Subjects -> COMPUTER SCIENCE (Total: 2313 journals)     - ANIMATION AND SIMULATION (33 journals)    - ARTIFICIAL INTELLIGENCE (133 journals)    - AUTOMATION AND ROBOTICS (116 journals)    - CLOUD COMPUTING AND NETWORKS (75 journals)    - COMPUTER ARCHITECTURE (11 journals)    - COMPUTER ENGINEERING (12 journals)    - COMPUTER GAMES (23 journals)    - COMPUTER PROGRAMMING (25 journals)    - COMPUTER SCIENCE (1305 journals)    - COMPUTER SECURITY (59 journals)    - DATA BASE MANAGEMENT (21 journals)    - DATA MINING (50 journals)    - E-BUSINESS (21 journals)    - E-LEARNING (30 journals)    - ELECTRONIC DATA PROCESSING (23 journals)    - IMAGE AND VIDEO PROCESSING (42 journals)    - INFORMATION SYSTEMS (109 journals)    - INTERNET (111 journals)    - SOCIAL WEB (61 journals)    - SOFTWARE (43 journals)    - THEORY OF COMPUTING (10 journals) COMPUTER SCIENCE (1305 journals)                  1 2 3 4 5 6 7 | Last
Similar Journals
 Automatic Control and Computer SciencesJournal Prestige (SJR): 0.218 Citation Impact (citeScore): 1Number of Followers: 6      Hybrid journal (It can contain Open Access articles) ISSN (Print) 1558-108X - ISSN (Online) 0146-4116 Published by Springer-Verlag  [2469 journals]
• Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm
for Feed-Forward Neural Networks

Abstract: For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths’ cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.
PubDate: 2022-04-01

• Time Series Similarity Search Methods for Sensor Data

Abstract: Time series is a type of dynamic data used in many applications. Time series speed may vary from milliseconds to years or decades. In past decade, rise in various sensor based technologies have made time series sensor data available easily and in larger extent. Therefore, high dimensionality of the data in customized applications is always a challenging task for efficient mathematical computing accuracy and performance optimization. One of the major operations performed on time series is finding out similarity between two or more time series. Two time series can be considered similar on the basis of distance between them. Computation of these distances is achieved by various methods. This research study aims to compare eight such methods for accelerometer sensor data collected from smartphone based accelerometer during car and scooter ride. This study also proposes a modified method of distance computation considering tyre pressure and weight of the vehicle. Research findings have shown that modified method of DTW (dynamic time warping) is proved more efficient in distinguishing time series generated by two different weights’ vehicles. Results have shown as maximum of 67% recognition rate is achieved by modified DTW method compared to traditional DTW method.
PubDate: 2022-04-01

• Neural Translation System of Meta-Domain Transfer Based on Self-Ensemble
and Self-Distillation

Abstract: In order to address the shortcoming that feature representation limitation in machine translation (MT) system, this paper presents a transfer method for features in MT. Its main aim is to solve knowledge transfer of different training corpus in the decoding process. In this paper, the meta domain is modeled. A model agnostic self-ensemble and self-distillation training framework is proposed. The training is divided into model training and meta training to better adapt to the two types of features. In this paper, we have done extensive experiments on the classical neural machine translation system, and the model is compared with the classical methods. The experimental results show that the proposed model has improved in the transfer task of different domains and systems. In this paper, translation knowledge transfer is carried out on the Chinese-English translation dataset in the subdivided domain, which has a significant performance improvement in the news, education and law domain.
PubDate: 2022-04-01

• Recognition Confidence of Welding Seam Defects in TOFD Images Based on
Artificial Intelligence

Abstract: In this paper, a target detection approach (Faster R-CNN) based on convolutional neural networks is applied to the training and recognition of typical defects in TOFD welding seam images. Before training and recognition, a total of 162 ultrasonic TOFD welding seam images containing five typical defects are collected. The ultrasonic TOFD welding seam image dataset required for neural network model training is established on the basis of the collected images. The neural network model is trained including pre-training on ImageNet, RPN training alone, Faster R-CNN training alone, and joint RPN and Faster R-CNN training. During training, the parameters in the program are adjusted, and, then, the convergence of the neural network models and recognition performance are compared after the same training iterations. It is found that the neural network model has a tendency to converge only when the batch size is 10 and the learning rate is 0.001. Under this parameter configuration condition, the program conducts training with more iterations and is used to identify welding seam defects. The results show that the program is accurate in locating typical defects in the images, and the recognition confidence for all kinds of defects is more than 0.9. Compared with the other parameter configuration conditions after the same training iterations, the program has the highest recognition confidence in identifying all types of defects when the batch size is 10 and the learning rate is 0.001.
PubDate: 2022-04-01

