检索结果-内蒙古大学图书馆

data-driven Near Optimization for Fast Sampling Singularly Perturbed systems

ieee TRANSACTIONS ON AUTOMATIC control 2024年第7期69卷 4689-4694页

作者： Shen, Hao Peng, Chuanjun Yan, Huaicheng Xu, Shengyuan Anhui Univ Technol Anhui Prov Key Lab Power Elect & Mot Control Maanshan 243002 Peoples R China Anhui Univ Technol Sch Elect & Informat Engn Maanshan 243002 Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China

The optimal control issue of fast sampling singularly perturbed systems is discussed throughout this article. As a new attempt, without using complete system dynamics, the composite controller is designed by using controller of the different subsystems along with the usage of the subsystem decomposition technique by means of singular perturbation theory. Compared with the existing policy iteration and value iteration algorithms, there is no enforced requirement for a stabilizing control strategy and the increase in convergence speed is achieved by the proposed hybrid iteration algorithm. For the purpose of considering that the fast and slow subsystems have different characteristics, two hybrid iteration algorithms that can be applied in different situations are developed. Meanwhile, the difference between the given composite controller and the optimal controller is analyzed in detail. Finally, the validity of the proposed controller design method is demonstrated by an example.

关键词： Heuristic algorithms Optimal control Design methodology Approximation algorithms Perturbation methods Performance analysis Optimization Fast sampling singularly perturbed systems hybrid iteration learning optimal control subsystem decomposition

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving data Sharing in IoV: A Federated learning and Blockchain-Based Approach 59

Privacy-Preserving Data Sharing in IoV: A Federated Learning...

引用

59th Annual ieee International conference on Communications (ieee ICC)

作者： Xia, Zhuoqun Sun, Jiahao Tan, Jingjing Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China

ISBN: (纸本)9798350304060;9798350304053

With the development of in-vehicle sensors and communication infrastructures, vehicles facilitate intelligent transportation systems (ITS) and traffic flow management by enabling information exchange between vehicles and between vehicles and infrastructures through data sharing in Internet of Vehicles (IoV). Meanwhile, these data sharing schemes also pose security and privacy protection issues for the sharers. Traditional data encryption and access control algorithms are difficult to address data integrity issues and centralized characteristics. Additionally, those encryption and decryption algorithms require large amounts of computational and storage resources. To address these issues, we propose a privacy-preserving data sharing scheme based on blockchain and federated learning, where blockchain technology is used for authentication and data sharing, and asynchronous federated learning allows participants to train local models on local devices to reduce the risk of privacy leakage. Moreover, we screen out unrelated vehicles by calculating the similarity of vehicle trajectories to select participants. Experimental data and analysis validate the effectiveness and scalability of the proposed scheme.

关键词： data sharing federated learning blockchain internet of vehicles

来源：评论

学校读者我要写书评

暂无评论

Enabling Privacy-Preserving Edge AI: Federated learning Enhanced with Forward-Forward Algorithm

Enabling Privacy-Preserving Edge AI: Federated Learning Enha...

引用

ieee International conference on Omni-Layer Intelligent systems (ieee COINS)

作者： Ghader, Mohammadnavid Kheradpisheh, Saeed Reza Farahani, Bahar Fazlali, Mahmood Shahid Beheshti Univ Dept Comp Sci Tehran Iran Shahid Beheshti Univ Cyberspace Res Inst Tehran Iran Univ Hertfordshire Cybersecur & Comp Syst Res Grp Hatfield Herts England

ISBN: (纸本)9798350349603;9798350349597

Artificial Intelligence (AI) has emerged as a pivotal technology across various sectors, including healthcare, transportation, and the development of smart cities, revolutionizing service delivery and operational efficiency. However, the adoption and introduction of new data-driven services leveraging centralized training models have been hindered by significant concerns over privacy and data security, as these traditional techniques potentially expose sensitive information to breaches. Federated learning (FL) presents a compelling solution to this dilemma, enabling decentralized data processing without compromising privacy. Integrating Edge AI into this framework, FL enables the collaborative training of models based on data distributed across different clients. Nevertheless, implementing FL on edge devices introduces a set of challenges due to the limited computational and memory resources available on such tiny devices. Specifically, the backpropagation (BP) phase of training models is notably resource-intensive, posing a barrier to efficient deployment. To address this, we replaced the backpropagation phase with a Forward-Forward (FF) algorithm. Moreover, we integrated and compared several loss functions, namely Hinton, Symba, and Swish, to assess their compatibility and efficiency in the context of forward-forward training within the federated learning framework. The study indicates that our novel method leads to a slight decrease in accuracy for large and complex datasets compared to the traditional BP technique. However, it has the potential to enhance runtime and reduce memory overhead. The proposed technique represents a promising path toward the broader adoption of Edge AI by effectively addressing critical technical challenges, namely privacy concerns and on-chip model training.

