AUTOMATIC CONTROL AND COMPUTER SCIENCES最新文献

An Intelligence Algorithm for Solving the FDCP Model 求解FDCP模型的智能算法

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411626700513

Ning Xiao, Jin Wang, Xin Wang, Yudong Wang

{"title":"An Intelligence Algorithm for Solving the FDCP Model","authors":"Ning Xiao, Jin Wang, Xin Wang, Yudong Wang","doi":"10.3103/S0146411626700513","DOIUrl":"10.3103/S0146411626700513","url":null,"abstract":"Fuzzy programming has shown great vitality in the fields of management, optimal control, economics, power dispatch, and other applications. However, the algorithm that solves such problems has not made significant progress due to the injection of fuzzy parameters. This study aimed to propose a novel intelligent algorithm combining fuzzy simulation, multilayer backpropagation (BP) artificial neural networks, and the stochastic particle swarm optimization (SPSO) algorithm to solve the fuzzy dependent-chance programming (FDCP) model problem in the fuzzy programming field more efficiently. In this computational method, fuzzy simulation was used to acquire training samples for multilayer BP artificial neural networks, and the artificial neural networks were used to approximate the fuzzy chance function. Also, SPSO was used to complete iterative optimization. Meanwhile, in SPSO, the neural networks were used to compute the fuzzy chance function. Our algorithm addressed several constraints such as a long run time, intricate computation, and a tendency to get trapped in a locally optimal value in the mixed algorithm with intelligence based on the classic genetic algorithm. The results for the issues related to the fuzzy dependent-chance programming model were validated by some cases. Also, the validity and reliability of the algorithm were verified, highlighting its application value.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"325 - 333"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real Time Recognition and Error Quantification System for Difficult Movements in Aerobics Based on Spatiotemporal Graph Convolutional Network 基于时空图卷积网络的健美操高难度动作实时识别与误差量化系统

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411625602539

Rong Tian, Xin Feng

{"title":"Real Time Recognition and Error Quantification System for Difficult Movements in Aerobics Based on Spatiotemporal Graph Convolutional Network","authors":"Rong Tian,  Xin Feng","doi":"10.3103/S0146411625602539","DOIUrl":"10.3103/S0146411625602539","url":null,"abstract":"Aerobics, a dynamic physical activity promoting cardiovascular fitness and muscular strength, can be challenging for beginners due to the precision and synchronization required in complex routines. To address this challenge, this research introduces a real-time recognition and error quantification system specifically designed for analyzing difficult movements in aerobics, leveraging the capabilities of deep learning (DL). The system integrates wearable biosensing devices with spatiotemporal graph convolutional network (ST-GCN) to capture and analyze motion skelton data, including joint trajectories and anatomical position. Preprocessing using Z-score normalization followed by feature extraction through fast fourier transform (FFT). The error quantification system involves alignment of the user’s real-time skeletal sequence with a standard expert template using dynamic time warping, computation of joint-wise angular deviation and trajectory differences across frames, and scoring based on cumulative spatial-temporal deviations. The process yields interpretable deviation numerical performance scores, aiding athletes in correcting posture and timing. To enhance the system’s accuracy and learning efficiency, optimization techniques, such as gases Brownian motion optimization (GBMO) are employed. Comparative evaluations reveal that the proposed ST-GCN model significantly outperforms baseline models achieving accuracy (0.989), precision (0.992), recall (0.991), and F1-score (0.990) for peak recognition accuracy compared to standard traditional networks. Overall, the system offers a significant advancement in intelligent sports training by combining deep learning, real-time motion analysis, and biomechanical evaluation for precise aerobic movement assessment.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"349 - 362"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Enhanced Hybrid Scheduling Approach in Hadoop MR Framework Hadoop MR框架中一种增强的混合调度方法

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411625603454

R. Vignesh, M. Chennakesava Rao, K. Chaitanya, Akhila Ravi, Joel Sunny Deol Gosu, Mutyala Satish

{"title":"An Enhanced Hybrid Scheduling Approach in Hadoop MR Framework","authors":"R. Vignesh, M. Chennakesava Rao, K. Chaitanya, Akhila Ravi, Joel Sunny Deol Gosu, Mutyala Satish","doi":"10.3103/S0146411625603454","DOIUrl":"10.3103/S0146411625603454","url":null,"abstract":"Every year, more and more data is produced by people due to the development of new technologies like social networking sites, gadgets, and communication tools. Large data sets that cannot be processed using conventional computing methods are called “big data.” The introduction of MapReduce has addressed big data computing issues. It is based on the divide and conquer strategy and is designed to run on affordable hardware. Researchers’ attention is now primarily on Hadoop MapReduce. One of MapReduce’s most important features is scheduling, which can pinpoint the data’s location. One or more performance indicators (such as data location, energy use, and job completion time) can be optimized with the help of the data location-aware scheduler. As in all situations, the MapReduce framework’s most crucial features are time and scheduling. By running concurrent workloads made up of Terasort benchmarks and Word count benchmarks, it is suggested that you evaluate the algorithm and compare it to the Hadoop default scheduler (FIFO, regular). Experimental evaluation using concurrent Terasort and Word count workloads demonstrates that the proposed HybSMRP scheduler improves data locality and reduces execution overhead. The results show that the proposed method achieves higher data localization rates and reduces average job completion time by approximately 15–20% compared to the default Hadoop FIFO and Fair schedulers. These improvements lead to better resource utilization and minimized network overhead, thereby enhancing overall system performance.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"287 - 292"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploration of Address Resolution Cache Attacks and Defense Technologies in IPV6 Networks IPV6网络中地址解析缓存攻击及防御技术研究

