JournalTOCs

International Journal of Advanced Network, Monitoring and Controls
Number of Followers: 0

This is an Open Access Journal

Open Access journal
ISSN (Online) 2470-8038
Published by Sciendo

[389 journals]

Research on Intelligentization of Cloud Computing Programs Based on
Self-awareness
- Abstract: Through the research of MapReduce programming framework of cloud computing, the current MapReduce program only solves specific problems, and there is no design experience or design feature summary of MapReduce program, let alone formal description and experience inheritance and application of knowledge base. In order to solve the problem of intelligent cloud computing program, a general MapReduce program generation method is designed. This paper proposes the architecture of intelligent cloud computing by studying AORBCO model and combining cloud computing technology. According to the behavior control mechanism in AORBCO model, a program generation method of MapReduce in intelligent cloud computing is proposed. This method will extract entity information in input data set and entity information in knowledge base in intelligent cloud computing for similarity calculation, and extract the entity in the top order as key key-value pair information in intelligent cloud computing judgment data set. The data processing types are divided, and then aligned with each specific MapReduce capability, and the MapReduce program generation experiment is verified in the AORBCO model development platform. The experiment shows that the complexity of big data MapReduce program code is simplified, and the generated code execution efficiency is good.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Improved Double Regression Nonlinear Image Super Resolution Model
- Abstract: The existing super resolution reconstruction methods are mainly divided into traditional super resolution reconstruction and deep learning super resolution reconstruction. The main problem faced by traditional super resolution reconstruction algorithms, such as image enlargement and space transformation, is how to establish the mapping relationship between the input image and the target image, and express the pixel value of the target image through the mapping relationship. As a prominent problem, the difficulty of super resolution reconstruction lies in the fact that there is no realizable matrix relationship between one - to - many mapping relationships. Based on the U-Net network framework, this paper improves the jump-connected modules. By using the combination of convolutional layer, activation layer and residual channel block, the overall module operation efficiency is increased by 2.4%, the overall PNSR is increased by 0.49db, and the running speed is increased by 0.3ms on average when processing a single image compared with other classical models.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Research on Joint Modeling of Intent Detection and Slot Filling
- Abstract: In task-based dialogue system, the key of the natural language understanding module is intent detection and slot filling. At this stage, Joint modeling of intention detection and slot filling tasks has become the mainstream and achieved good results. In order to investigate the correlation between intention detection and slot filling tasks, Joint model of intention detection and slot filling based on attention mechanism in three dimensions: one-way modeling from intention to slot, Unidirectional modeling from slot to intention and bidirectional modeling from intention to slot Separately. And experiments were conducted using the Chinese dataset CAIS, and the results showed three evaluation results for time slot F1.The intention accuracy and overall accuracy of joint models for intention detection and filling gaps are usually higher than those of unidirectional models.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Exploring the Potential of A-ResNet in Person-Independent Face Recognition
and Classification
- Abstract: This study offers a novel face recognition and classification method based on classifiers that use statistical local features. The use of ResNet has generated growing interest in a variety of areas of image processing and computer vision in recent years and demonstrated its usefulness in several applications, especially for facial image analysis, which includes tasks as varied as face detection, face recognition, facial expression analysis, demographic classification, etc. This paper is divided into two steps i.e. face recognition and classification. The first step in face recognition is automatic data cleansing which is done with the help of Multi-Task Cascaded Convolutional Neural Networks (MTCNNs) and face.evoLVe, followed by parameter changes in MTCNN to prevent dirty data. The authors next trained two models: Inception-ResNetV1, which had pre-trained weights, and Altered-ResNet (A-ResNet), which used Conv2d layers in ResNet for feature extraction and pooling and softmax layers for classifications. The authors use the best optimizer after comparing a number of them during the training phase, along with various combinations of batch and epoch. A-ResNet, the top model overall, detects 86/104 Labelled Faces in the Wild (LFW) dataset images in 0.50 seconds. The proposed approach was evaluated and received an accuracy of 91.7%. Along with this, the system achieved a training accuracy of 98.53% and a testing accuracy of 99.15% for masked face recognition. The proposed method exhibits competitive outcomes when measured against other cutting-edge algorithms and models. Finally, when it comes to why the suggested model is superior to ResNet, it may be because the A-ResNet is simpler thus it can perform at its best with little data, whereas deeper networks require higher data size.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Optimization and Improvement of BP Decoding Algorithm for Polar Codes
