-assisted MIMO-OFDM system using 8-PSK by about 2 dB at BER = 10−4. Moreover, the AM-CAZAC-TD-MIMO system demonstrated an SNR gain of about 4 dB when compared with an adaptive single-input single-output (SISO)-OFDM system with M-PSK. Therefore, it was shown that the spatial diversity of the MIMO-OFDM system is key for the AM-CAZAC-TD-MIMO system’s improved performance.
Citation: Algorithms
PubDate: 2025-02-09
DOI: 10.3390/a18020097
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 98: Pediatric Pneumonia Recognition Using an
Improved DenseNet201 Model with Multi-Scale Convolutions and Mish
Activation Function
Authors: Petra Radočaj, Dorijan Radočaj, Goran Martinović
First page: 98
Abstract: Pediatric pneumonia remains a significant global health issue, particularly in low- and middle-income countries, where it contributes substantially to mortality in children under five. This study introduces a deep learning model for pediatric pneumonia diagnosis from chest X-rays that surpasses the performance of state-of-the-art methods reported in the recent literature. Using a DenseNet201 architecture with a Mish activation function and multi-scale convolutions, the model was trained on a dataset of 5856 chest X-ray images, achieving high performance: 0.9642 accuracy, 0.9580 precision, 0.9506 sensitivity, 0.9542 F1 score, and 0.9507 specificity. These results demonstrate a significant advancement in diagnostic precision and efficiency within this domain. By achieving the highest accuracy and F1 score compared to other recent work using the same dataset, our approach offers a tangible improvement for resource-constrained environments where access to specialists and sophisticated equipment is limited. While the need for high-quality datasets and adequate computational resources remains a general consideration for deep learning applications, our model’s demonstrably superior performance establishes a new benchmark and offers the delivery of more timely and precise diagnoses, with the potential to significantly enhance patient outcomes.
Citation: Algorithms
PubDate: 2025-02-10
DOI: 10.3390/a18020098
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 99: A Levelized Multiple Workflow Heterogeneous
Earliest Finish Time Allocation Model for Infrastructure as a Service
(IaaS) Cloud Environment
Authors: Farheen Bano, Faisal Ahmad, Mohammad Shahid, Mahfooz Alam, Faraz Hasan, Mohammad Sajid
First page: 99
Abstract: Cloud computing, a superset of heterogeneous distributed computing, allows sharing of geographically dispersed resources across multiple organizations on a rental basis using virtualization as per demand. In cloud computing, workflow allocation to achieve the optimum schedule has been reported to be NP-hard. This paper proposes a Levelized Multiple Workflow Heterogeneous Earliest Finish Time (LMHEFT) model to optimize makespan in the cloud computing environment. The model has two phases: task prioritization and task allocation. The task prioritization phase begins by dividing workflows into the number of partitions as per the level attribute; after that, upward rank is employed to determine the partition-wise task allocation order. In the allocation phase, the best-suited virtual machine is determined to offer the lowest finish time for each task in partition-wise mapping to minimize the workflow task’s completion time. The model considers the inter-task communication between the cooperative workflow tasks. A comparative performance evaluation of LMHEFT has been conducted with the competitive models from the literature implemented in MATLAB, i.e., heterogeneous earliest finish time (HEFT) and dynamic level scheduling (DLS), on makespan, flowtime, and utilization. The experimental findings indicate that LMHEFT surpasses HEFT and DLS in terms of makespan 15.51% and 85.12% when varying the number of workflows, 41.19% and 86.73% when varying depth levels, and 13.74% and 80.24% when varying virtual machines, respectively. Further statistical analysis has been carried out to confirm the hypothesis developed in the simulation study by using normality tests, homogeneity tests, and the Kruskal–Wallis test.
