检索结果-内蒙古大学图书馆

Federated Learning With Meta-Layers Training for Privacy-Preserving in Vehicular Consumer Electronics

IEEE Transactions on Consumer Electronics 2024年

作者： Shen, Xiaoyang Li, Haibin Li, Yaqian Zhang, Wenming Alenazi, Mohammed J.F. Agarwal, Kadambri Yanshan University College of Electrical Engineering Hebei Qinhuangdao066000 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066000 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia ABES Engineering College Department of Computer Science and Engineering Ghaziabad201009 India

Vehicular consumer electronics, such as autonomous vehicles (AVs), need collecting large amounts of private user information, which face the risk of privacy leakage. To protect the privacy of consumers, researchers have proposed to apply federated learning (FL) to privacy-preserving vehicular consumer electronics, that is, leveraging FL for collaborative training of a decision model without exchanging the sensitive information generated by AVs. However, FL generally needs to exchange the gradients of client models periodically with the central server, which can be attacked by adversaries to infer user information. Thereby, it may still face the risk of privacy leakage. To solve that challenge, we put forward a novel FL framework, called FL with Meta-Layers Training (FL-MLT). Instead of exchanging the gradients of the client models, it exchanges, meta-layers with the central servers. Since meta-layers are only a slice of the client models, exchanging them helps protect privacy. On the other hand, they contain meta-knowledge to help the FL training process. In the experiments, we conduct extensive visual classification simulation to evaluate FL-MLT, and the experimental results demonstrate the superior performance of FL-MLT. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Two-Player Multiagent Graphical Games with Reinforcement Learning*

Two-Player Multiagent Graphical Games with Reinforcement Lea...

引用

industrial Cyber-Physical Systems (ICPS)

作者： Bosen Lian Jiacheng Wu Electrical and Computer Engineering Department Auburn University Auburn AL USA State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350363012

ISBN: (纸本)9798350363029

This paper studies the synchronization problem of two-player multiagent systems through reinforcement learning methods. A Nash-minmax strategy is formulated, where the interactions of two players in the same agent are non-zero-sum, while interactions of players between agents are zero-sum games. We propose an offline model-based reinforcement learning algorithm to identify Nash solutions for players within each agent, as well as the worst control solutions for players in neighboring antagonistic agents. On this basis, a data-driven off-policy algorithm is provided to alleviate the requirement for accurate system dynamics in the offline algorithm. Besides, the convergence of the proposed algorithms is analyzed. Finally, simulation results verify the effectiveness of the designed algorithms.

关键词： System dynamics Heuristic algorithms Simulation Games Reinforcement learning Cyber-physical systems Synchronization

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Competition and Cooperation Mechanism Between Agency Selling and Wholesale: An Application of the Emerging E-commerce Model

Competition and Cooperation Mechanism Between Agency Selling...

引用

2023 IEEE International Conference on industrial engineering and engineering Management, IEEM 2023

作者： Wang, Haonan Lee, C.K.M. Ji, Ping Li, Gang The Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong Science Park New Territories Hong Kong Xi'an Jiaotong - Liverpool University China School of Management Xi'an Jiaotong University The State Key Lab for Manufacturing Systems Engineering The Key Lab of the Ministry of Education for Process Control and Efficiency Engineering Xi'an China

ISBN: (纸本)9798350323153

Recently, the platform economy allows enterprises to collaborate with business partners and provide additional channels for various parties. E-commerce platforms have become integral channels for connecting suppliers with consumers. In the platform economy, agency selling and reselling are two predominant sales models that often coexist for the same product types, resulting in a competitive relationship. This study analyzes transaction data for 30,000 Stock Keeping Units (SKUs) provided by the Chinese e-commerce platforms over one month. We employ three models to compare the sales quantity and profits of manufacturers and online platforms and to identify the most efficient mode for stakeholders based on the model establishment and empirical evidence. Our findings suggest that apart from the existing channel to provide products to customers, manufacturers enter the platform which will increase the profit of platform operators. On the other hand, platform operators may also affect the profit of the manufacturers. © 2023 IEEE.

