Pub Date : 2025-11-11DOI: 10.1109/TSMC.2025.3628968
Shuo-Qiu Zhang;Wei-Wei Che;Zheng-Guang Wu
For unknown continuous-time heterogeneous linear multiagent systems (MASs) under mixed denial-of-service (DoS) attacks, a novel reinforcement learning (RL) algorithm named hybrid iterative (HI) is proposed in this article to solve the secure output tracking problem based on a prescribed-time observer. Considering the scenario that MASs are subjected to mixed DoS attacks that can cause the connectivity maintained or broken of the network communication topology, a distributed resilient prescribed-time observer is designed to accurately estimate the leader’s state and output within a prescribed time. Then, the secure output tracking problem of heterogeneous MASs is converted into the optimal linear quadratic tracking (LQT) problem by introducing a discounted performance function, and inhomogeneous algebraic Riccati equations (AREs) are further derived to solve it. Meanwhile, an HI-based data-driven RL algorithm independent of the initial admissible control policy and the system dynamics knowledge is proposed to learn the optimal solution of inhomogeneous AREs. Compared with the traditional RL algorithms, that is, policy iteration (PI) and value iteration (VI), HI can not only remove the restrictions of the initial admissible policy in PI but also converge to the optimal solution faster than the VI. Finally, comparative simulation verifies the effectiveness of the theoretical results.
{"title":"Prescribed-Time Observer-Based HI-RL Secure Output Tracking Control for Heterogeneous MASs Under DoS Attacks","authors":"Shuo-Qiu Zhang;Wei-Wei Che;Zheng-Guang Wu","doi":"10.1109/TSMC.2025.3628968","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3628968","url":null,"abstract":"For unknown continuous-time heterogeneous linear multiagent systems (MASs) under mixed denial-of-service (DoS) attacks, a novel reinforcement learning (RL) algorithm named hybrid iterative (HI) is proposed in this article to solve the secure output tracking problem based on a prescribed-time observer. Considering the scenario that MASs are subjected to mixed DoS attacks that can cause the connectivity maintained or broken of the network communication topology, a distributed resilient prescribed-time observer is designed to accurately estimate the leader’s state and output within a prescribed time. Then, the secure output tracking problem of heterogeneous MASs is converted into the optimal linear quadratic tracking (LQT) problem by introducing a discounted performance function, and inhomogeneous algebraic Riccati equations (AREs) are further derived to solve it. Meanwhile, an HI-based data-driven RL algorithm independent of the initial admissible control policy and the system dynamics knowledge is proposed to learn the optimal solution of inhomogeneous AREs. Compared with the traditional RL algorithms, that is, policy iteration (PI) and value iteration (VI), HI can not only remove the restrictions of the initial admissible policy in PI but also converge to the optimal solution faster than the VI. Finally, comparative simulation verifies the effectiveness of the theoretical results.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"709-723"},"PeriodicalIF":8.7,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778260","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}
Pub Date : 2025-11-03DOI: 10.1109/TSMC.2025.3624888
Yao Huang;Yinan Guo;Hong Wei;Jianbin Xin;Shengxiang Yang
Flexible job shop co-scheduling problems (FJSCSPs) normally adopt single-load automated guided vehicles (AGVs) for transportation, possibly causing the waste of load capacity. To enhance the transportation efficiency, a multiload AGVs (MAGVs) that carry more than one job simultaneously within its load capacity come into use in flexible manufacturing systems (FMSs). In this scenario, transit throughput can achieve the obvious improvement without increasing the vehicle fleet size, having become more prevalent gradually. However, co-scheduling machines and MAGVs is seldom investigated, which is crucial for maximizing production efficiency due to the inherent interdependence between transporting and processing. Considering constraints on load capacity, task assignment, and transportation sequence, this co-scheduling problem is formulated by minimizing the makespan as an optimization objective. Subsequently, a collaboration–competition estimation of distribution algorithm (CCEDA) is put forward to solve the difficulties caused by the flexible sequence for pickup and delivery tasks of MAGVs. In particular, two problem-related heuristic rules for selecting AGVs and machines are designed, and then a hybrid initialization strategy is developed to produce high-quality initial individuals. To comprehensively describe the landscape of the problem, multiple probability models are established by learning the elite solutions, and then a collaboration–competition mechanism adaptively samples using different models to maintain the high-efficiency exploration. Furthermore, a local search based on variable neighborhood is introduced to enhance the exploitation in promising regions. The experimental results on 30 instances expose that the proposed algorithm outperforms the other state-of-the-art algorithms significantly. Also, the analysis on the impact of AGV load capacity on production confirms that its increase effectively reduces the makespan, thereby demonstrating the practical value of MAGVs.