Citation: Algorithms
PubDate: 2025-02-10
DOI: 10.3390/a18020099
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 100: Performance Investigation of Active,
Semi-Active and Passive Suspension Using Quarter Car Model
Authors: Kyle Samaroo, Abdul Waheed Awan, Siva Marimuthu, Muhammad Naveed Iqbal, Kamran Daniel, Noman Shabbir
First page: 100
Abstract: In this paper, a semi-active and fully active suspension system using a PID controller were designed and tuned in MATLAB/Simulink to achieve simultaneous optimisation of comfort and road holding ability. This was performed in order to quantify and observe the trends of both the semi-active and active suspension, which can then influence the choice of controlled suspension systems used for different applications. The response of the controlled suspensions was compared to a traditional passive setup in terms of the sprung mass displacement and acceleration, tyre deflection, and suspension working space for three different road profile inputs. It was found that across all road profiles, the usage of a semi-active or fully active suspension system offered notable improvements over a passive suspension in terms of comfort and road-holding ability. Specifically, the rms sprung mass displacement was reduced by a maximum of 44% and 56% over the passive suspension when using the semi-active and fully active suspension, respectively. Notably, in terms of sprung mass acceleration, the semi-active suspension offered better performance with a 65% reduction in the passive rms sprung mass acceleration compared to a 40% reduction for the fully active suspension. The tyre deflection of the passive suspension was also reduced by a maximum of 6% when using either the semi-active or fully active suspension. Furthermore, both the semi-active and fully active suspensions increased the suspension working space by 17% and 9%, respectively, over the passive suspension system, which represents a decreased level of performance. In summary, the choice between a semi-active or fully active suspension should be carefully considered based on the level of ride comfort and handling performance that is needed and the suspension working space that is available in the particular application. However, the results of this paper show that the performance gap between the semi-active and fully active suspension is quite small, and the semi-active suspension is mostly able to match and sometimes outperform the fully active suspension n in certain metrics. When considering other factors, such as weight, power requirements, and complexity, the semi-active suspension represents a better choice over the fully active suspension, in the author’s opinion. As such, future work will look at utilising more robust control methods and tuning procedures that may further improve the performance of the semi-active suspension.
Citation: Algorithms
PubDate: 2025-02-10
DOI: 10.3390/a18020100
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 101: A Lightweight Deep Learning Approach for
Detecting External Intrusion Signals from Optical Fiber Sensing System
Based on Temporal Efficient Residual Network
Authors: Yizhao Wang, Ziye Guo, Haitao Luo, Jing Liu, Ruohua Zhou
First page: 101
Abstract: Deep neural networks have been widely applied to fiber optic sensor systems, where the detection of external intrusion in metro tunnels is a major challenge; thus, how to achieve the optimal balance between resource consumption and accuracy is a critical issue. To address this issue, we propose a lightweight deep learning model, the Temporal Efficient Residual Network (TEResNet), for the detection of anomalous intrusion. In contrast to the majority of two-dimensional convolutional approaches, which require a deep architecture to encompass both low- and high-frequency domains, our methodology employs temporal convolutions and a compact residual network architecture. This allows the model to incorporate lower-level features into the higher-level feature formation in subsequent layers, leveraging informative features from the lower layers, and thus reducing the number of stacked layers for generating high-level features. As a result, the model achieves a superior performance with a relatively small number of layers. Moreover, the two-dimensional feature map is reduced in size to reduce the computational burden without adding parameters. This is crucial for enabling rapid intrusion detection. Experiments were conducted in the construction environment of the Guangzhou Metro, resulting in the creation of a dataset containing 6948 signal segments, which is publicly accessible. The results demonstrate that TEResNet outperforms the existing intrusion detection methods and advanced deep learning networks, achieving an accuracy of 97.12% and an F1 score of 96.15%. With only 48,009 learnable parameters, it provides an efficient and reliable solution for intrusion detection in metro tunnels, aligning with the growing demand for lightweight and robust information processing systems.
Citation: Algorithms
PubDate: 2025-02-11
DOI: 10.3390/a18020101
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 102: Improved Algorithm to Detect Clandestine
Airstrips in Amazon RainForest
Authors: Gabriel R. Pardini, Paulo M. Tasinaffo, Elcio H. Shiguemori, Tahisa N. Kuck, Marcos R. O. A. Maximo, William R. Gyotoku
First page: 102
Abstract: The Amazon biome is frequently targeted by illegal activities, with clandestine mining being one of the most prominent. Due to the dense forest cover, criminals often rely on covert aviation as a logistical tool to supply remote locations and sustain these activities. This work presents an enhancement to a previously developed landing strip detection algorithm tailored for the Amazon biome. The initial algorithm utilized satellite images combined with the use of Convolutional Neural Networks (CNNs) to find the targets’ spatial locations (latitude and longitude). By addressing the limitations identified in the initial approach, this refined algorithm aims to improve detection accuracy and operational efficiency in complex rainforest environments. Tests in a selected area of the Amazon showed that the modified algorithm resulted in a recall drop of approximately 1% while reducing false positives by 26.6%. The recall drop means there was a decrease in the detection of true positives, which is balanced by the reduction in false positives. When applied across the entire biome, the recall decreased by 1.7%, but the total predictions dropped by 17.88%. These results suggest that, despite a slight reduction in recall, the modifications significantly improved the original algorithm by minimizing its limitations. Additionally, the improved solution demonstrates a 25.55% faster inference time, contributing to more rapid target identification. This advancement represents a meaningful step toward more effective detection of clandestine airstrips, supporting ongoing efforts to combat illegal activities in the region.