关键词： Federated learning Forward-Forward Algorithm Edge AI Privacy-Preserving ML

来源：评论

学校读者我要写书评

暂无评论

Diff-control: A Stateful Diffusion-based Policy for Imitation learning

Diff-Control: A Stateful Diffusion-based Policy for Imitatio...

引用

2024 International conference on Intelligent Robots and systems

作者： Liu, Xiao Zhou, Yifan Weigend, Fabian Sonawani, Shubham Ikemoto, Shuhei Ben Amor, Heni Arizona State Univ Sch Comp & Augmented Intelligence Tempe AZ 85281 USA Kyushu Inst Technol Grad Sch Life Sci & Syst Engn Dept Human Intelligence Syst Kitakyushu Fukuoka Japan

ISBN: (纸本)9798350377712;9798350377705

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent action during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-control policy, which utilizes a diffusion-based model to learn action representation from a state-space modeling viewpoint. We demonstrate that diffusion-based policies can acquire statefulness through a Bayesian formulation facilitated by controlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-control shows improved performance across various tasks. Specifically, Diff-control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Notably, Diff-control also shows consistent performance in the presence of perturbations, outperforming other state-of-the-art methods that falter under similar conditions. Project page: https://***/

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient Federated learning for Earth Observation in LEO Satellite systems 25

Energy-efficient Federated Learning for Earth Observation in...

引用

ieee Wireless Communications and Networking conference (ieee WCNC)

作者： Xiong, Ting Xu, Xiaofan Du, Ping Zhang, Yueyue Zhang, Ran Liu, Jiang Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China Shanghai Satellite Network Res Inst Co Ltd Shanghai Peoples R China Purple Mt Labs Nanjing Peoples R China

ISBN: (纸本)9798350303582;9798350303599

Low Earth Orbit (LEO) satellites enable various Internet of Things (IoT) applications by providing plentiful observation data at different spatial scales. However, transmitting such a large volume of observation data to the ground for model training is challenging due to the intermittent connection between satellites and ground stations, leading to long training delays for task-oriented artificial intelligence models. Orbital federated learning has been investigated to enable on-board model training sharing model parameters instead of observation data, thus greatly reducing the communication overhead. However, these works underutilize the availability of inter-satellite links and ignore energy consumption. To fill this gap, we propose an energy-efficient federated learning scheme for earth observation applications in LEO satellite systems to minimize learning loss and energy consumption. Specifically, to reduce the effect of data heterogeneity on learning accuracy, we propose a satellite grouping scheme based on satellites' data distribution and communication delay to ground stations. Then, we optimize each satellite's transmission power and computing frequency under the constraint of training time. Experimental results based on popular datasets show the efficacy of the proposed scheme compared to benchmark methods.

关键词： Earth observation federated learning energy consumption LEO satellite systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning for SLP-based ISAC Waveform Design 59

Deep Learning for SLP-based ISAC Waveform Design

引用

59th Annual ieee International conference on Communications (ieee ICC)

作者： Jiang, Peng Liu, Rang Li, Ming Xiao, Zichao Liu, Qian Dalian Univ Technol Dalian 116024 Liaoning Peoples R China Univ Calif Irvine Ctr Pervas Commun & Comp Irvine CA USA

ISBN: (纸本)9781728190549

Integrated sensing and communication (ISAC) is a key enabling technology for future 6G communication systems. Recently emerged symbol-level precoding (SLP) is considered to possess substantial potential for ISAC waveform design, owing to its ability to enhance multi-user communication and radar sensing performances by simultaneously leveraging both temporal and spatial design degrees of freedom (DoFs). Considering the high complexity challenges brought by existing model-driven optimization based SLP design approaches, in this paper we propose a lightweight SLP-Inception-Net and efficient data-driven deep learning algorithm to solve the highly complex SLP design problem. In particular, we propose a phase-based activation function method to guarantee the equality constraints and use the soft loss to ensure the inequality constraints. Simulation results verify that our proposed deep learning algorithm achieves comparable communication and radar sensing performance to the prior optimization-based approaches, while providing a noteworthy 1000-fold reduction in computational complexity in terms of average execution time.

关键词： Deep learning ISAC SLP waveform design

来源：评论

学校读者我要写书评

暂无评论

Event-Based data-driven Consensus control for Multiagent systems with Unknown Dynamics 6

Event-Based Data-Driven Consensus Control for Multiagent Sys...

