Fangfang Zhang;Yongqi Wang;Jianbin Xin;Haijing Wang;Jinzhu Peng;Yaonan Wang
{"title":"Improved GBNN Guided Multirobot Coverage Search Based on Neuronal Connectivity","authors":"Fangfang Zhang;Yongqi Wang;Jianbin Xin;Haijing Wang;Jinzhu Peng;Yaonan Wang","doi":"10.1109/JSYST.2025.3567283","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3567283","url":null,"abstract":"The multirobot coverage search problem in unknown environments has attracted significant attention. However, the existing methods are inefficient in the search process. The aim of the present study is to improve the search efficiency through an enhanced bioinspired neural network method. In this work, a connected Glasius bioinspired neural network (CGBNN) model is introduced to address the lack of consideration for neuronal connectivity and transmission properties in existing studies. The dynamic search environment is represented by the changes in neurons' activity values, which guide the robots in performing the search task. Each robot automatically plans its search path according to the principle of the decreasing gradient of CGBNN activity values until the task is completed. Experimental results demonstrate that the robots can avoid different types of obstacles to complete the coverage search, confirming the effectiveness of the proposed method. Meanwhile, it indicates that the proposed method outperforms others, the coverage rate is improved by 6.90%, 6.22%, and 4.02% compared to the GBNN, A-RPSO, and DMPC algorithms, respectively. In adition, the decision time is less affected by the complexity of the environment, which fulfills the practical demands of real-time decision-making in a large-scale complex environment.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"701-711"},"PeriodicalIF":4.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144339028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"TL-ConvLSTM: A Transfer-Learning-Based Convolutional LSTM to Identify and Forecast Traffic in the NextG Environments","authors":"Bikash Chandra Singh;Peter Foytik;Rafael Diaz;Sachin Shetty","doi":"10.1109/JSYST.2025.3569445","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3569445","url":null,"abstract":"Forecasting and categorizing cellular traffic flows and their types are essential functions in intelligent network systems to ensure efficient network optimization. The ever-evolving nature of 5G networks results in fluctuations in traffic patterns over time, leading to a phenomenon known as model drift. Consequently, accurately predicting and identifying cellular traffic patterns becomes a complex task. To tackle this challenge, this article introduces an innovative approach called <italic>TL-ConvLSTM</i>, which combines transfer learning with convolutional long short-term memory (ConvLSTM) to effectively combat model drift and provide precise forecasting and recognition of cellular traffic within the network. To accomplish this, we initiate the training of <italic>TL-ConvLSTM</i> by estimating its parameters from the source domain. We then employ the Kolmogorov–Smirnov method to adapt the model within the target domain, fine tuning its weights. To improve the precision of this model adaptation, we systematically explore optimal learning windows. This exploration includes adjusting window size for time-series data and feature dimensions to capture dynamic traffic patterns in a 5G environment. Furthermore, we make use of the Amarisoft 5G testbed in our lab to create a 12-day time-series dataset. This dataset includes various features related to traffic flows and their patterns. We showcase the effectiveness of our approach through a set of experiments.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"358-369"},"PeriodicalIF":4.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DAMAGE: Directed Heterogeneous Network Attack Sequence Inference Through Graph Attention Matrix Generation Embedding and Reinforcement Learning","authors":"Hongfu Liu;Chengyi Zeng;Zhen Li;Lina Lu;Jing Chen;Zongtan Zhou","doi":"10.1109/JSYST.2025.3547491","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3547491","url":null,"abstract":"Distributed heterogeneous multiagent systems (DHMASs) link geographically dispersed agents through networks, harnessing information technology to foster collaboration. Considering the mainstream status of wireless communication in modern multiagent systems and the differences in the performance of interagent communication devices, we believe that it is appropriate to use directed heterogeneous networks (DHNs) to model distributed heterogeneous multiagent systems. This model not only reflects the directionality of interagent communication but also reflects the complexity of communication due to performance differences, thus providing a more accurate framework for understanding and optimizing