Citation: Algorithms
PubDate: 2025-02-13
DOI: 10.3390/a18020102
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 103: Building a Custom Crime Detection Dataset
and Implementing a 3D Convolutional Neural Network for Video Analysis
Authors: Juan Camilo Londoño Lopera, Freddy Bolaños Martinez, Luis Alejandro Fletscher Bocanegra
First page: 103
Abstract: This study addresses the challenge of detecting crimes against individuals in public security applications, particularly where the availability of quality data is limited, and existing models exhibit a lack of generalization to real-world scenarios. To mitigate the challenges associated with collecting extensive and labeled datasets, this study proposes the development of a novel dataset focused specifically on crimes against individuals, including incidents such as robberies, assaults, and physical altercations. The dataset is constructed using data from publicly available sources and undergoes a rigorous labeling process to ensure both quality and representativeness of criminal activities. Furthermore, a 3D convolutional neural network (Conv 3D) is implemented for real-time video analysis to detect these crimes effectively. The proposed approach includes a comprehensive validation of both the dataset and the model through performance comparisons with existing datasets, utilizing key evaluation metrics such as the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). Experimental results demonstrate that the proposed dataset and model achieve an accuracy rate between 94% and 95%, highlighting their effectiveness in accurately identifying criminal activities. This study contributes to the advancement of crime detection technologies, offering a practical solution for implementation in surveillance and public safety systems in urban environments.
Citation: Algorithms
PubDate: 2025-02-14
DOI: 10.3390/a18020103
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 104: A Training Algorithm for Locally Recurrent
Neural Networks Based on the Explicit Gradient of the Loss Function
Authors: Sara Carcangiu, Augusto Montisci
First page: 104
Abstract: In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at the same time guarantee the stability of the network during the training. The main feature of the proposed algorithm is the capability to represent the gradient of the error in an explicit form. The algorithm builds on the interpretation of Fibonacci’s sequence as the output of an IIR second-order filter, which makes it possible to use Binet’s formula that allows the generic terms of the sequence to be calculated directly. Thanks to this approach, the gradient of the loss function during the training can be explicitly calculated, and it can be expressed in terms of the parameters, which control the stability of the neural network.
Citation: Algorithms
PubDate: 2025-02-14
DOI: 10.3390/a18020104
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 105: Advancing Taxonomy with Machine Learning:
A Hybrid Ensemble for Species and Genus Classification
Authors: Loris Nanni, Matteo De Gobbi, Roger De Almeida Matos Junior, Daniel Fusaro
First page: 105
Abstract: Traditionally, classifying species has required taxonomic experts to carefully examine unique physical characteristics, a time-intensive and complex process. Machine learning offers a promising alternative by utilizing computational power to detect subtle distinctions more quickly and accurately. This technology can classify both known (described) and unknown (undescribed) species, assigning known samples to specific species and grouping unknown ones at the genus level—an improvement over the common practice of labeling unknown species as outliers. In this paper, we propose a novel ensemble approach that integrates neural networks with support vector machines (SVM). Each animal is represented by an image and its DNA barcode. Our research investigates the transformation of one-dimensional vector data into two-dimensional three-channel matrices using discrete wavelet transform (DWT), enabling the application of convolutional neural networks (CNNs) that have been pre-trained on large image datasets. Our method significantly outperforms existing approaches, as demonstrated on several datasets containing animal images and DNA barcodes. By enabling the classification of both described and undescribed species, this research represents a major step forward in global biodiversity monitoring.