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411625600905

Xilai Wang, Gang Wang, Yiyi Jiang, Yonghui Meng, Jiandeng Huang

{"title":"Exploration of Address Resolution Cache Attacks and Defense Technologies in IPV6 Networks","authors":"Xilai Wang, Gang Wang, Yiyi Jiang, Yonghui Meng, Jiandeng Huang","doi":"10.3103/S0146411625600905","DOIUrl":"10.3103/S0146411625600905","url":null,"abstract":"The widespread application of IPv6 networks has brought about greater address space and performance improvements, but it is also accompanied by security threats such as address resolution cache attacks. These attacks achieve deception and denial of service by faking neighbor discovery messages, causing the target device to cache incorrect address information. Although traditional defense technologies such as firewalls and IPsec (Internet Protocol Security) can reduce harm, they have limitations in dynamic adaptability and real-time detection, making it difficult to cope with new and variant attacks. This article focuses on address resolution cache attacks in IPv6 networks and studies real-time monitoring methods based on convolutional neural network (CNN). By constructing a CNN model, network traffic features are automatically extracted, and attack patterns are identified. The experimental results show that the address resolution cache attack detection method based on CNN has a minimum accuracy of 88.55% and a maximum accuracy of 97.84% under different intensities of address resolution cache attacks. It exhibits high detection accuracy under different attack intensities, effectively distinguishing between normal traffic and malicious attacks and improving the security protection capability of IPv6 networks. This article provides not only new technological means for IPv6 network security but also valuable references for teaching and practice in related fields.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"304 - 316"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Adaptive Data Transmission and Efficient Congestion Control in Wireless Acoustic Sensor Networks 无线声学传感器网络中的动态自适应数据传输与有效拥塞控制

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411625602928

Utpal Ghosh, Shrabanti Kundu

{"title":"Dynamic Adaptive Data Transmission and Efficient Congestion Control in Wireless Acoustic Sensor Networks","authors":"Utpal Ghosh,  Shrabanti Kundu","doi":"10.3103/S0146411625602928","DOIUrl":"10.3103/S0146411625602928","url":null,"abstract":"Wireless acoustic sensor networks (WASNs) represent a unique set of challenges and opportunities in the realm of data transmission and routing due to their inherent characteristics and environmental constraints. This paper explores the concept of adaptive transmission flow control and route sensing within WASNs, focusing on addressing route congestion and optimizing communication efficiency. This research proposes an adaptive, cost-effective and dynamic energy-efficient architecture for real-time data transmission across distributed points, along with a congestion control scheme for congestion avoidance, detection and mitigation within WASNs. The main goal of this system is to efficiently transmit data while reducing transmission time, with a crucial focus on maintaining high-quality data transmission even during congested situations. The proposed approach leverages route maps to dynamically adapt transmission paths based on real-time congestion sensing, allowing nodes to intelligently reroute data to avoid bottlenecks and optimize network performance. Additionally, receiver capability is considered as a key factor in the adaptive routing process, ensuring that data is efficiently delivered to intended recipients even under varying network conditions. By integrating adaptive data transmission and route congestion sensing capabilities, serving a dual role in both transmitting data information to the access point for storing information of data collected throughout the operational cycle and control the congestion into WASNs. This research contributes to enhancing the reliability, energy efficiency, multihop communicability and adaptability of data transmission in acoustic sensor networks, paving the way for improved performance and scalability in diverse application scenarios.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"389 - 405"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of Power System Signal Processing Method Based on Deep Convolutional Neural Network 基于深度卷积神经网络的电力系统信号处理方法分析

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411624603824

Hai Xue, Nan Yao, Qing Fan, Ziquan Liu, Zhengyu Liu

引用次数: 0

Baseline Study of Machine Learning Applications for Power Grid Damage Prediction in Latvia 机器学习在拉脱维亚电网损伤预测中的应用基线研究

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411626700549

Arnis Stasko, Eduards Otomers, Andrejs Bondarenko, Rihards Sirmais, Kārlis Kristofers Vēliņš, Dmitrijs Bļizņuks, Ilze Birzniece

引用次数: 0

Hybrid Deep Reinforcement and Ensemble Learning for Intrusion Detection in Autonomous Vehicle Can Networks 基于混合深度强化和集成学习的自动驾驶汽车网络入侵检测

