检索结果-内蒙古大学图书馆

Low-cost Data Offloading Strategy with Deep Reinforcement Learning for Smart Healthcare System

IEEE Transactions on Services Computing 2024年

作者： He, Qiang Feng, Zheng Chen, Zhixue Nan, Tianhang Li, Kexin Shen, Huiming Yu, Keping Wang, Xingwei Northeastern University College of Medicine and Biological Information Engineering Shenyang China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries College of Computer Science and Engineering Shenyang China Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan

With the widespread adoption of the Internet of Things (IoT) and various smart medical devices, the volume of medical data has dramatically increased, making the processing of medical Internet of Things (IoMT) data increasingly challenging. Due to the integration of edge computing and cloud computing, IoMT can allocate increased computing and storage resources in proximity to the terminal, addressing the low-latency requirements of computationally intensive tasks. While existing initiatives have shifted services to edge servers, they have not taken into account the joint impact of task priorities and mobile computing services on Mobile Edge Computing (MEC) networks. Fortunately, the rapidly advancing field of Artificial Intelligence (AI) has proven effective in some resource allocation applications in recent years. In this paper, we propose a mobile edge computing-based intelligent healthcare multitasking processing system aimed at addressing the issue of service prioritization in medical scenarios. Considering energy consumption and latency, we present a multi-objective task-aware service offloading algorithm under the framework of end-edge-cloud collaborative IoMT systems, employing deep deterministic policy gradients (DDPG). Adaptability to the diversity of different services is achieved through dynamic adjustments based on various business types and system requirements. Finally, the effectiveness of DDPG for IoMT is validated using real-world data. © 2008-2012 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Zero-Sum Optimal Control for a Cyber-Physical System in Unreliable Communications via Secure Decentralized Policy Iteration

引用

IEEE Internet of Things Journal 2025年

作者： Zhang, Kun Dong, Xiwang Zhang, Huaguang Su, Rong Beihang University School of Astronautics Beijing100191 China Beihang University Institute of Unmanned System Institute of Artificial Intelligence School of Automation Science and Electrical Engineering Beijing100191 China Northeastern University School of Information Science and Engineering State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China School of Electrical and Electronic Engineering Singapore639798 Singapore

This paper investigates the robust consensus scheme for a specific type of leader-follower multi-agent systems (MASs) in the context of a human-cyber-physical interactive system. The system encounters frequent communication challenges characterized by packet loss and data leakage. To address these challenges, the paper proposes a secure decentralized scheme that leverages game theory to determine optimal policies in a zero-sum game. The scheme utilizes the adaptive dynamic programming (ADP) method, which involves a decentralized iterative process. The paper demonstrates that the generated sequence exhibits exponential convergence and provides the maximum iteration number based on the convergence error. To mitigate data leakage among players, the scheme incorporates a secure operation that involves encrypted data. This integration seamlessly combines data conversion and encryption-decryption into decentralized computation. Finally, the paper presents a simulation example to validate the efficacy of the consensus scheme. © 2014 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

EFIN-MP: Explicit Future Interaction Network for Motion Prediction

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Li, Linhui Su, Jiazheng Qiu, Lihong Lian, Jing Guo, Ge Department of Automotive Engineering School of Mechanical Engineering Dalian University of Technology Dalian China Chongqing Changxian Intelligent Technology Co. Ltd Chongqing China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

Accurate prediction the future movements of surrounding traffic participants is crucial for autonomous driving. Among various strategies, learning complex interactive behaviors among agents efficiently stands out as both an effective means and a challenging aspect of improving predictive model performance. To address this challenges, this paper proposes the Explicit Future Interaction Network for Motion Prediction (EFIN-MP), which aims for more precise agent motion predictions. By constructing a novel N-layer decoding module, EFIN-MP can effectively model future interactions between agents. Each layer capitalizes on the multimodal trajectory predictions from its preceding layer to explicitly integrate future interaction features. Specifically, In the first layer of the decoding module, EFIN-MP constructs a goal prediction module based on the attention mechanism, which regresses the multimodal predicted trajectories of multiple agents in the scene by fusing goal points with contextual features. To predict goal points efficiently, EFIN-MP establishes a dynamic search area in the preprocessing stage. This area integrates rules and knowledge, effectively utilizing road constraints and minimizing the number of potential goal points. Experiments show that EFIN-MP achieves outstanding performance on the Argoverse 1 motion forecasting benchmark and nuScenes dataset, demonstrating both high predictive accuracy and effectiveness. IEEE

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Prescribed Performance Control of Feedback Linearizable Systems Under Actuator Failures

Fault-Tolerant Prescribed Performance Control of Feedback Li...