• Visual Tracking Method Based on Siamese Network with Multi-Feature Fusion

Abstract: The traditional deep learning tracking method SiamFC faces performance degradation while solving issues, for instance, similar background, occlusion, target deformation, and illumination variation. This paper proposes an improved SiamFC with multi-feature fusion strategy. The proposed method first extracts the histogram of gradient and color name of the template image and search area by correlation filter. Then, the method fuses them and weights the SiamFC response map to obtain a more accurate object response position. Comparison experiments on VOT and OTB datasets prove that the improved method is more accurate and robust than the excellent tracking methods to deal with problems such as target cover, out of sight, scale variation and motion blur.
PubDate: 2022-04-01

• Hybrid Path Planning Algorithm of the Mobile Agent Based on Q-Learning

Abstract: In the path planning using Q-learning of the mobile agent, the convergence speed is too slow. So, based on Q-learning, two hybrid algorithms are proposed to improve the above problem in this paper. One algorithm is combining Manhattan distance and Q-learning (CMD-QL); the other one is combining flower pollination algorithm and Q-learning (CFPA-QL). In the former algorithm, the Q table is firstly initialized with Manhattan distance to enhance the learning efficiency of the initial stage of Q-learning; secondly, the selection strategy of the ε-greedy action is improved to balance the exploration-exploitation relationship of the mobile agent’s actions. In the latter algorithm, the flower pollination algorithm is first used to initialize the Q table, so that Q-learning can obtain the necessary prior information which can improve the overall learning efficiency; secondly, the ε-greedy strategy under the minimum value of the exploration factor is adopted, which makes effective use of the action with high value. Both algorithms have been tested under known, partially known, and unknown environments, respectively. The test results show that the CMD-QL and CFPA-QL algorithms proposed in this paper can converge to the optimal path faster than the single Q-learning method, besides the CFPA-QL algorithm has the better efficiency.
PubDate: 2022-04-01

• Algorithms for the Analysis of Queueing System M/G/1/ $$\infty$$ with
Cut-Off of the Line

Abstract: The classical queueing system M/G/1 is considered for a case when the service begins, if the number of waited claims reaches the fixed level k. Various algorithms are considered for the calculation of such indices as the mean and the distribution of the waiting time, the queue length and so on.
PubDate: 2022-04-01

• An Evader Control Strategy in the Non-Linear Differential Game Problem
with Terminal Limitations

Abstract: This article considers the method of developing an evader control strategy in the non-linear differential pursuit-evasion game problem. It is assumed that the pursuer resorts to the most probable control strategy in order to capture the evader and that at each moment the evader knows its own and the enemy’s physical capabilities. This assumption allows to bring the game problem down to the problem of a unilateral evader control, with the condition of reaching a saddle point not obligatory to be fulfilled. The control is realised in the form of synthesis and additionally ensures that the requirements for bringing the evader to a specified area with terminal optimization of certain state variables are satisfied.
PubDate: 2022-04-01

• Analysis of Dynamic Characteristics of Man-Machine Co-Driving Vehicle
during Driving Right Switching

Abstract: In order to study the influence of different drivers and vehicle speeds on the dynamics of smart cars when the driving rights are switched; this paper analyzes them through driving experiments. This experiment recruited 16 participants, and built a virtual experimental platform for man-machine co-driving, and designed an experimental program at three speeds of 50, 80, and 120 km/h based on 8 s early warning time interval for driving rights to take over. And the experimental data is processed and analyzed by K-means clustering. The results show that the driver’s age and driving experience affect the driver’s take-over behavior and the dynamics of the vehicle. The take-over behavior taken by the high driving experience or young driver in the process of driving right switching can ensure that the vehicle has better stability. On the one hand, the increase in vehicle speed will affect the driver’s take-over behavior. On the other hand, it will cause the nonlinear characteristic of the vehicle to be significant and the driving stability of the vehicle to be worse.
PubDate: 2022-04-01

• Duplication of Boolean Complements for Synthesis of Fault-Tolerant Digital
Devices and Systems

