IEEE Transactions on Systems Man Cybernetics-Systems最新文献_第3页

Rank-Based Learning and Local Model-Based Evolutionary Algorithm for High-Dimensional Expensive Multiobjective Problems 高维昂贵多目标问题的秩学习和局部模型进化算法

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-04 DOI: 10.1109/TSMC.2026.3656639

Guodong Chen;Jiu Jimmy Jiao;Xiaoming Xue;Zhongzheng Wang

{"title":"Rank-Based Learning and Local Model-Based Evolutionary Algorithm for High-Dimensional Expensive Multiobjective Problems","authors":"Guodong Chen;Jiu Jimmy Jiao;Xiaoming Xue;Zhongzheng Wang","doi":"10.1109/TSMC.2026.3656639","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3656639","url":null,"abstract":"Surrogate-assisted evolutionary algorithms (SAEAs) have been widely developed to solve complex and computationally expensive multiobjective optimization problems (EMOPs) in recent years. However, when dealing with high-dimensional optimization problems in decision space, the performance of these surrogate-assisted multiobjective evolutionary algorithms (MOEAs) deteriorates drastically. In this work, a novel classifier-assisted rank-based learning and local model-based multiobjective evolutionary algorithm (CLMEA) is proposed for high-dimensional EMOPs. CLMEA makes full use of the uncertainty of solutions in the decision space and objective space to explore the uncertain but informative space toward high-dimensional problems. Specifically, the offspring in different ranks uses rank-based learning strategy to generate more promising and informative candidates for function evaluations (FEs). To reduce the search region of high-dimensional problems and maintain the diversity of solutions, the most uncertain sample point from the nondominated solutions measured by the crowding distance is selected as the center to conduct local search. The experimental results of benchmark problems and a real-world application on geothermal reservoir heat extraction optimization demonstrate superior performance of CLMEA compared with the state-of-the-art surrogate-assisted MOEAs. The source code for this work is available at <uri>https://github.com/JellyChen7/CLMEA</uri>","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3272-3285"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multitense Knowledge Transfer for Asynchronous Multitasking Optimization 异步多任务优化的多时态知识转移

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-03-02 DOI: 10.1109/TSMC.2026.3658328

Honggui Han;Ben Zhao;Xiaolong Wu;Xin Li

{"title":"Multitense Knowledge Transfer for Asynchronous Multitasking Optimization","authors":"Honggui Han;Ben Zhao;Xiaolong Wu;Xin Li","doi":"10.1109/TSMC.2026.3658328","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3658328","url":null,"abstract":"Multitasking optimization (MTO), addressing multiple optimization problems synchronously, has achieved significant success in the field of evolutionary computation. However, in practice, few tasks are accomplished synchronously due to asynchronous initialization. In this article, an asynchronous MTO (AMTO) paradigm is proposed, which aims to deal with multiple optimization problems with asynchronous arrivals. Due to the asynchronous characteristic of tasks, there is multiple tenses knowledge in an AMTO environment. Transferring multitense knowledge may accelerate the optimization process of the target task. Also, an AMTO algorithm is proposed to transfer multitense knowledge. The past-tense knowledge is transferred by an initialization strategy, which selects effective knowledge to deal with mismatched tenses. And the present-tense knowledge is transferred by knowledge reuse, which aligns convergence intervals to handle mismatched evolutionary states. Finally, several AMTO test problem sets and a practical problem are designed to verify the performance of the proposed algorithm. The experimental results show that the performance of the algorithm can be improved by multitense knowledge transfer.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3370-3383"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HDEFG-UFormer: A Hierarchical Depthwise-Expanded Feature Grouping Transformer-Based UNet for Gastrointestinal Disease Segmentation HDEFG-UFormer：一种基于层次深度扩展特征分组变压器的胃肠道疾病分割UNet

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3659057

Anass Garbaz;Yassine Oukdach;Said Charfi;Mohamed El Ansari;Lahcen Koutti;Mouna Salihoun