system behavior. The study of disintegration in DHNs is vital for enhancing the decision-making agility of DHMAS. We introduce <underline>D</u>irected heterogeneous network <underline>A</u>ttack sequence inference through graph attention <underline>MA</u>trix <underline>G</u>eneration <underline>E</u>mbedding and reinforcement learning (DAMAGE), an algorithm that integrates graph neural networks and reinforcement learning within an inductive reasoning framework. DAMAGE is designed to optimize the generation of disintegration strategies, improving the efficiency of network breakdown processes. Our approach includes a directed network embedding technique with a graph attention matrix generation module, which enhances the utilization of imperfect network structure information. Through ablation studies, we demonstrate that DAMAGE not only increases the effectiveness of network disintegration under perfect topological conditions but also maintains robustness in scenario with imperfect topological information.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"392-403"},"PeriodicalIF":4.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Permutation-Based Firmware Remote Attestation for Internet-of-Things Edge-Based Network","authors":"Zainab AlJabri;Jemal H. Abawajy","doi":"10.1109/JSYST.2025.3550055","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3550055","url":null,"abstract":"Firmware security in edge-enabled IoT devices is crucial, but existing methods struggle to balance strong protection with realistic hardware trust assumptions, device privacy, nontraceability, and resilience against attacks. This article addresses these challenges by introducing a novel permutation-based firmware attestation mechanism. Our method leverages edge servers as verifiers, low-cost memory, randomized permutations, and avalanche criteria for optimized security and efficiency. Rigorous formal and informal security analysis, coupled with performance evaluation, demonstrates superior performance against various attacks, achieving over 90% detection probability and effectively mitigating both remote and mobile software attacks. These results demonstrate the significant potential of our approach for enhancing firmware security in edge-enabled IoT devices.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"346-357"},"PeriodicalIF":4.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quantum Reinforcement Learning for QoS-Aware Real-Time Job Scheduling in Cloud Systems","authors":"Shuhong Dai;Nishant Saurabh;Qingle Wang;Jiawei Nian;Shuwen Kan;Ying Mao;Long Cheng","doi":"10.1109/JSYST.2025.3568752","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3568752","url":null,"abstract":"Effective cloud job scheduling is essential for enhancing the performance and operational efficiency of cloud-based services, directly impacting their quality of service (QoS). Among existing methodologies, deep reinforcement learning (DRL) has proven effective in addressing complex, multidimensional optimization challenges in real-time scheduling. With advancements in quantum computing, quantum neural networks (QNNs) are showing unique advantages in information representation and processing. This study is the first to explore quantum reinforcement learning (QRL) for real-time job scheduling in cloud systems. Specifically, we propose a QRL framework that utilizes variational and encoding layers to convert state information into quantum data, repeatedly embedded into a QNN to compute optimal value returns. This approach aims to enhance QoS by improving job execution success rates and reducing average response times with unpredictable job arrivals. We present the detailed design of our approach, and our simulation results demonstrate that the QRL method significantly exceeds established baselines, including those based on DRL, across a range of workload intensities and computational resource configurations. This is particularly evident under high-load conditions, where our approach can achieve 55.2% higher success rates, underscoring its significant potential in cloud job scheduling optimization.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"471-482"},"PeriodicalIF":4.