Based on Deep Learning
- Abstract: In order to solve the high latency problem of polar codes belief propagation decoding algorithm in the 5G and the dimension limitation problem of belief propagation decoding algorithm under deep learning, a multilayer perceptron belief propagation decoding (MLP-BP) algorithm based on partitioning idea is proposed. In this work, polar codes is decoded using neural networks in partitioning, and the right transfer message value of BP decoding algorithm is also set to complete the propagation process. Simulation results show that, compared with BP decoding algorithm, the proposed algorithm has better decoding performance, reducing the decoding latency, and it is also applicable to long polar codes.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Research on Blockchain Anonymous Communication Based on Key Derivation
- Abstract: With the continuous development of the Internet and communication technologies, network communication provides convenience but also brings security problems such as exposure of users' personal privacy information and theft, private tampering, and forgery of false information. Modern cryptography technology is an important safeguard against message eavesdropping and tampering, while the rapidly developing anonymous communication technology in this century makes it difficult for attackers to infer user's personal information and communication relationships. In response to the potential threats of traditional centralized systems such as central nodes being vulnerable to attacks and data storage being tampered with, this paper proposes a blockchain anonymous communication algorithm KDAC based on key derivation, which takes advantage of the decentralization, data immutability, consensus mechanism and anonymity of blockchain and combines the ECC cryptographic derivation algorithm and anonymous communication technology to realize the key-at-a-time, one-address-at-a-time The key derivation scheme ensures the message integrity and tamper-evident while effectively hiding the identity information of both communication parties. In addition, this paper also optimizes the blockchain anonymous communication system with key derivation. Users only need the initial key of blockchain nodes to join the network for communication, and the information transmission is difficult to trace based on the blockchain network, which can effectively guarantee communication security and anonymity. The experimental results show that the efficiency of the derived key algorithm is roughly in the same order of magnitude as that of the 256-bit AES symmetric encryption algorithm, which can play a better role in practical applications. On the other hand, the derived key generated based on the algorithm has complete randomness in association verification, and it is impossible to reverse the initial parameters, which can well guarantee the anonymity of user identity.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
IP Addresses through 2022: This article is reproduced from “The ISP
Column-A monthly column on things Internet” of Geoff Huston's Blog
- PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Simulation of Comfort Algorithm for Automatic Driving of Urban Rail Train
- Abstract: The automation and intelligence of transportation vehicles is the focus and hotspot of the future research and development of the entire transportation industry, which can effectively improve a series of social problems such as traffic accidents, exhaust pollution, and traffic jams caused by the current increase in the number of transportation vehicles. With the rapid development of rail transit in our country, more and more people choose urban rail transit for travel, which is greatly convenient for travel. The comfort of Automatic Train Operation (ATO) system is an inevitable consideration when people choose it. Aiming at the comfort of ATO system, this paper designs a train operation target curve that can meet the comfort index of train. At the same time, two simulation models are established by using the SIMULINK module of MATLAB software to compare the experiments. One model is the train simulation model based on PID control, and the other model is the train simulation model based on fuzzy PID. The final simulation results show that fuzzy PID control has stronger superiority in train comfort in the process of train motion simulation, and the traditional PID control is not as good as fuzzy PID control in train comfort.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Performance of Automatic Frequency Planning and Optimization Algorithm for
Cellular Networks