Abstract: A new architecture for the synthesis of fault-tolerant digital devices, which is easier to implement as compared to the well-known architecture based on triple modular redundancy (TMR), is proposed. The architecture is implemented based on the Boolean complement principle, which implies the use of a special control block for evaluating complement functions, rather than by introducing exact copies of an original circuit. In practice, its complexity can be significantly lower than the complexity of the original circuit. This makes it possible to synthesize fault-tolerant devices with simpler designs as compared to TMR-based devices. The proposed architecture consists of three blocks: the original circuit, the signal error detection circuit, and the signal correction circuit. The synthesis of a fault-tolerant digital device is aimed at generating the structure of the signal error detection circuit, which implements the idea of duplication of complements. The advantages and disadvantages of the proposed fault-tolerant architecture are discussed. The results of experiments on some combinational benchmarks, which demonstrate the effectiveness of the proposed approach, are presented.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010096

• The Design of an Expressway Lighting and Early Warning System Based on MCU

Abstract: There is a design of an expressway lighting and early warning system based on MCU, and the corresponding control method is proposed in this paper. The system and its control method can realize the lighting and direction guidance of the vehicles on the expressway under different situations. The different colors of lights are used to remind the vehicle of the different driving situation. The emergent buttons and GSM module can realize help-calling for people in distress in the expressway and can also be used for road maintenance personnel to locate the worker and check on work attendance. The system and its control method can also realize the vehicle counting function and the calculation of magnitude of traffic flow.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010059

• Inter-Organizational Cloud Computing and Robust Scalability in Current
Scenario and Beyond

Abstract: Inter-organizational cloud computing model is beneficial for academic institutions. We propose a collaborative inter-institutional cloud learning, where cloud entities can learn the same model cooperatively. The inter-institutional cloud model can reduce network bandwidth costs and ensure privacy. We recommend a trainer to student’s/customer strategy. The key role is to combine a regularization term with the objective function to adjust the gradient of the inter-institutional students/customers under different data. Then, based on the training strategy, a robust federated optimization technique based on joint identification verification is proposed to reduce the number of communication rounds. The main aims of this paper are, first, it can provide a technical platform for cloud services, then institutional resources utilization and opportunistic resources have been evaluated for their overall usage of cloud services and goals. Secondly, our time allocation for cloud computing management workloads is an active area of investigation metrics for the current scenario and control strategy. Experimental results analyze through the different case studies and use the scalability technology compared with the academia and robust scalability techniques.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010060

• Hot News Prediction Method Based on Natural Language Processing Technology
and Its Application

Abstract: In today’s era of information expansion, there exist a lot of real-time news every day, and there will be a time difference between potential real-time hotspots and hot news. It is time-consuming for IT operators to read all the real-time news and find the hot spots by human effort. Therefore, the prediction of hot news is particularly important for we-media operation. Therefore, this paper attempts to use natural language processing technology to predict hot news and to assist operators to create articles about the hot news. For hot news prediction, this paper proposes a method of data preprocessing and uses several models based on convolutional neural networks (CNNs), text convolutional neural networks (TextCNNs), long-short term memory (LSTM), bi-directional long short-term memory (BiLSTM) to train. We also build a new model—CNN Distinct and BiLSTM Extract, which can be called CDBE for short—to obtain better performance. We evaluate several training models and analyze them by multiple evaluation indexes. In addition, we apply the method proposed in this paper to actual operation work, and the result shows that such can greatly reduce operators’ pressure, save the working time for creating articles about hot news, and greatly improve their work efficiency.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010023

• An Improvement on LEACH-C Protocol (LEACH-CCMSN)

Abstract: Wireless sensor networks (WSNs) are composed of tiny sensors nodes with limited resources, and communicating together to monitor the environment. Sensor nodes are usually powered by battery. Consequently, the energy efficiency is critical for the lifetime of the Wireless sensors network. Routing protocols are the most important issue for WSNs. LEACH (low energy adaptive clustering hierarchy) is one of the first hierarchical routing algorithms for WSNs. LEACH-C (LEACH-centralized) is a variant of LEACH where the cluster heads are selected by the Sink. At the beginning of each round in LEACH-C, the sensor nodes must send information about their current energy to the Sink, which exhausts the sensor node battery. This paper proposes an improved LEACH-C algorithm in which, the Sink uses a consumption mode for each sensor node (CMSN) to estimate the amount of energy needed for the next rounds; so, sensor nodes doesn’t have to send the value of the current energy to the Sink at the beginning of each round. The simulation results and analysis show that our proposed protocol achieve much better performances in terms of energy dissipation and network lifetime compared to LEACH-C.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010102