关键词： Channel structure Data-analysis Online platform

来源：评论

学校读者我要写书评

暂无评论

3D printed-electrospun PCL/hydroxyapatite/MWCNTs scaffolds for the repair of subchondral bone

引用

Regenerative Biomaterials 2023年第1期10卷 294-305页

作者： Yanyan Cao Lei Sun Zixian Liu Zhizhong Shen Wendan Jia Peiyi Hou Shengbo Sang College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030031China

Osteochondral defect caused by trauma or osteoarthritis exhibits a major challenge in clinical treatment with limited symptomatic effects at *** regeneration and remodeling of subchondral bone play a positive effect on cartilage regeneration and further promotes the repair of osteochondral *** use of the strengths of each preparation method,the combination of 3D printing and electrospinning is a promising method for designing and constructing multi-scale scaffolds that mimic the complexity and hierarchical structure of subchondral bone at the microscale and nanoscale,*** this study,the 3D printed-electrospun poly(ɛ-caprolactone)/nano-hydroxyapatites/multi-walled carbon nanotubes(PCL/nHA/MWCNTs)scaffolds were successfully constructed by the combination of electrospinning and layer-by-layer 3D *** resulting dual-scale scaffold consisted of a dense layer of disordered nanospun fibers and a porous microscale 3D scaffold layer to support and promote the ingrowth of subchondral ***,the biomimetic PCL/nHA/MWCNTs scaffolds enhanced cell seeding efficiency and allowed for higher cell-cell interactions that supported the adhesion,proliferation,activity,morphology and subsequently improved the osteogenic differentiation of bone marrow mesenchymal stem cells in ***,this study elucidates that the construction of 3D printed-electrospun PCL/nHA/MWCNTs scaffolds provides an alternative strategy for the regeneration of subchondral bone and lays a foundation for subsequent in vivo studies.

关键词： additive manufacturing 3D printing electrospinning subchondral bone

来源：评论

学校读者我要写书评

暂无评论

SIMSE: a contrastive learning method combining sample importance metric and semantic enhancement

引用

Expert Systems with Applications 2025年 286卷

作者： Gao, Yangyang Zheng, Zhi Huang, Wenjun Lin, Xiaomin College of Computer and Cyber Security Fujian Normal University Fuzhou350117 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China

In complex application scenarios, the lack of accurate labels for training samples has positioned contrastive learning a key focus in self-supervised learning. This approach effectively extracts meaningful representations from unlabeled data. A significant challenge lies in identifying high-value samples and exploring their semantic features to improve performance. Most existing self-supervised learning methods do not focus much on mining or augmenting valuable samples, relying mainly on contrastive learning between original samples. As a result, performance suffers in cases with limited or sparse data. To address this, we propose a contrastive learning method that combines sample importance measurement and semantic enhancement, overcoming the limitations of traditional methods that only use original samples. First, we generate additional valuable samples using interpolation and apply a similarity-based strategy to better distinguish positive and negative samples, refining the sample partitioning process. Second, we design a semantic enhancement mechanism to better capture and strengthen shared high-level semantic features between samples. Third, we introduce a new metric to evaluate sample value by measuring oscillations in the learning model caused by gradients, determining the importance of each sample. We also use confidence learning to identify and correct mislabeled samples. Extensive evaluations conduct on multiple benchmark datasets demonstrate that our method improves linear classification accuracy by 2.23 %, 4.3 %, 1.6 %, 3.73 %, and 4.69 % on ImageNet-100, ImageNet-10, CIFAR-10, CIFAR-100, and STL-10, respectively. Additionally, accelerates convergence speed by 1.5x and effectively detects mislabeled samples. © 2025 Elsevier Ltd

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

DexRepNet: Learning Dexterous Robotic Grasping Network with Geometric and Spatial Hand-Object Representations

DexRepNet: Learning Dexterous Robotic Grasping Network with ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Qingtao Liu Yu Cui Qi Ye Zhengnan Sun Haoming Li Gaofeng Li Lin Shao Jiming Chen College of Control Science and Engineering Zhejiang University Hangzhou China Key Lab of CS&AUS Zhejiang Province College of Control Science and Engineering and the State Key Laboratory of Industrial Control Technology Zhejiang University Department of Computer Science National University of Singapore Singapore

Robotic dexterous grasping is a challenging problem due to the high degree of freedom (DoF) and complex contacts of multi-fingered robotic hands. Existing deep re-inforcement learning (DRL) based methods leverage human demonstrations to reduce sample complexity due to the high dimensional action space with dexterous grasping. However, less attention has been paid to hand-object interaction representations for high-level generalization. In this paper, we propose a novel geometric and spatial hand-object interaction representation, named DexRep, to capture object surface features and the spatial relations between hands and objects during grasping. DexRep comprises Occupancy Feature for rough shapes within sensing range by moving hands, Surface Feature for changing hand-object surface distances, and LocalGeo Feature for local geometric surface features most related to potential contacts. Based on the new representation, we propose a dexterous deep reinforcement learning method DexRepNet to learn a generalizable grasping policy. Experimental results show that our method outperforms baselines using existing representations for robotic grasping dramatically both in grasp success rate and convergence speed. It achieves a 93% grasping success rate on seen objects and higher than 80% grasping success rates on diverse objects of unseen categories in both simulation and real-world experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Bilevel Optimization via Adaptive Penalization with Time-Scale Separation