{"title":"HDEFG-UFormer: A Hierarchical Depthwise-Expanded Feature Grouping Transformer-Based UNet for Gastrointestinal Disease Segmentation","authors":"Anass Garbaz;Yassine Oukdach;Said Charfi;Mohamed El Ansari;Lahcen Koutti;Mouna Salihoun","doi":"10.1109/TSMC.2026.3659057","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3659057","url":null,"abstract":"Gastrointestinal (GI) disease segmentation is challenging due to the variability in lesion appearance, size, and location across imaging modalities. Accurate segmentation is essential for diagnosis and treatment planning, but traditional methods often fail to balance local details and global context. CNNs and Transformers offer complementary strengths in image processing. CNNs detect local patterns, while Transformers use self-attention to capture global context. Integrating both architectures has been shown to improve performance in various medical imaging tasks. In this study, we propose HDEFG-UFormer, a model based on the hierarchical depthwise-expanded feature grouping transformer (HDEFG-Former). It includes the HDEFG block for capturing local spatial details and expanding receptive fields through multiscale features. We integrate the concentration-driven feature enhancement transition (CDFET) module to improve the flow of information between layers. This module balances both local and global contexts. The transformative hierarchical context integration transformer (THCI-Former) further enhances feature aggregation. It also integrates a hierarchical context for more precise semantic interpretation. HDEFG-UFormer addresses segmentation challenges by combining depthwise (DW) convolution with Transformer-based context integration. Its multiscale feature extraction ensures adaptability to different imaging modalities and lesion types. The model achieved Dice coefficients (DCs) of 92.45% on the MICCAI 2017 (Red Lesion) dataset and 90.08% on the CVC-ClinicDB dataset. Finally, to demonstrate robustness across imaging modalities and assess generalization, HDEFG-UFormer achieved a DC of 95.06% on the dermoscopic PH2 dataset.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3408-3419"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Event-Based Distributed Output Feedback Intermittent Control for Cyber–Physical Systems Resilient to Denial-of-Service Attacks 网络物理系统抗拒绝服务攻击的动态事件分布式输出反馈间歇控制

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3655012

Zhenyu Chang;Ying Guo;Guangdeng Zong;Wenhai Qi;Xudong Zhao

{"title":"Dynamic Event-Based Distributed Output Feedback Intermittent Control for Cyber–Physical Systems Resilient to Denial-of-Service Attacks","authors":"Zhenyu Chang;Ying Guo;Guangdeng Zong;Wenhai Qi;Xudong Zhao","doi":"10.1109/TSMC.2026.3655012","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3655012","url":null,"abstract":"This article investigates the security control problem of cyber–physical systems (CPSs) under denial-of-service (DoS) attacks. These attacks disrupt the information transmission within the system, thus making the system unstable or even paralyzed. In addition, due to environmental uncertainties, it is usually impossible to acquire the full-state measurement in practice. To overcome the above challenges, this article constructs a switching observer to estimate the system state and combines the distributed intermittent control (IC) protocol to construct a security control strategy. The dynamic event-triggering (ET) method is utilized to adjust the control signal update frequency during the attack dormant period, reducing the network bandwidth occupation. The IC strategy is designed in combination with the switching state observer to guarantee operational security during the active attack period. Theoretical analysis proves that the system consensus error achieves asymptotic convergence and that Zeno behavior in the ET process is strictly excluded. The developed control strategy is employed on the wheeled mobile robotic system for simulation to verify its effectiveness.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3186-3195"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Homomorphic-Encryption-Based Secondary Voltage Regulation Secure Strategy for Multimicrogrids With Self-Updating Final Boundary Funnel Constraint 具有自更新终边界漏斗约束的多微电网基于同态加密的二次稳压安全策略