Citation: Algorithms
PubDate: 2025-02-14
DOI: 10.3390/a18020105
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 106: Machine Learning for Decision Support and
Automation in Games: A Study on Vehicle Optimal Path
Authors: Gonçalo Penelas, Luís Barbosa, Arsénio Reis, João Barroso, Tiago Pinto
First page: 106
Abstract: In the field of gaming artificial intelligence, selecting the appropriate machine learning approach is essential for improving decision-making and automation. This paper examines the effectiveness of deep reinforcement learning (DRL) within interactive gaming environments, focusing on complex decision-making tasks. Utilizing the Unity engine, we conducted experiments to evaluate DRL methodologies in simulating realistic and adaptive agent behavior. A vehicle driving game is implemented, in which the goal is to reach a certain target within a small number of steps, while respecting the boundaries of the roads. Our study compares Proximal Policy Optimization (PPO) and Soft Actor–Critic (SAC) in terms of learning efficiency, decision-making accuracy, and adaptability. The results demonstrate that PPO successfully learns to reach the target, achieving higher and more stable cumulative rewards. Conversely, SAC struggles to reach the target, displaying significant variability and lower performance. These findings highlight the effectiveness of PPO in this context and indicate the need for further development, adaptation, and tuning of SAC. This research contributes to developing innovative approaches in how ML can improve how player agents adapt and react to their environments, thereby enhancing realism and dynamics in gaming experiences. Additionally, this work emphasizes the utility of using games to evolve such models, preparing them for real-world applications, namely in the field of vehicles’ autonomous driving and optimal route calculation.
Citation: Algorithms
PubDate: 2025-02-15
DOI: 10.3390/a18020106
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 107: Multi-Strategy Improved Artificial Rabbit
Algorithm for QoS-Aware Service Composition in Cloud Manufacturing
Authors: Le Deng, Ting Shu, Jinsong Xia
First page: 107
Abstract: Cloud manufacturing represents a pioneering service paradigm that provides flexible, personalized manufacturing services to customers via the Internet. Service composition plays a crucial role in cloud manufacturing, which focuses on integrating dispersed manufacturing services in the cloud platform into a complete composite service to form an efficient and collaborative manufacturing solution that fulfills the customer’s requirements, having the highest service quality. This research presents the multi-strategy improved artificial rabbit optimization (MIARO) technique, designed to overcome the limitations with the original method, which often risks converging to local optima and have poor solution quality when dealing with optimization problems. MIARO helps the algorithm escape local optimality with Lévy flights, extends local search with the golden sine mechanism, and expands variability with Archimedean spiral mutations. MIARO is experimented on 23 benchmark functions, 3 engineering design problems, and QoS-aware cloud service composition (QoS-CSC) issues at various sizes, and the experimental findings indicate that MIARO delivers outstanding performance and offers a viable solution to the QoS-CSC problem.
Citation: Algorithms
PubDate: 2025-02-15
DOI: 10.3390/a18020107
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 108: Beyond Spectrograms: Rethinking Audio
Classification from EnCodec’s Latent Space
Authors: Jorge Perianez-Pascual, Juan D. Gutiérrez, Laura Escobar-Encinas, Álvaro Rubio-Largo, Roberto Rodriguez-Echeverria
First page: 108
Abstract: This paper presents a novel approach to audio classification leveraging the latent representation generated by Meta’s EnCodec neural audio codec. We hypothesize that the compressed latent space representation captures essential audio features more suitable for classification tasks than the traditional spectrogram-based approaches. We train a vanilla convolutional neural network for music genre, speech/music, and environmental sound classification using EnCodec’s encoder output as input to validate this. Then, we compare its performance training with the same network using a spectrogram-based representation as input. Our experiments demonstrate that this approach achieves comparable accuracy to state-of-the-art methods while exhibiting significantly faster convergence and reduced computational load during training. These findings suggest the potential of EnCodec’s latent representation for efficient, faster, and less expensive audio classification applications. We analyze the characteristics of EnCodec’s output and compare its performance against traditional spectrogram-based approaches, providing insights into this novel approach’s advantages.