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411626700525

Manivannan Thulasiraman, Lordwin Cecil Prabhaker

{"title":"Hybrid Deep Reinforcement and Ensemble Learning for Intrusion Detection in Autonomous Vehicle Can Networks","authors":"Manivannan Thulasiraman,  Lordwin Cecil Prabhaker","doi":"10.3103/S0146411626700525","DOIUrl":"10.3103/S0146411626700525","url":null,"abstract":"Autonomous vehicles (AVs) rely heavily on the controller area network (CAN) for internal communication among sensors and actuators. However, this protocol lacks built-in security mechanisms, making AVs vulnerable to cyber-attacks such as denial of service (DoS), fuzzy, and impersonation attacks. This work proposes a hybrid intrusion detection system (IDS) that integrates Rainbow deep Q-network (DQN), a reinforcement learning technique, with a random forest classifier to improve the detection accuracy and robustness against such attacks in real-time AV environments. The methodology involves preprocessing CAN traffic datasets into state-action representations suitable for reinforcement learning. Rainbow DQN learns optimal policies by leveraging prioritized experience replay, duelling architecture, and multistep bootstrapping to predict attack probabilities. The output Q-values are then passed to a random forest classifier, which refines the decision boundaries using ensemble voting, thus enhancing classification precision. The implementation was carried out using Python (PyTorch and scikit-learn) on a labelled CAN intrusion dataset comprising attack-free and malicious traffic. Experimental results demonstrate that the proposed hybrid model outperforms standalone rainbow DQN in terms of classification performance, achieving an accuracy of 87.93%, an F1-score of 0.86, and a reduced false alarm rate of 3.2%. These findings establish the effectiveness of combining deep reinforcement learning with ensemble learning for reliable and scalable intrusion detection in AVs.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"334 - 348"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human–Computer Interaction System and Design Based on Expression Recognition 基于表情识别的人机交互系统与设计

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411626700537

Xin Wang, Feifei Tian, Yi Jin Chen

{"title":"Human–Computer Interaction System and Design Based on Expression Recognition","authors":"Xin Wang, Feifei Tian, Yi Jin Chen","doi":"10.3103/S0146411626700537","DOIUrl":"10.3103/S0146411626700537","url":null,"abstract":"Human–computer interaction (HCI) has advanced into another age arising from developments in artificial intelligence that allow machines to comprehend and interpret human emotions dynamically. Modern systems confront challenges such as noisy input data and emotion classification accuracy, impeding adaptability in interactive environments. This work proposes a design of an intelligent HCI system for interpreting human emotions to improve better decision-making in intervention applications for human–computer collaboration in virtual reality (VR) applications. Initially, data acquisition of facial emotion expressions was done, which is followed by preprocessing techniques, including Savitzky–Golay filtering for noise removal and quadratic contrast stretching for contrast enhancement to improve clarity of the image. Subsequently, feature extraction via GhostNet along with the emotion classification through ShuffleNetV2, the classified emotions are integrated into the HCI system for dynamic adjustments based on user emotion, thereby fostering immersion and engagement in VR. Experimental evaluation shows the efficiently of proposed model performance with an accuracy of 99.80%, a precision of 99.77%, recall of 99.79%, and F1-score of 99.78%. These signify that the system can suggestively impact collaborative work between humans and computers, giving users personalized experiences and intelligent automation capabilities.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"406 - 424"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Multistage Energy Efficient and Secure Node Localization Policy for Wireless Sensor Networks 无线传感器网络的多级节能安全节点定位策略

IF 0.5

AUTOMATIC CONTROL AND COMPUTER SCIENCES Pub Date : 2026-10-19 DOI: 10.3103/S0146411625602783

T. P. Mohankumar, R. M. Raveesh, H. D. Kallinatha

{"title":"A Multistage Energy Efficient and Secure Node Localization Policy for Wireless Sensor Networks","authors":"T. P. Mohankumar, R. M. Raveesh, H. D. Kallinatha","doi":"10.3103/S0146411625602783","DOIUrl":"10.3103/S0146411625602783","url":null,"abstract":"Accurate and secure node localization in wireless sensor networks (WSNs) continues to resist straightforward solutions, even as the research community has invested considerable effort over the past two decades. Scalability failures, poor adaptability under node mobility, and the persistent vulnerability to rogue node attacks collectively undermine the practical value of many otherwise promising algorithms. This paper introduces SABWP-NL a multi stage localization framework that brings together self-adaptive binary waterwheel plant optimization (SABWP) and Bayesian optimization to simultaneously address localization accuracy, energy consumption, scalability, and network security. A mobile anchor traverses the deployment area to supply fresh positional references, after which the trustworthiness of each node is evaluated through Dempster–Shafer evidence theory before any spatial computation is attempted. Localization itself is then carried out via a combined trilateration multilateration scheme governed by the SABWP algorithm. The experimental results are unambiguous: with ten anchor nodes, SABWP-NL localizes 15.5, 44.7, and 30.7% more nodes than BWP, ROA, and AO, respectively, and reduces localization error by up to 52.6% relative to AO. At fifty anchors, the error reduction against AO reaches 82.4%. These figures position SABWP-NL as a competitive and practically deployable solution for security sensitive WSN deployments.","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 3","pages":"293 - 303"},"PeriodicalIF":0.5,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0