引用

6th International conference on Electronic Engineering and Informatics, EEI 2024

作者： Zhang, Peiyang Dong, Tao College of Electronics and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9798350353594

This paper addresses the problem of achieving tracking consensus control for multi-agent systems (MASs) with unknown dynamics. First, an augmented neighborhood error system model is designed, and the optimal consensus protocol of MASs is converted to the optimal regulation for augmented system with a performance function. A control policy based on event-triggered is proposed to address the optimal regulation of the augmented system. Then, a data-driven control approach is proposed to implement the event-triggered policy, including a critic network and an actor. The actor is utilized to generate control inputs and the critic network estimates the performance value. Through the selection of suitable event-triggered thresholds and learning rates, the local neighborhood error is proved to be uniformly ultimately bounded, effectively preventing the occurrence of Zeno behaviors. Finally, two simulation examples are presented and analyzed to validate the efficacy of the proposed control model. © 2024 ieee.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Review On data driven control Techniques Within Industrial Heating Furnaces 33

A Review On Data Driven Control Techniques Within Industrial...

引用

33rd Southern African Universities Power Engineering conference, SAUPEC 2025

作者： Donkor, David N. Ogudo, Kingsley A. Rameshar, Vikash University of Johannesburg Department of Electrical Engineering Technology South Africa

ISBN: (纸本)9798331535162

This study presents a comprehensive review of recent advancements in data-driven control techniques applied to industrial heating furnaces. The investigation focuses on three prominent approaches: fuzzy-PID controllers, neural network controllers utilizing model reference control, and Genetic Algorithm (GA) techniques for PID parameter optimization. These data-driven methodologies demonstrated good performance metrics compared to conventional control strategies based on their results. This paper contributes to the field by synthesizing current knowledge, identifying research gaps, and proposing future directions that could lead to more efficient, robust, and widely applicable control solutions for diverse heating furnace systems in the heating industry. © 2025 ieee.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

data-driven Modelling of Aeroengine systems Based on Variational Bayes and Adaptive Kalman Filter 39

Data-Driven Modelling of Aeroengine systems Based on Variati...

引用

39th Youth Academic Annual conference of Chinese-Association-of-Automation (YAC)

作者： Qian, Yu Liu, Xinpeng Tang, Wentao Dalian Univ Technol Sch Control Sci & Engn Dalian Peoples R China

ISBN: (纸本)9798350390780;9798350379228

This paper mainly develops a data-driven modeling approach for aeroengine systems. To describe how the system behaves dynamically, a state variable model is constructed, and it is further transformed such that the unknown parameters are treated as hidden states. As a result, the model parameters with their uncertainties, and the noise statistics can be jointly estimated by integrating an adaptive Kalman filter into the variational Bayesian (VB) framework. The efficacy of the proposed data-driven model is verified through comparison study with the component-level JT9D aeroengine model provided by NASA.

关键词： System identification variational Bayesian aeroengine systems measurement noise

来源：评论

学校读者我要写书评

暂无评论

Efficiency-driven Adaptive Task Planning for Household Robot Based on Hierarchical Item-Environment Cognition

引用

ieee TRANSACTIONS ON CYBERNETICS 2025年第4期55卷 1772-1788页

作者： Zhang, Mengyang Tian, Guohui Cui, Yongcheng Liu, Hong Lyu, Lei Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China

Task planning focused on household robots represents a conventional yet complex research domain, necessitating the development of task plans that enable robots to execute unfamiliar household services. This area has garnered significant research interest due to its extensive applications in robotics, particularly concerning household robots. Nevertheless, the majority of task planning methodologies exhibit suboptimal performance regarding the success and efficiency of completing household tasks, primarily due to a lack of cognitive capacity of household items and home environments. To address these challenges, we propose an efficiency-driven adaptive task planning approach based on hierarchical item-environment cognition. Initially, we establish a multiple semantic attribute-based priori knowledge (MSAPK) framework to facilitate the attributive representation of household items. Utilizing MSAPK, we develop a long short-term memory (LSTM) based item cognition model that assigns relevant attributes and substitutes to specified household items, thereby enhancing the cognitive capabilities of household robots at the attribute level. Subsequently, we construct an environment cognition model that delineates the relationships between household items and room types, enabling household robots to locate target items more efficiently. Through hierarchical item-environment cognition, we introduce a strategy for adaptive task planning, empowering household robots to execute household tasks with both flexibility and efficiency. The generated plans are evaluated in both virtual and real-world experiments, with promising results affirming the effectiveness of our proposed methodology.

关键词： Robots Planning Cognition Semantics Adaptation models Long short term memory Knowledge based systems Complexity theory Training Robustness Adaptive task planning environment cognition household robot item cognition

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：