Citation: Algorithms
PubDate: 2025-02-16
DOI: 10.3390/a18020108
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 109: Optimizing Investment Portfolios with
Bacterial Foraging and Robust Risk Management
Authors: Hubert Zarzycki
First page: 109
Abstract: This study introduces a novel portfolio optimization approach that combines Bacterial Foraging Optimization (BFO) with risk management techniques and Sharpe ratio analysis. BFO, a nature-inspired algorithm, is employed to construct diversified portfolios, while risk management strategies, including stop-loss limits and transaction cost considerations, enhance risk control. The Sharpe ratio is used to evaluate the efficiency of the investment strategy by accounting for risk-adjusted returns. The experiments demonstrate that this approach effectively balances risk and return, making it a valuable tool for portfolio management in dynamic financial markets.
Citation: Algorithms
PubDate: 2025-02-17
DOI: 10.3390/a18020109
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 110: Optimized Travel Itineraries: Combining
Mandatory Visits and Personalized Activities
Authors: Parida Jewpanya, Pinit Nuangpirom, Siwasit Pitjamit, Warisa Nakkiew
First page: 110
Abstract: Tourism refers to the activity of traveling for pleasure, recreation, or leisure purposes. It encompasses a wide range of activities and experiences, from sightseeing to cultural exploration. In today’s digital age, tourists often organize their excursions independently by utilizing information available on websites. However, due to constraints in designing customized tour routes such as travel time and budget, many still require assistance with vacation planning to optimize their experiences. Therefore, this paper proposes an algorithm for personalized tourism planning that considers tourists’ preferences. For instance, the algorithm can recommend places to visit and suggest activities based on tourist requirements. The proposed algorithm utilizes an extended model of the team orienteering problem with time windows (TOPTW) to account for mandatory locations and activities at each site. It offers trip planning that includes a set of locations and activities designed to maximize the overall score accumulated from visiting these locations. To solve the proposed model, the Adaptive Neighborhood Simulated Annealing (ANSA) algorithm is applied. ANSA is an enhanced version of the well-known Simulated Annealing algorithm (SA), providing an adaptive mechanism to manage the probability of selecting neighborhood moves during the SA search process. The computational results demonstrate that ANSA performs well in solving benchmark problems. Furthermore, a real-world attractive location in Tak Province, Thailand, is used as the case study in this paper to illustrate the effectiveness of the proposed model.
Citation: Algorithms
PubDate: 2025-02-17
DOI: 10.3390/a18020110
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 111: Enhancing Energy Microgrid Sizing: A
Multiyear Optimization Approach with Uncertainty Considerations for
Optimal Design
Authors: Sebastián F. Castellanos-Buitrago, Pablo Maya-Duque, Walter M. Villa-Acevedo, Nicolás Muñoz-Galeano, Jesús M. López-Lezama
First page: 111
Abstract: This paper addresses the challenge of optimizing microgrid sizing to enhance reliability and efficiency in electrical energy supply. A comprehensive framework that integrates multiyear optimization with uncertainty considerations is presented to facilitate optimal microgrid design. The aim is to economically, safely, and reliably supply electrical energy to communities with limited or no access to the main power grid, primarily utilizing renewable sources such as solar and wind technologies. The proposed framework incorporates environmental stochasticity, electrical demand uncertainty, and various electrical generation technologies. Electric power generation models are developed, and a metaheuristic optimization method is employed to minimize total costs while improving power supply reliability. The practical utility of the developed computational tool is emphasized, highlighting its significance in decision-making for microgrid installations. Utilizing real-world data, the approach involves a two-stage process: the first stage focuses on installation decisions, and the second evaluates operational performance using an iterated local search (ILS) optimization algorithm. Additionally, dispatch strategies are implemented to optimize computational time and enable real-time network modeling. The proposed microgrid sizing approach is a valuable asset for optimizing decision-making processes, significantly contributing to extending electricity coverage in non-interconnected zones while minimizing costs and ensuring steadfast reliability.
Citation: Algorithms
PubDate: 2025-02-17
DOI: 10.3390/a18020111
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 112: Enumerating Minimal Vertex Covers and
Dominating Sets with Capacity and/or Connectivity Constraints
Authors: Yasuaki Kobayashi, Kazuhiro Kurita, Kevin Mann, Yasuko Matsui, Hirotaka Ono
First page: 112
Abstract: In this paper, we consider the minimal vertex cover and minimal dominating sets with capacity and/or connectivity constraint enumeration problems. We develop polynomial-delay enumeration algorithms for these problems on bounded-degree graphs. For the case of minimal connected vertex covers, our algorithms run in polynomial delay, even on the class of d-claw free graphs. This result is extended for bounded-degree graphs and outputs in quasi-polynomial time on general graphs. To complement these algorithmic results, we show that the minimal connected vertex cover, minimal connected dominating set, and minimal capacitated vertex cover enumeration problems in 2-degenerated bipartite graphs are at least as hard as enumerating minimal transversals in hypergraphs.