{"title":"Collaboration–Competition Estimation of Distribution Algorithm for Flexible Job Shop Co-Scheduling With Multiload AGVs","authors":"Yao Huang;Yinan Guo;Hong Wei;Jianbin Xin;Shengxiang Yang","doi":"10.1109/TSMC.2025.3624888","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3624888","url":null,"abstract":"Flexible job shop co-scheduling problems (FJSCSPs) normally adopt single-load automated guided vehicles (AGVs) for transportation, possibly causing the waste of load capacity. To enhance the transportation efficiency, a multiload AGVs (MAGVs) that carry more than one job simultaneously within its load capacity come into use in flexible manufacturing systems (FMSs). In this scenario, transit throughput can achieve the obvious improvement without increasing the vehicle fleet size, having become more prevalent gradually. However, co-scheduling machines and MAGVs is seldom investigated, which is crucial for maximizing production efficiency due to the inherent interdependence between transporting and processing. Considering constraints on load capacity, task assignment, and transportation sequence, this co-scheduling problem is formulated by minimizing the makespan as an optimization objective. Subsequently, a collaboration–competition estimation of distribution algorithm (CCEDA) is put forward to solve the difficulties caused by the flexible sequence for pickup and delivery tasks of MAGVs. In particular, two problem-related heuristic rules for selecting AGVs and machines are designed, and then a hybrid initialization strategy is developed to produce high-quality initial individuals. To comprehensively describe the landscape of the problem, multiple probability models are established by learning the elite solutions, and then a collaboration–competition mechanism adaptively samples using different models to maintain the high-efficiency exploration. Furthermore, a local search based on variable neighborhood is introduced to enhance the exploitation in promising regions. The experimental results on 30 instances expose that the proposed algorithm outperforms the other state-of-the-art algorithms significantly. Also, the analysis on the impact of AGV load capacity on production confirms that its increase effectively reduces the makespan, thereby demonstrating the practical value of MAGVs.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"321-335"},"PeriodicalIF":8.7,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760901","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}
Forecasting the power consumption of the spacecraft is critical for optimizing its lifespan and task allocation. However, the complex electromagnetic environment of outer space introduces unavoidable noise into the collected electrical signals. Moreover, the various subsystems of a multipower spacecraft are affected differently by internal and external noise, making it challenging for the existing methods to effectively capture the features of long-term power consumption sequences. We propose adaptive frequency-pruning-enhanced (AFPE)-iTransformer, a robust time-series forecasting model designed for spacecraft telemetry forecasting under noise and long-range dependency conditions. The model combines three key components: Legendre memory projection for historical compression, adaptive top-$k$ frequency pruning for per-channel denoising, and an improved inverted transformer for cross-subsystem attention. Evaluated on three years of Mars Express (MEX) data, our method consistently outperforms the state-of-the-art baselines in both within-year and cross-year forecasting. It also achieves competitive efficiency, with fast model load time and moderate parameter size. While focused on power forecasting, the model’s modular design supports broader applications in telemetry and industrial forecasting. Model code and configurations are open-sourced for reproducibility.