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3656439

Zeyi Liu;Huaguang Zhang;Jiayue Sun;Ying Yan

{"title":"Homomorphic-Encryption-Based Secondary Voltage Regulation Secure Strategy for Multimicrogrids With Self-Updating Final Boundary Funnel Constraint","authors":"Zeyi Liu;Huaguang Zhang;Jiayue Sun;Ying Yan","doi":"10.1109/TSMC.2026.3656439","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3656439","url":null,"abstract":"This article designs a homomorphic-encryption-based information transmission framework and a novel self-updating final boundary funnel function (SFBF) for the secondary voltage regulation problem of distributed multimicrogrid systems (MMGSs). First, based on the designed objective function, the proposed SFBF method can update the constraint boundary to balance the energy consumption and voltage synergy error of the system. This ensures that the consistency error does not exceed the boundary and does not consume too much energy. Second, a distributed MMGS information exchange framework is constructed based on a homomorphic encryption method, which effectively protects neighboring microgrids (MGs) and reference signals, avoiding the leakage of sensitive and valuable information, and effectively improving the information security. In addition, the MMGS is transformed into a controllable system by using linearization methods, and the additional unknown model information and disturbances introduced are solved through adaptive fuzzy methods. Based on the two strategies proposed above and the transformed system, an effective control method is designed to achieve secondary voltage regulation in MMGSs. Finally, the effectiveness of the proposed method is verified through Lyapunov theory and simulation results.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3210-3219"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rendezvous Optimization for Second-Order Multiagent Systems: A Neurodynamic Approach With Generalized Compensation Term 二阶多智能体系统的交会优化：一种具有广义补偿项的神经动力学方法

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-12 DOI: 10.1109/TSMC.2026.3658424

Zhanshan Wang;Yiyang Ge;Xiaolu Ye

{"title":"Rendezvous Optimization for Second-Order Multiagent Systems: A Neurodynamic Approach With Generalized Compensation Term","authors":"Zhanshan Wang;Yiyang Ge;Xiaolu Ye","doi":"10.1109/TSMC.2026.3658424","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3658424","url":null,"abstract":"This article investigates the rendezvous optimization problem for second-order multiagent systems. This task is typically framed as a convex optimization with equality constraints, which must also adhere to the system dynamics. Traditional neurodynamic approaches may lead to strong oscillations or instability due to uncoordinated intrinsic system dynamics. Inspired by proportional-derivative control and accelerated optimization techniques, a neurodynamic approach with a generalized compensation term (NGCT) is proposed to achieve oscillation suppression. The advantages of the approach include: 1) using state derivatives to provide predictions for oscillation suppression and 2) employing a compensation term based on the equality constraint coefficient matrix <inline-formula> <tex-math>$A$ </tex-math></inline-formula> to enhance constraint matching sensitivity. The transformation properties of <inline-formula> <tex-math>$A$ </tex-math></inline-formula> enable convergence to specified geometries. It is proven that the proposed approach exponentially converges to the optimal solution. Numerical experiments have demonstrated the effectiveness of the proposed approach in different rendezvous optimization problems.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3384-3395"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Uncertainty Predictive Observer-Based Model-Free Adaptive Disturbance Rejection Control 基于不确定性预测观测器的无模型自适应抗干扰控制