Citation: Algorithms
PubDate: 2025-02-17
DOI: 10.3390/a18020112
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 113: DLMinTC+: A Deep Learning Based Algorithm
for Minimum Timeline Cover on Temporal Graphs
Authors: Giorgio Lazzarinetti, Riccardo Dondi, Sara Manzoni, Italo Zoppis
First page: 113
Abstract: Combinatorial optimization on temporal graphs is critical for summarizing dynamic networks in various fields, including transportation, social networks, and biology. Among these problems, the Minimum Timeline Cover (MinTCover) problem, aimed at identifying minimal activity intervals for representing temporal interactions, remains underexplored in the context of advanced machine learning techniques. Existing heuristic and approximate methods, while effective in certain scenarios, struggle with capturing complex temporal dependencies and scalability in dense, large-scale networks. Addressing this gap, this paper introduces DLMinTC+, a novel deep learning-based algorithm for solving the MinTCover problem. The proposed method integrates Graph Neural Networks for structural embedding, Transformer-based temporal encoding, and Pointer Networks for activity interval selection, coupled with an iterative adjustment algorithm to ensure valid solutions. Key contributions include (i) demonstrating the efficacy of deep learning for temporal combinatorial optimization, achieving superior accuracy and efficiency over state-of-the-art heuristics, and (ii) advancing the analysis of temporal knowledge graphs by incorporating robust, time-sensitive embeddings. Extensive evaluations on synthetic and real-world datasets highlight DLMinTC+’s ability to achieve significant coverage size reduction while maintaining generalization, offering a scalable and precise solution for complex temporal networks.
Citation: Algorithms
PubDate: 2025-02-17
DOI: 10.3390/a18020113
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 114: Energy Management and Hosting Capacity
Evaluation of a Hybrid AC-DC Micro Grid Including Photovoltaic Units and
Battery Energy Storage Systems
Authors: Mohammed Ajel Awdaa, Elaheh Mashhour, Hossein Farzin, Mahmood Joorabian
First page: 114
Abstract: Renewable energy sources must be scheduled to manage power flow and load demand. Photovoltaic power generation is usually connected to power distribution networks and is not designed to add significant amounts of production in the event of increased electricity demand. Therefore, it is necessary to increase the generated capacity (i.e., hosting capacity) to meet the expansion in demand. This paper discussed two topics; the first is how to create an energy management strategy (EMS) for a hybrid micro-grid containing photovoltaic (PV) and battery energy storage system (BESS). A model was created within the MATLAB program through which the charging and discharging process of the BESS was managed, and the energy source was through PV. The model is connected to the leading network, where the m.file is linked to the model to control variable settings. This was carried out by using a logical–numerical modeling method. The second topic discussed how to evaluate hosting capacity (HC) without causing the network to collapse. This was achieved by choosing the best location and size for the PV. This study relied on the use of two algorithms, particle swarm optimization (PSO) and Harris hawks optimization (HHO). The fast decoupled load Flow (FDPF) method was adopted in the network analysis and finally the results of the two algorithms were compared.
Citation: Algorithms
PubDate: 2025-02-18
DOI: 10.3390/a18020114
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 115: Solution of Bin Packing Instances in
Falkenauer T Class: Not So Hard
Authors: György Dósa, András Éles, Angshuman Robin Goswami, István Szalkai, Zsolt Tuza
First page: 115
Abstract: In this work, the Bin Packing combinatorial optimization problem is studied from the practical side. The focus is on the Falkenauer T benchmark class, which is a collection of 80 problem instances that are considered hard to handle algorithmically. Contrary to this widely accepted view, we show that the instances of this benchmark class can be solved relatively easily, without applying any sophisticated methods like metaheuristics. A new algorithm is proposed, which can operate in two modes: either using backtrack or local search to find optimal packing. In theory, both operating modes are guaranteed to find a solution. Computational results show that all instances of the Falkenauer T benchmark class can be solved in a total of 1.18 s and 2.39 s with the two operating modes alone, or 0.2 s when running in parallel.