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Path Planning for Cooperative Aerial Load Transportation in Complex Environments","authors":"Peyman Abeshtan;Fariborz Saghafi","doi":"10.1109/JSYST.2025.3547065","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3547065","url":null,"abstract":"In this article, a planning algorithm is presented, which is capable to design an overall path in the first stage and determine the formation shape of a cooperative load transportation system forced to move in a spatial hypothetical tunnel (an authorized tunnel), in the second stage. The planning algorithm works in multipassages environment containing obstacles with different shapes and dimensions. The shape of the formation is determined optimally to handle nonconvex constraints like obstacle avoidance, intercollision avoidance between agents and allowable range of cable forces for minimal swing motion. The optimization algorithm also considers the response of the system dynamics and ability of controllers in tracking the optimal path and formation shape. Three types of optimization-based path planning methods are presented called simultaneously all waypoints, waypoint by waypoint (WBW), and waypoints in risk. It is shown that the WBW method presents the best performance in terms of adjustment of the formation shape for passing through narrow passages in complex environment without external or internal collision.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"565-576"},"PeriodicalIF":4.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive Consensus Tracking Control for Nonlinear Multiagent Systems With Unknown Dynamics: A State Observer-Based Framework","authors":"Xiao Chen;Jinsha Li;Jiaxi Chen;Junmin Li;Weisheng Chen","doi":"10.1109/JSYST.2025.3562957","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3562957","url":null,"abstract":"In this study, we introduce an observer-based adaptive output-feedback tracking consensus approach designed for a class of uncertain nonlinear leader–follower multiagent systems. Each follower agent exhibits second-order unknown nonlinear dynamics, incorporates unmeasured states, and possesses an unknown control direction. To tackle these challenges, fuzzy logic system is integrated with an observer, and a Nussbaum-type item is integrated into the protocol for each agent to adaptively and cooperatively determine the control direction. Subsequently, we have developed adaptive fuzzy distributed control protocols for each follower agent. The proposed consensus protocols have been demonstrated to ensure semiglobally uniformly ultimate boundedness for all system signals. Furthermore, we extend the control gain from constant to a state-dependent gain, delving into the globally uniformly ultimate boundedness of multiagent systems. To mitigate the intricacies arising from virtual control differentiation, command filtering is integrated with backstepping techniques, thereby streamlining the control process and enhancing overall system performance. The efficacy of the proposed method has been validated through simulation examples.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"447-458"},"PeriodicalIF":4.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Safety Analysis and Prediction of UAVs Aerial Refueling Docking Based on Deep Learning Data-Driven Method","authors":"Bin Hang;Shuai Liang;Pengjun Guo;Bin Xu","doi":"10.1109/JSYST.2025.3546476","DOIUrl":"https://doi.org/10.1109/JSYST.2025.3546476","url":null,"abstract":"Autonomous aerial refueling (AAR) is essential for both military and civilian applications, but the docking phase poses significant safety risks due to complex environmental conditions that cannot be fully captured by precise mathematical models. This article proposes a data-driven docking predictive model that integrates variational mode decomposition (VMD), sparrow search algorithm (SSA), and long short-term memory (LSTM) neural networks. First, a comprehensive simulation platform for the entire AAR docking system is established to generate reliable data. Then, to address the complex nature of AAR docking signals, VMD decomposes the data into modes with distinct natural frequencies, enhancing input accuracy. SSA optimizes the LSTM parameters, improving prediction accuracy and avoiding local minima. Based on these predictions, a docking safety evaluation network is developed to assess docking safety and prevent failures or collisions. Finally, the performance comparison with other models demonstrates the effectiveness of the proposed approach in diverse scenarios.","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 2","pages":"529-540"},"PeriodicalIF":4.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IEEE Systems Journal Information for Authors","authors":"","doi":"10.1109/JSYST.2024.3525313","DOIUrl":"https://doi.org/10.1109/JSYST.2024.3525313","url":null,"abstract":"","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 1","pages":"C4-C4"},"PeriodicalIF":4.0,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10929691","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IEEE Systems Council Information","authors":"","doi":"10.1109/JSYST.2024.3525315","DOIUrl":"https://doi.org/10.1109/JSYST.2024.3525315","url":null,"abstract":"","PeriodicalId":55017,"journal":{"name":"IEEE Systems Journal","volume":"19 1","pages":"C3-C3"},"PeriodicalIF":4.0,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10929694","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}