• An Approach for Detecting Anonymized Traffic: Orbot as Case Study

Abstract: — This work studies Orbot, an anonymous overlay network used to browse the Internet. Its ease of use has attracted all kinds of people, including ordinary Internet users who want to avoid being profiled to bypass censorship, government intelligence agencies that need to do operations on the Internet without being detected and companies who do not want to reveal information to their competitors. This article aims to study, analyze, and mostly identify the Orbot traffic, since much of it is used for illegal purposes. A method of identification of the anonymous network is established by examining the traffic to identify clues. The method used to detect the use of the Orbot application in the network is based on the creation of the rules with Snort IDS from the analysis of the packets in Wireshark analyzer. The encryption aspect of the flow of this anonymous network brings us to a deep packet inspection (DPI). A set of Snort rules were developed as a proof of concept for the proposed Orbot detection approach. Our traffic detection methodology has demonstrated that it can detect Orbot connections in real time.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010072

• Automatic Recognition of Welding Seam Defects in TOFD Images Based on
TensorFlow

Abstract: This study is aimed to analyze the characteristics of different kinds of time-of-flight diffraction (TOFD) images for welding seam defects. Combined with the image recognition technology of artificial intelligence, a deep learning neural network program based on TensorFlow was developed and applied to the training and recognition of welding seam defects in ultrasonic TOFD images. The results showed that, after training, the program could identify typical welding seam defects such as stoma, crackle, slag inclusion, lack of fusion, and incomplete penetration in TOFD images of the welding seam, and the recognition confidence was more than 0.8. This proved that the program developed in this study provided an effective reference for determining typical welding seam defects in TOFD images of the welding seam.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010035

• Classification of Road Pavement Defects Based on Convolution Neural
Network in Keras

Abstract: The aim of this paper is to propose the convolution neural network—VGG16 structure in Keras to classify pavement defects. In this paper, we present a method to build an automated system to classify different types of defects such as block cracks, longitudinal cracks and potholes. A region of interest is found and features are extracted using image processing techniques and machine learning methods. This system includes the following steps. The first step is to detect the defect location (ROI), then the defect is described by its features. Finally, each defect is classified based on these different features. The system ensures stable operation in the presence of limited lighting conditions, shadowing, and complex shaped defects.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010084

• Fully Integrated Spatial Information to Improve FCM Algorithm for Brain
MRI Image Segmentation

Abstract: FCM algorithm is one of the well-known techniques for image segmentation; it is based on an imprecise decision by using the membership function. However, FCM algorithm fails to proceed well enough in the presence of imaging artifacts due to its performance without any consideration of spatial information. In this paper, we propose two crucial modifications to the conventional FCM algorithm to tackle its sensitivity against noise. Firstly, the proposed algorithm provides full consideration of the spatial constraint, wherein the influence of neighboring pixels is defined according to two proposed terms, a fuzzy similarity measure as well as the level of noise. Secondly, we adopt a strategy to select the optimal pixel between the central pixel and its neighboring pixels that can better influence the segmentation performance in terms of compactness and separation information. The proposed algorithm is compared qualitatively and quantitatively with five existing clustering methods in terms of cluster validity functions, segmentation accuracy, tissue segmentation accuracy, and computational time.
PubDate: 2022-02-01
DOI: 10.3103/S0146411622010047

• A Two-Component Steganographic System Based on the Sum of Linear Functions
of Two Signals Using a Multiplicative Form of Constraint of Embedded
Signals

Abstract: A steganographic system based on linear mixing of two signals and nonlinear communication between container components, which is invariant to masking signal, is considered, and the key coefficient, which provides effective protection of hidden signal from unauthorized recovery, is determined.
PubDate: 2021-12-01
DOI: 10.3103/S0146411621080435

• Using Security-through-Obscurity Principle in an Industrial Internet of
Things

Abstract: Considering the openness of industrial Internet-of-Things systems as compared with conventional SCADA-like systems, the provision of sustainable and continuous production becomes a more relevant and complex task. This article considers the application of the security-through-obscurity principle as the original method of maintaining production process continuity. An attempt to derive a formula for evaluating the protection level when using this principle is described.
PubDate: 2021-12-01
DOI: 10.3103/S0146411621080083

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762