Citation: Algorithms
PubDate: 2025-02-19
DOI: 10.3390/a18020115
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 116: Knowledge Discovery in Predicting
Martensite Start Temperature of Medium-Carbon Steels by Artificial Neural
Networks
Authors: Xiao-Song Wang, Anoop Kumar Maurya, Muhammad Ishtiaq, Sung-Gyu Kang, Nagireddy Gari Subba Reddy
First page: 116
Abstract: Martensite start (Ms) temperature is a critical parameter in the production of parts and structural steels and plays a vital role in heat treatment processes to achieve desired properties. However, it is often challenging to estimate accurately through experience alone. This study introduces a model that predicts the Ms temperature of medium-carbon steels based on their chemical compositions using the artificial neural network (ANN) method and compares the results with those from previous empirical formulae. The results indicate that the ANN model surpasses conventional methods in predicting the Ms temperature of medium-carbon steel, achieving an average absolute error of −0.93 degrees and −0.097% in mean percentage error. Furthermore, this research provides an accurate method or tool with which to present the quantitative effect of alloying elements on the Ms temperature of medium-carbon steels. This approach is straightforward, visually interpretable, and highly accurate, making it valuable for materials design and prediction of material properties.
Citation: Algorithms
PubDate: 2025-02-19
DOI: 10.3390/a18020116
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 117: TOCA-IoT: Threshold Optimization and
Causal Analysis for IoT Network Anomaly Detection Based on Explainable
Random Forest
Authors: Ibrahim Gad
First page: 117
Abstract: The Internet of Things (IoT) is developing quickly, which has led to the development of new opportunities in many different fields. As the number of IoT devices continues to expand, particularly in transportation and healthcare, the need for efficient and secure operations has become critical. In the next few years, IoT connections will continue to expand across different fields. In contrast, a number of problems require further attention to be addressed to provide safe and effective operations, such as security, interoperability, and standards. This research investigates the efficacy of integrating explainable artificial intelligence (XAI) techniques and causal inference methods to enhance network anomaly detection. This study proposes a robust TOCA-IoT framework that utilizes the linear non-Gaussian acyclic model (LiNGAM) to find causal relationships in network traffic data, thereby improving the accuracy and interpretability of anomaly detection. A refined threshold optimization strategy is employed to address the challenge of selecting optimal thresholds for anomaly classification. The performance of the TOCA-IoT model is evaluated on an IoT benchmark dataset known as CICIoT2023. The results highlight the potential of combining causal discovery with XAI for building more robust and transparent anomaly detection systems. The results showed that the TOCA-IoT framework achieved the highest accuracy of 100% and an F-score of 100% in classifying the IoT attacks.
Citation: Algorithms
PubDate: 2025-02-19
DOI: 10.3390/a18020117
Issue No: Vol. 18, No. 2 (2025)
- Algorithms, Vol. 18, Pages 118: Robust Client Selection Strategy Using an
Improved Federated Random High Local Performance Algorithm to Address High
Non-IID Challenges
Authors: Pramote Sittijuk, Narin Petrot, Kreangsak Tamee
First page: 118
Abstract: This paper introduces an improved version of the Federated Random High Local Performance (Fed-RHLP) algorithm, specifically aimed at addressing the difficulties posed by Non-IID (Non-Independent and Identically Distributed) data within the context of federated learning. The refined Fed-RHLP algorithm implements a more targeted client selection approach, emphasizing clients based on the size of their datasets, the diversity of labels, and the performance of their local models. It employs a biased roulette wheel mechanism for selecting clients, which improves the aggregation of the global model. This approach ensures that the global model is primarily influenced by high-performing clients while still permitting contributions from those with lower performance during the model training process. Experimental findings indicate that the improved Fed-RHLP algorithm significantly surpasses existing methodologies, including FederatedAveraging (FedAvg), Power of Choice (PoC), and FedChoice, by achieving superior global model accuracy, accelerated convergence rates, and decreased execution times, especially under conditions of high Non-IID data. Furthermore, the improved Fed-RHLP algorithm exhibits resilience even when the number of clients participating in local model updates and aggregation is diminished in each communication round. This characteristic positively influences the conservation of limited communication and computational resources.
Citation: Algorithms
PubDate: 2025-02-19
DOI: 10.3390/a18020118
Issue No: Vol. 18, No. 2 (2025)