{"title":"Power Consumption Forecasting of Spacecraft Based on Adaptive Frequency-Domain Pruning-Enhanced Transformer","authors":"Joey Chan;Shiyuan Piao;Huan Wang;Zhen Chen;Ershun Pan;Fugee Tsung","doi":"10.1109/TSMC.2025.3624401","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3624401","url":null,"abstract":"Forecasting the power consumption of the spacecraft is critical for optimizing its lifespan and task allocation. However, the complex electromagnetic environment of outer space introduces unavoidable noise into the collected electrical signals. Moreover, the various subsystems of a multipower spacecraft are affected differently by internal and external noise, making it challenging for the existing methods to effectively capture the features of long-term power consumption sequences. We propose adaptive frequency-pruning-enhanced (AFPE)-iTransformer, a robust time-series forecasting model designed for spacecraft telemetry forecasting under noise and long-range dependency conditions. The model combines three key components: Legendre memory projection for historical compression, adaptive top-<inline-formula> <tex-math>$k$ </tex-math></inline-formula> frequency pruning for per-channel denoising, and an improved inverted transformer for cross-subsystem attention. Evaluated on three years of Mars Express (MEX) data, our method consistently outperforms the state-of-the-art baselines in both within-year and cross-year forecasting. It also achieves competitive efficiency, with fast model load time and moderate parameter size. While focused on power forecasting, the model’s modular design supports broader applications in telemetry and industrial forecasting. Model code and configurations are open-sourced for reproducibility.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"336-349"},"PeriodicalIF":8.7,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760923","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}
In order to improve the environmental adaptation and safety of autonomous vehicles trajectory planning process in a complex driving environment, a novel trajectory planning method which meets the requirement of multidriving tasks and adapts to various driving conditions is proposed in this article. In the trajectory planning method, the optimal control problem considering multiple driving tasks is established based on the constructed performance function and constraint analysis of different driving tasks to ensure the accurate realization of driving tasks. Besides, the neural network empirical model, precollision detection model, and trajectory evaluation model are designed by the consideration of selecting the optimal planning parameters in different driving conditions to enhance the adaptability to traffic environment. The advantage of the proposed method is that it not only meets the requirements of a variety of driving tasks, but also able to select the optimal planning parameters according to different traffic conditions while existing methods usually only meet single planning task, such as lane change, and has the fixed and rigid parameter selection. Four different typical scenarios are given to verify the effectiveness of the proposed method and the results show that the proposed trajectory planning method is able to ensure the safety of the vehicle and adapt to different traffic environments flexibly.
{"title":"An Adaptive Trajectory Planning Method of Autonomous Vehicles Integrating Multiple Tasks","authors":"Haiyan Zhao;Hongbin Xie;Bingzhao Gao;Xinghao Lu;Hong Chen","doi":"10.1109/TSMC.2025.3624625","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3624625","url":null,"abstract":"In order to improve the environmental adaptation and safety of autonomous vehicles trajectory planning process in a complex driving environment, a novel trajectory planning method which meets the requirement of multidriving tasks and adapts to various driving conditions is proposed in this article. In the trajectory planning method, the optimal control problem considering multiple driving tasks is established based on the constructed performance function and constraint analysis of different driving tasks to ensure the accurate realization of driving tasks. Besides, the neural network empirical model, precollision detection model, and trajectory evaluation model are designed by the consideration of selecting the optimal planning parameters in different driving conditions to enhance the adaptability to traffic environment. The advantage of the proposed method is that it not only meets the requirements of a variety of driving tasks, but also able to select the optimal planning parameters according to different traffic conditions while existing methods usually only meet single planning task, such as lane change, and has the fixed and rigid parameter selection. Four different typical scenarios are given to verify the effectiveness of the proposed method and the results show that the proposed trajectory planning method is able to ensure the safety of the vehicle and adapt to different traffic environments flexibly.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"350-361"},"PeriodicalIF":8.7,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760881","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}
Pub Date : 2025-10-30DOI: 10.1109/TSMC.2025.3624473
Shuai Wu;Chunwei Tian;Ruyi Liu;Hang Wei;Yong Xu
An effective method for improving the object detection performance is to decrease the number of false positive (NFP) detection boxes and increase the number of true positive (NTP) detection boxes. In terms of the region-based object detection framework, an appropriate sample weighting strategy can help effectively achieve this goal without causing any inference efficiency loss. However, designing a suitable weighting method is not easy, and a reasonable guiding metric and comprehensive analysis are needed. This article directly sets the NFP and NTP as the evaluation metrics and examines how some preliminary weighting methods affect these two metrics. Based on the results of our analysis, we carefully design a simple yet effective sample weighting method, referred to as the interval normalization weighting strategy (INWS). Unlike some previous works, which only view sample losses as the weighting factor (e.g., focal losses), the INWS applies both the foreground score and the intersection over union (IoU) as the weighting factors. The INWS consists of two components: the IoU interval score normalization strategy (IISNS) for negative samples and the score interval IoU normalization strategy (SIINS) for positive samples. The IISNS can effectively decrease the NFP, and the SIINS is beneficial for increasing the NTP, especially under higher IoU thresholds. Furthermore, the INWS is convenient for application to most of the existing region-based object detection models. The experimental results on the mainstream benchmarks demonstrate that our INWS can achieve consistent improvements on various baselines.