- Abstract: Frequency planning is one of the most expensive aspects of deploying a cellular network. If a set of base stations can be deployed with minimal service and planning, the cost of both deploying and maintaining the network will decrease. To ensure that the scarce frequency is utilized to its maximum, planning and optimization are done. This is also carried out to ensure that there is high efficiency in cellular radio systems and little or minimum interference due to co-channeling. This paper focuses on coming up with an automatic way of planning and optimizing the frequency in the cellular network. The approach replaces the inefficient, inaccurate and tedious manual approach. The automatic approach simplifies work for the radio frequency(RF) engineers and also reduces the cost of operation. The automatic approach ensures that the cellular network is extensively deployed in a way that criteria of maximum quality, quantity and good coverage are met. The paper focuses on coming up with an automatic planning and optimization algorithm that minimizes the intra-system interference levels to reasonable ranges within the key performance indicators (KPIs) defined for any acceptable cellular network.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Deep Learning Based Melanoma Diagnosis Identification
- Abstract: Malignant melanoma is considered to be one of the deadliest types of skin cancer, and it is responsible for the death of a large number of people worldwide. However, distinguishing whether melanoma is benign or malignant has been a challenging task. Many Computer Aided Diagnosis and Detection Systems have been developed in the past for this task. This paper presents a deep learning framework based approach for melanoma diagnosis and recognition. In the proposed method, the original skin mirror image is first preprocessed and then passed to the VGG16 convolutional neural network for tumor property classification. VGG16 uses smaller convolutional kernels instead of a larger convolutional kernel to achieve a reduction in network parameters and thus improve network performance. The system is trained using segmented RGB images generated from ground truth images of the ISIC2016 dataset, and finally a softmax classifier is used for pixel-level classification of melanoma lesions. In this study, a new method to become a lesion classifier was designed to classify melanoma lesion regions into benign and malignant tumors based on the results of pixel-level classification, and experiments were conducted on two well-established public test datasets, ISIC2016 and ISIC2017, with a final accuracy of 96.1%. The results indicate that convolutional neural networks are suitable for melanoma diagnosis identification. This study is of great relevance for advanced cancer caused by malignant melanoma.
  PubDate: Wed, 16 Aug 2023 00:00:00 GMT
Research on Super-resolution Image Based on Deep Learning
- Abstract: Image super-resolution is a kind of important image processing technology in computer vision and image processing. It refers to the process of recovering high-resolution image from low-resolution image. It has a wide range of real-world applications, such as medical imaging, security and others. In addition to improving image perception quality, it also helps improve other computer vision tasks. Compared with traditional methods, deep learning methods show better reconstruction results in the field of image super-resolution reconstruction, and have gradually developed into the mainstream technology. This article will study the depth in the super resolution direction is important method of types of introduction, combed the main image super-resolution reconstruction method, expounds the depth study of several important super-resolution network model, the advantages and disadvantages of different algorithms and adaptive application scenarios are analyzed and compared, this paper expounds the different ways in the super resolution to liquidate, Finally, the potential problems of current image super-resolution reconstruction techniques are discussed, and the future development direction is prospected.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Research on Pilots ’ Mental Workload Classification in Simulated
Flight
- Abstract: The problem of human-computer interaction mental workload in flight driving has great reference value for the prevention of safety hazards in aviation driving. This paper analyzes and studies the classification method of mental workload in flight driving by designing different simulated flight experiment tasks. This study uses a combination of EEG signals and subjective evaluation, through the use of convolutional neural networks and long short-term memory network method of combining EEG signals for research and analysis. The accuracy of EEG signal classification is as high as 94.9 %. NASA-TLX evaluation results show that there is a positive correlation between task load difficulty and evaluation score. The results show that the combination of convolutional neural network and long short-term memory network is suitable for pilots ’ mental workload classification. This study has important practical significance for flight accidents caused by pilots ’ mental workload.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Research on Visibility Estimation Model Based on DenseNet
- Abstract: In recent years, the road visibility detection method based on video has been paid more and more attention. It has overcome the deficiency of laser visibility meter to some extent. Deep learning has a good effect in image processing and analysis. This paper firstly analyzes the current situation of deep learning, and then compares DenseNet and ResNet to propose a visibility estimation model based on deep DenseNet. The model firstly integrates airport video data and visibility data. Secondly, the DenseNet algorithm is used to automatically extract the features of the airport data set. Finally, Softmax classifier is constructed to evaluate the visibility accuracy. They reduce the problem of disappearing gradient, enhance feature propagation, encourage functional reuse, and greatly reduce the number of parameters, well train the deep model, has a good visibility estimation effect. On this basis, this paper based on Canny operator lane dividing line extraction edge extraction and visibility analysis based on edge detection, and do the corresponding test. Finally, a video visibility analysis model based on Kalman filter is built based on the given data, and Gaussian process regression model is used to predict the fog change trend.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