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3654943

Yu Hui;Ronghu Chi;Yang Liu;Zhongsheng Hou;Biao Huang

{"title":"Uncertainty Predictive Observer-Based Model-Free Adaptive Disturbance Rejection Control","authors":"Yu Hui;Ronghu Chi;Yang Liu;Zhongsheng Hou;Biao Huang","doi":"10.1109/TSMC.2026.3654943","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3654943","url":null,"abstract":"An uncertainty predictive observer-based model-free adaptive disturbance rejection control (UPO-MFADRC) is developed for nonaffine nonlinear systems with uncertain nonlinearities and exogenous disturbances. A linear predictive data model (LPDM) consisting of a linear parametric part and a total residual uncertainty is derived from the original nonaffine nonlinear system. Then, an adaptive law with a prediction algorithm is proposed to address the unknown parameter sequence of the LPDM. An uncertainty predictive observer (UPO) is developed to predict the future behavior of the total residual uncertainty sequence of the LPDM including the unmodeled dynamics and exogenous disturbances. The UPO involves an extended state observer for the uncertainty estimation at the current time instant and a hierarchical prediction algorithm to predict the uncertainty at more than one future time instant. Finally, an entire UPO-MFADRC is constructed by incorporating the adaptive law, UPO, and a control law generated from the moving-window optimization of a designed performance index function. The proposed UPO-MFADRC is almost model-independent except that the control direction needs to be known. The convergence is shown mathematically with the use of contraction mapping-based method. Simulation verifies the ability of the proposed UPO-MFADRC in tolerating the uncertainty.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3128-3139"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IEEE Transactions on Systems, Man, and Cybernetics: Systems Publication Information IEEE系统、人与控制论汇刊：系统出版信息

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-04-16 DOI: 10.1109/TSMC.2026.3679004

引用次数: 0

Hybrid Iteration-Based Reinforcement Learning Scheme for Markov Jump Multiarea Interconnected Power Systems 基于混合迭代的马尔可夫跳多区域互联电力系统强化学习方案

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-01-28 DOI: 10.1109/TSMC.2026.3655579

Hao Shen;Jinxu Liu;Qing Yang;Ju H. Park;Jing Wang

{"title":"Hybrid Iteration-Based Reinforcement Learning Scheme for Markov Jump Multiarea Interconnected Power Systems","authors":"Hao Shen;Jinxu Liu;Qing Yang;Ju H. Park;Jing Wang","doi":"10.1109/TSMC.2026.3655579","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3655579","url":null,"abstract":"This article presents a novel reinforcement learning (RL)-based load frequency control (LFC) algorithm designed for Markov jump multiarea interconnected power systems (MJMIPSs). Existing LFC methods often require precise dynamic information of the power system, which is challenging to acquire accurately due to the the system complexity, stochastic disturbances, and high modeling costs. Such limitations make it difficult to implement effective control strategies in real-world applications. In response to these challenges, we propose a decentralized hybrid iteration (HI) algorithm that combines the RL scheme with a decentralized control technique to address the LFC problem for MJMIPSs. In contrast to conventional RL schemes, such as policy iteration (PI) and value iteration (VI), the proposed algorithm achieves the controller design without subsystem decomposition (SD) by employing mixed-mode data acquisition and mode-related data classification, while eliminating the requirements on exact system dynamics and initial admissible control policies. Finally, we verify the effectiveness of the proposed method through the power systems.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3198-3209"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Extraction of Subdialogs for Dialog Emotion Recognition 面向对话情感识别的子对话动态提取

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3655378

Zhenyu Yang;Zhibo Zhang;Yuhu Cheng;Tong Zhang;Xuesong Wang

{"title":"Dynamic Extraction of Subdialogs for Dialog Emotion Recognition","authors":"Zhenyu Yang;Zhibo Zhang;Yuhu Cheng;Tong Zhang;Xuesong Wang","doi":"10.1109/TSMC.2026.3655378","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3655378","url":null,"abstract":"The goal of emotion recognition in conversation (ERC) is to identify the emotion expressed in each utterance in a conversation. However, some previous approaches have not sufficiently considered the effect of information about the relative positions of each speaker’s utterance and the target utterance in a conversation on emotion analysis and have ignored the differences in the emotions expressed in the target utterance under different subthemes. We introduce a dynamic extraction of subdialogs (DESDs) approach to emotion recognition to address these issues. The method extracts subdialogs using information about the relative positions of each speaker’s utterance and the target utterance. The emotional dynamics in the dialog are then captured more accurately by considering each speaker’s contribution to the emotional expression. Additionally, we extract the subdialog topic information to capture the impact of different subthemes on the emotion of the target utterance. Through experiments conducted on four different datasets, we validate the effectiveness of the network. Our code is available at <uri>https://anonymous.4open.science/r/DESD-1FDF</uri>","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"2996-3007"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0