{"title":"An Effective Interval Normalization Weighting Method for Accurate Object Detection","authors":"Shuai Wu;Chunwei Tian;Ruyi Liu;Hang Wei;Yong Xu","doi":"10.1109/TSMC.2025.3624473","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3624473","url":null,"abstract":"An effective method for improving the object detection performance is to decrease the number of false positive (NFP) detection boxes and increase the number of true positive (NTP) detection boxes. In terms of the region-based object detection framework, an appropriate sample weighting strategy can help effectively achieve this goal without causing any inference efficiency loss. However, designing a suitable weighting method is not easy, and a reasonable guiding metric and comprehensive analysis are needed. This article directly sets the NFP and NTP as the evaluation metrics and examines how some preliminary weighting methods affect these two metrics. Based on the results of our analysis, we carefully design a simple yet effective sample weighting method, referred to as the interval normalization weighting strategy (INWS). Unlike some previous works, which only view sample losses as the weighting factor (e.g., focal losses), the INWS applies both the foreground score and the intersection over union (IoU) as the weighting factors. The INWS consists of two components: the IoU interval score normalization strategy (IISNS) for negative samples and the score interval IoU normalization strategy (SIINS) for positive samples. The IISNS can effectively decrease the NFP, and the SIINS is beneficial for increasing the NTP, especially under higher IoU thresholds. Furthermore, the INWS is convenient for application to most of the existing region-based object detection models. The experimental results on the mainstream benchmarks demonstrate that our INWS can achieve consistent improvements on various baselines.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"387-399"},"PeriodicalIF":8.7,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760885","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}
Pub Date : 2025-10-30DOI: 10.1109/TSMC.2025.3623697
Jie Jiang;Ying Dai;Fei Yang;Ruijuan Zhang;Zujun Ma
Given the sparse demands and poor traffic conditions, rural logistics is still challenging in providing efficient yet cost-effective pickup and delivery service. To realize cost reduction and efficiency enhancement, we study a novel cooperative vehicle routing problem with drones (CoVRPDs) to address operational optimization and cost allocation among a coalition with multiple heterogeneous players and investigate how their heterogeneous operating modes (i.e., operating in a truck-drone or truck-only mode) influence cooperation efficiency and cost sharing. This problem is formulated to formally represent highly interactive and complex decisions, including online participation choice, customer assignment among copartners, and collaborative truck-drone routing scheduling involving vehicle matching, intersection scheduling, and transshipment management. To tackle this, we customize an adaptive neighborhood search metaheuristic by introducing a series of customer-level and route-level destroy and repair operators to solve operational optimization efficiently, then apply both the Shapley value and the equal profit method for fair cost allocation. Then, numerical studies demonstrate that the emerging truck-drone delivery mode within a cooperative framework offers substantial economic advantages. From coalition partners, those utilizing a truck-drone delivery can significantly improve the coalition’s efficiency and thereby share smaller coalition costs, encouraging more partners to adopt an efficient truck-drone mode. Further insights on the coalition efficiency and cost allocation are also offered.
{"title":"The Cooperative Vehicle Routing Problem With Drones","authors":"Jie Jiang;Ying Dai;Fei Yang;Ruijuan Zhang;Zujun Ma","doi":"10.1109/TSMC.2025.3623697","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3623697","url":null,"abstract":"Given the sparse demands and poor traffic conditions, rural logistics is still challenging in providing efficient yet cost-effective pickup and delivery service. To realize cost reduction and efficiency enhancement, we study a novel cooperative vehicle routing problem with drones (CoVRPDs) to address operational optimization and cost allocation among a coalition with multiple heterogeneous players and investigate how their heterogeneous operating modes (i.e., operating in a truck-drone or truck-only mode) influence cooperation efficiency and cost sharing. This problem is formulated to formally represent highly interactive and complex decisions, including online participation choice, customer assignment among copartners, and collaborative truck-drone routing scheduling involving vehicle matching, intersection scheduling, and transshipment management. To tackle this, we customize an adaptive neighborhood search metaheuristic by introducing a series of customer-level and route-level destroy and repair operators to solve operational optimization efficiently, then apply both the Shapley value and the equal profit method for fair cost allocation. Then, numerical studies demonstrate that the emerging truck-drone delivery mode within a cooperative framework offers substantial economic advantages. From coalition partners, those utilizing a truck-drone delivery can significantly improve the coalition’s efficiency and thereby share smaller coalition costs, encouraging more partners to adopt an efficient truck-drone mode. Further insights on the coalition efficiency and cost allocation are also offered.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"292-306"},"PeriodicalIF":8.7,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778332","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}