A Compound Optimization Greedy Strategy with Reverse Correction Mechanism
- Abstract: Greedy strategy is an algorithm thinking with local optimization as the core idea, but only when the problem has no after-effect, the global optimization can be achieved. Therefore, greedy strategy is not the first choice for researchers to solve the problem. Based on the greedy strategy, this paper adds the mechanism of reverse correction thinking, transfers the local optimal solution to the global optimal solution, and puts forward a compound optimal greedy strategy integrating reverse correction thinking. Based on the actual application scenario of blood robot operating costs, the overall “simple greedy strategy model” is constructed and tested based on the greedy strategy as the main modeling basis according to the application needs. On this basis, the interaction relationship between local optimal solutions is deeply analyzed, and the reverse correction mechanism is integrated to optimize the system through the two steps of reverse allocation and reverse merge repair. Gradually improve the model to get the optimized “reverse modified greedy strategy model”, the algorithm can effectively reduce the operating cost. On this basis, in order to test the optimization effect, the effectiveness and stability of the reverse correction mechanism were verified by modifying some parameters of the application scene and randomly generating multiple arrays for re-test, etc., and new parameters were selected to re-run the application scene, and satisfactory verification results were obtained. Compared with other modeling ideas of the same topic, this model weakens the expression of the overall function and emphasizes the change relationship and action mechanism between data, and obtains better operation results. Greedy strategy is very conducive to the analysis of the relationship between requirements, constraints and variables. According to the actual application needs, combined with the mathematical analysis method, the reverse correction mechanism is added to the greedy strategy modeling. In the demand sequence test of 100 groups of simulation, the maximum saving rate can be close to 1.6%, while the lowest saving rate is less than 0.6%, and the average saving rate is 0.9677%. It can save tens of thousands of operating costs for application scenarios.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Research and Simulation of Negative Group Delay and Superluminal
Propagation
- Abstract: In recent years, negative group delay circuits have attracted much attention due to their propagation characteristics and wide application prospects. In the history of human exploration, the exploration of the speed of light has never stopped. The theory of relativity points out that the speed of light in vacuum is the limit speed of signal propagation. However, it is found through research that phase velocity and group velocity appear faster than the speed of light, which does not violate the causal relationship. This paper first introduces the related concepts of negative group delay and superluminal phenomenon, the second focuses on the principle of negative group delay and superluminal phenomenon in-depth analysis and research, finally using the principle of Multisim software, the bandwidth of two different job, different structure of circuit design, the virtual simulation experiment to negative group delay phenomenon and measurement data. It is of great significance to explore the field of faster-than-light and negative group delay in today's rapidly developing information age, and it can try to meet the high requirements for signal transmission. In the future, the interdisciplinary research direction of this research topic also has great development space.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Fabricate the Auto-aquaculture Structure with Android Monitoring System
- Abstract: Based on the Android monitoring system, the automated fish feeder has been developed. The system provides a convenient and reliable solution for fish farmers. This system includes a fish feeder that distributes food at predetermined intervals. The Android application allows farmers to monitor and control the feeding process remotely. The application displays the current feeding schedule. At the same time, the users can adjust the frequency and amount of food dispensed. The alarm function can send the notification information to the farmer’s mobile phone if the feeder experiences any issues or requires maintenance. By automating the feeding process and providing real-time monitoring, the system can help farmers optimize fish growth and health while reducing the time and effort required for artificial feeding.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Research on Extraction Method of Financial Knowledge Based on How Net