arXiv

引用

arXiv 2024年

作者： Niu, Youcheng Xu, Jinming Sun, Ying Chai, Li Chen, Jiming State Key Laboratory of Industrial Control Technology The College of Control Science and Engineering Zhejiang University Hangzhou310027 China School of Electrical Engineering and Computer Science Pennsylvania State University PA16802 United States

This paper studies a class of distributed bilevel optimization (DBO) problems with a coupled inner-level subproblem. Existing approaches typically rely on hypergradient estimations involving computationally expensive Hessian information. To address this, we propose an equivalent constrained reformulation by treating the inner-level subproblem as an inequality constraint, and introduce an adaptive penalty function to properly penalize both inequality and consensus constraints based on subproblem properties. Moreover, we propose a loopless distributed algorithm, AHEAD, that employs multiple-timescale updates to solve each subproblem asymptotically without requiring Hessian information. Theoretically, we establish convergence κ4 rates of O((1−ρ)2K1/3 ) for nonconvex-strongly-convex cases and κ2 O((1−ρ)2K2/3 ) for distributed min-max problems. Our analysis shows the clear dependence of convergence performance on bilevel heterogeneity, the adaptive penalty parameter, and network connectivity, with a weaker assumption on heterogeneity requiring only bounded first-order heterogeneity at the optimum. Numerical experiments validate our theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Objective Optimization Algorithm for Classification of Decision Variables Based on Objective Monotonicity

SSRN

引用

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066004 China

Dynamic multi-objective optimization problems (DMOPs) are prevalent in daily life, and the aim of dealing with DMOPs is to track the moving Pareto Front(PF) and find a series of Pareto Sets (PS) at different moments. Strategies based on decision variable classification improve the performance of multi-objective evolutionary algorithms. However, it has been a challenge to ensure fast and accurate classification. In this study, a decision variable classification method based on objective monotonicity(CDMO) is proposed to reduce the negative effects of inaccurate classification. In addition, a multi-step convergence prediction method and a diversity maintenance strategy are proposed to improve the algorithm performance. The effectiveness of the CDMO algorithm is verified by comparing it with three state-of-the-art DMOEAs on 16 benchmark test problems. The experimental results show that the CDMO algorithm is able to obtain high-quality populations with good convergence and distributivity in a dynamic environment. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

EAVFormer: an end-to-end audio and visual emotion recognition network based on transformers

引用

Multimedia Systems 2025年第3期31卷 1-22页

作者： Liu, Haoran Sun, Zijian Li, Haibin Li, Yaqian Zhang, Wenming Song, Tao School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province Yanshan University Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China Shenzhen Research Institute of Yanshan University Shenzhen518057 China Key Lab of Measurement Technology & Instrumentation of Hebei Province School of Electrical Engineering Yanshan University Qinhuangdao066004 China

Audio-visual emotion recognition, integrating information from various sources, enhances the comprehensive understanding and analysis of human emotions. However, existing methods in this field primarily focus on feature fusion, often overlooking the equally crucial stage of feature extraction. Typically, these methods employ pre-trained models to extract features during the initial phase, complicating modality-specific feature extraction and increasing system complexity and coordination challenges, which hinder effective audio-visual feature fusion. To address these issues, we propose an end-to-end audio-visual emotion recognition model, EAVFormer. For the audio modality, we input raw audio signals along with a mix of mel spectrograms and Mel Frequency Cepstral Coefficients (MFCCs), employing a hierarchical transformer technique that facilitates both shallow local and deep global feature extraction to fully harness complementary acoustic information, significantly enhancing the acoustic modality’s contribution. For the visual modality, we input raw video frames and employ a hierarchical transformer feature extraction method that integrates three-dimensional convolution and spatio-temporal self-attention mechanisms to address spatial and temporal redundancies and dependencies, thereby enhancing the expression of dynamic visual information. In the modal fusion stage, we construct dual-modality representations and encode inter-modal information while preserving modality-specific and meaningful intra-modal features. Testing on three popular datasets RAVDESS, CREMA-D, and CMU-MOSEI demonstrates that EAVFormer surpasses existing state-of-the-art methods in audio-visual emotion recognition accuracy, achieving rates of 95.17%, 86.13%, and 78.22%, respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：