Pub Date : 2025-10-30DOI: 10.1109/TSMC.2025.3623628
Kangmin Jo;Junseok Boo;Dongkyoung Chwa
We propose an image-based visual servoing (IBVS) method to accurately track the trajectory of a target using a single camera mounted on an omnidirectional mobile robot (OMR). Existing IBVS methods for target tracking mainly focused on keeping the target centered in the camera’s field of view, hindering accurate trajectory tracking of the target along curves. To overcome this limitation, the proposed IBVS method for target trajectory tracking introduces a novel approach for generating the desired feature points while considering practical uncertainties caused by slipping, uncertain interaction matrix, and target motion. Specifically, an adaptive integral sliding mode observer (AISMO) is proposed to compensate for uncertainties, eliminating the limitations of previous integral sliding mode observers (ISMOs) that require prior knowledge of the maximum uncertainty values. In addition, using the AISMO estimates, an integral sliding mode control (ISMC) is proposed for robust IBVS of the OMR to guarantee finite-time convergence of the trajectory tracking error to zero. Notably, the proposed IBVS method aids the OMR in accurately tracking the target trajectory using a single camera instead of global external sensors (e.g., global positioning system (GPS) receivers) or applying complex pose estimation techniques. The tracking performance of the proposed method is demonstrated through Lyapunov stability analysis and confirmed with simulation and experimental results.
{"title":"Robust Image-Based Visual Servoing for Accurate Target Trajectory Tracking of Omnidirectional Mobile Robot With a Single Camera","authors":"Kangmin Jo;Junseok Boo;Dongkyoung Chwa","doi":"10.1109/TSMC.2025.3623628","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3623628","url":null,"abstract":"We propose an image-based visual servoing (IBVS) method to accurately track the trajectory of a target using a single camera mounted on an omnidirectional mobile robot (OMR). Existing IBVS methods for target tracking mainly focused on keeping the target centered in the camera’s field of view, hindering accurate trajectory tracking of the target along curves. To overcome this limitation, the proposed IBVS method for target trajectory tracking introduces a novel approach for generating the desired feature points while considering practical uncertainties caused by slipping, uncertain interaction matrix, and target motion. Specifically, an adaptive integral sliding mode observer (AISMO) is proposed to compensate for uncertainties, eliminating the limitations of previous integral sliding mode observers (ISMOs) that require prior knowledge of the maximum uncertainty values. In addition, using the AISMO estimates, an integral sliding mode control (ISMC) is proposed for robust IBVS of the OMR to guarantee finite-time convergence of the trajectory tracking error to zero. Notably, the proposed IBVS method aids the OMR in accurately tracking the target trajectory using a single camera instead of global external sensors (e.g., global positioning system (GPS) receivers) or applying complex pose estimation techniques. The tracking performance of the proposed method is demonstrated through Lyapunov stability analysis and confirmed with simulation and experimental results.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"362-374"},"PeriodicalIF":8.7,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760902","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}
Pub Date : 2025-10-29DOI: 10.1109/TSMC.2025.3624447
Pham Minh Thu Do;Qian Zhang;Guangquan Zhang;Jie Lu
Recommender systems often suffer from data sparsity, particularly when user interactions within a single domain are limited. Cross-domain recommender systems (CDRSs) address this challenge by transferring knowledge across related domains. However, existing approaches face two key limitations: 1) intra-domain noise, where skewed or unreliable interactions degrade representation quality and 2) negative transfer, where misaligned knowledge from the source domain harms target-domain performance. To tackle these issues, we propose GCLD-CDR, a novel cross-domain recommendation framework that integrates graph-based contrastive learning (CL) with diffusion-based knowledge transfer. To enhance intra-domain learning, GCLD-CDR incorporates two complementary augmentation modules: a feature perturbation generator that introduces controlled noise to improve representation diversity, and a denoising generator that prunes unreliable graph edges to refine structural signals. To mitigate negative transfer, we design a diffusion-based transfer mechanism that progressively perturbs source-domain user representations via a Gaussian diffusion process. A neural decoder then reverses this process, selectively recovering task-relevant information while filtering out noise and misaligned signals. Extensive experiments on real-world datasets demonstrate that GCLD-CDR consistently outperforms state-of-the-art baselines, underscoring its potential for advancing practical and trustworthy recommender systems.