- Abstract: In order to obtain the knowledge information of financial texts more efficiently and make the extracted information such as entity relation attribute more accurate, this paper studies the grammatical features of financial news texts and the semantic features of How Net, and puts forward the scheme of financial information extraction based on How Net. First, the phrase matching is carried out in the dictionary. Then the neural network is used for weighting, BiLSTM is used for character vector feature enhancement training, and then conditional random field (CRF) is used to complete named entity recognition, and then the relationship extraction of entity pairs from the dependency syntax is carried out to complete the research on the construction method of knowledge extraction of text in the financial field. The experimental results show that this model is superior to the other three models in entity recognition, and the overall performance is improved by about 1.2%. In relation extraction, the accuracy and recall rate of the model algorithm adopted in this paper are improved by 5% and 1.5% respectively, which shows that the improvement of the algorithm is effective.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Real-time Satellite Anomaly Data Tagging Based on DAE-LSTM
- Abstract: Spacecraft is the main carrier of human exploration of outer space, exploration and understanding of the Earth and the universe, and the development of spaceflight can promote human civilization andsocial development, and can meet the nee-ds of economic construction, scientific and technological development, security construction, social progress and other aspects. The current global number of satellites in orbit reaches 5,465, of which China has 541. The vigorous development of the space industry symbolizes the steady improvement of the country’s comprehensive national power and overall technology. During the operation, the satellite in orbit needs to transmit data to the ground, these data may be subject to interference from various aspects, or even equipment failure, we find these data in real time is very important to reduce losses. The data transmitted by satellite has obvious temporal characteristics, and Long Short-Term Memory (LSTM) network has obvious advantages for processing temporal data, so this paper proposes a BER marking model based on the combination of LSTM network and self-coding technology. By comparing the data before and after noise reduction, a threshold value can be determined, and the BERs can be accurately distinguished by this method. After testing with real satellite temperature data, the accuracy of the model detection reaches a high level.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Product Recommendation System Based on Deep Learning
- Abstract: With the development of Internet big data and e-commerce, the widespread popularity of information, information acquisition and personalized recommendation technologies have attracted extensive attention. The core value of personalized recommendation is to provide more accurate content and services around users. The recommended scenarios are not uniform, and different dimensions need to be considered. For example, we are facing enterprises or individuals, different age groups, different levels of education, social life and other aspects. In this paper, the classic DNN (Deep Neural Networks) double tower recommendation algorithm in the recommendation algorithm is used as the ranking algorithm of the recommendation system. It is divided into user and item for embedding respectively. The network model is built using tensorflow. The data processed by the initial data through feature engineering is sent into the model for training, and the trained DNN double tower model is obtained. Recall adopts collaborative filtering algorithm, and applies tfidf, w2v, etc. to process feature engineering, so as to better improve the accuracy of the system and balance the EE problem of the recommendation system. The recommendation module of this system is divided into data cleaning as a whole. Feature engineering includes the establishment of user portraits, the analysis of multiple recall and sorting algorithms, the adoption of multiple recall mode, and the implementation of a classic recommendation system with in-depth learning. This makes the recommendation system better balance the interests of both the platform and users, and achieve a win-win situation.
  PubDate: Wed, 31 May 2023 00:00:00 GMT
Construction of Driving Condition Based on Discrete Fourier Transform and
Improved K-Means Clustering Algorithm
- Abstract: In view of the low execution efficiency and slow convergence speed of traditional clustering algorithms, the initial clustering center has a greater impact on the clustering results, which leads to the problem of reduced algorithm accuracy. This paper proposes an improved K-means algorithm (Grid-K-means), that is, the Grid density is used to determine the initial clustering center; According to the density, the grid points are sorted to eliminate the idea of noise grid points and invalid grid points, so as to improve the efficiency and accuracy of the algorithm. First, the discrete Fourier transform was used to filter the original data, and then the principal component analysis and the improved K-means clustering algorithm were used to reduce and classify the kinematics fragments respectively, so as to construct the driving conditions of the vehicle. The experimental results show that this method can effectively improve the construction accuracy and reduce the construction time, and the fitted driving conditions can effectively reflect the local actual traffic conditions.
  PubDate: Wed, 31 May 2023 00:00:00 GMT