{"title":"Graph Contrastive Learning With Diffusion-Based Transfer for Cross-Domain Recommender System","authors":"Pham Minh Thu Do;Qian Zhang;Guangquan Zhang;Jie Lu","doi":"10.1109/TSMC.2025.3624447","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3624447","url":null,"abstract":"Recommender systems often suffer from data sparsity, particularly when user interactions within a single domain are limited. Cross-domain recommender systems (CDRSs) address this challenge by transferring knowledge across related domains. However, existing approaches face two key limitations: 1) intra-domain noise, where skewed or unreliable interactions degrade representation quality and 2) negative transfer, where misaligned knowledge from the source domain harms target-domain performance. To tackle these issues, we propose GCLD-CDR, a novel cross-domain recommendation framework that integrates graph-based contrastive learning (CL) with diffusion-based knowledge transfer. To enhance intra-domain learning, GCLD-CDR incorporates two complementary augmentation modules: a feature perturbation generator that introduces controlled noise to improve representation diversity, and a denoising generator that prunes unreliable graph edges to refine structural signals. To mitigate negative transfer, we design a diffusion-based transfer mechanism that progressively perturbs source-domain user representations via a Gaussian diffusion process. A neural decoder then reverses this process, selectively recovering task-relevant information while filtering out noise and misaligned signals. Extensive experiments on real-world datasets demonstrate that GCLD-CDR consistently outperforms state-of-the-art baselines, underscoring its potential for advancing practical and trustworthy recommender systems.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"375-386"},"PeriodicalIF":8.7,"publicationDate":"2025-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760853","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}
This article presents an adaptive ensemble control for stochastic systems subject to asymmetric noises and outliers. Asymmetric noises skew system observations, and outliers with large amplitude deteriorate the observations even further. Such disturbances induce poor system estimation and degraded stochastic system control. In this work, we model the asymmetric noises and outliers by mixed asymmetric Laplace distributions (ALDs) and propose an optimal control for stochastic systems with mixed ALD noises. Particularly, we segregate the system disturbed by mixed ALD noises into subsystems, each of which is subject to a specific ALD noise. For each subsystem, we design an iterative quantile filter (IQF) to estimate the system parameters using system observations. With the estimated parameters by the IQF, we derive the certainty equivalence (CE) control law for each subsystem. Then we use the Bayesian approach to ensemble the subsystem CE controllers, with each of the controllers weighted by its posterior probability. We finalize our control law as the weighted sum of the control signals by the subsystem CE controllers. To demonstrate our approach, we conduct three numerical simulations and Monte Carlo analyses. The results show improved tracking performance by our approach for skew noises and its robustness to outliers, compared with the RLS-based control policy.
{"title":"Adaptive Ensemble Control for Stochastic Systems With Mixed Asymmetric Laplace Noises","authors":"Yajie Yu;Xuehui Ma;Shiliang Zhang;Zhuzhu Wang;Xubing Shi;Yushuai Li;Tingwen Huang","doi":"10.1109/TSMC.2025.3623515","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3623515","url":null,"abstract":"This article presents an adaptive ensemble control for stochastic systems subject to asymmetric noises and outliers. Asymmetric noises skew system observations, and outliers with large amplitude deteriorate the observations even further. Such disturbances induce poor system estimation and degraded stochastic system control. In this work, we model the asymmetric noises and outliers by mixed asymmetric Laplace distributions (ALDs) and propose an optimal control for stochastic systems with mixed ALD noises. Particularly, we segregate the system disturbed by mixed ALD noises into subsystems, each of which is subject to a specific ALD noise. For each subsystem, we design an iterative quantile filter (IQF) to estimate the system parameters using system observations. With the estimated parameters by the IQF, we derive the certainty equivalence (CE) control law for each subsystem. Then we use the Bayesian approach to ensemble the subsystem CE controllers, with each of the controllers weighted by its posterior probability. We finalize our control law as the weighted sum of the control signals by the subsystem CE controllers. To demonstrate our approach, we conduct three numerical simulations and Monte Carlo analyses. The results show improved tracking performance by our approach for skew noises and its robustness to outliers, compared with the RLS-based control policy.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 1","pages":"307-320"},"PeriodicalIF":8.7,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760918","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}
Pub Date : 2025-10-16DOI: 10.1109/TSMC.2025.3618075
{"title":"IEEE Systems, Man, and Cybernetics Society Information","authors":"","doi":"10.1109/TSMC.2025.3618075","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3618075","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 11","pages":"C3-C3"},"PeriodicalIF":8.7,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11205938","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：