引用

第33届中国过程控制会议

作者： Wei Ding Jin-Xi Zhang Faculty of Electrical Engineering and Automation Changshu Institute of Technology State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

This paper is dealt with the fault-tolerant control(FTC) problem for a class of multi-input single-output feedback linearizable systems subject to actuator failures and external *** from the model-based FTC methods,a robust prescribed performance control approach is proposed to solve this *** controller is independent of information on the system nonlinearities or the failure patterns,but does not invoke fault detection,fault isolation,fault diagnosis,adaptive identification,function approximation,or disturbance ***,it guarantees the closed-loop system with satisfactory transient and steady-state performance in the context of reference tracking,despite the presence of actuator *** simulation results illustrate the effectiveness of the proposed control.

关键词： actuator failure fault-tolerant control nonlinear systems prescribed performance control

来源：评论

学校读者我要写书评

暂无评论

Efficient Ensemble Broad Learning System Based on Dropout and Dropconnect

引用

The International Journal of Intelligent Control and Systems 2024年第2期29卷 79-87页

作者： Yiwan Cao Fei Chu Shuai Li C.L.Philip Chen Jun Fu School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110004China

Broad learning system(BLS)is an emerging neural network characterized by its rapid processing and robust generalization ***,determining the appropriate structure for broad learning system is also a *** addition,broad learning system may perform overfitting due to the dependence between nodes in processing fully connected *** deal with these problems,an efficient ensemble broad learning system based on Dropout and Dropconnect is proposed in this *** proposed Dropout ensemble broad learning system randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction *** Dropconnect ensemble broad learning system randomly drops connection weights to generate more complementary models by adding input attribute *** experimental results on the UCI datasets confirm that the method proposed in this paper can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning *** proposed algorithm outperforms the original BLS in terms of prediction stability and classification accuracy.

关键词： Broad learning system ensemble learning Dropout Dropconnect

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sliding Mode Quantized Control under Hybrid Cyber-Attacks

Adaptive Sliding Mode Quantized Control under Hybrid Cyber-A...

引用

第43届中国控制会议

作者： Dancheng Mao Yugang Niu Jiarui Li Kun Xu The Key Laboratory of Smart Manufacturing in Energy Chemical Process (East China University of Science and Technology) Ministry of Education Department of Electrical Automation Logistics Engineering CollegeShanghai Maritime University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This work investigates the sliding mode quantized control problem for networked control system(NCS) under Markov-conforming hybrid *** system state is first quantized via a dynamic uniform quantizer,whose parameter is adaptively updated via a state-dependent adjusting strategy.A one-to-one mapping technique is used to cope with the hybrid attacks obeying Markov chains in sensor-controller(S-C) and controller-actuator(C-A) *** then,a sliding mode control(SMC) scheme is designed by means of the available quantized state signals via a compensation ***,sufficient conditions are derived to attain the stability of the closed-loop system and the reachability of the specified sliding surface ***,the practical simulation results are provided to illustrate the proposed security control strategy.

关键词： Hybrid cyber-attack Sliding mode security control Adaptive quantization

来源：评论

学校读者我要写书评

暂无评论

Robust Global Prescribed Performance Control of Unknown Strict-Feedback Systems

Robust Global Prescribed Performance Control of Unknown Stri...

引用

第34届中国控制与决策会议

This paper is concerned with the reference tracking control problem for strict-feedback systems with unknown nonlinear functions under mismatched disturbances.A tuning function-based prescribed performance control strategy is proposed to solve the *** the control design,the tuning function is employed to adjust the output tracking error and the intermediate tracking *** this way,the dependence of the performance specifications on the initial condition of the closed loop is ***,a set of barrier functions are adopted to confine the resulting error signals,while the potential robustness of the barrier functions is thoroughly *** doing so,it is guaranteed that all the real errors converge from any initial positions to the preassigned sets in the given *** simulation results illustrate the effectiveness of the proposed control.

关键词： Prescribed Performance Control Nonlinear Systems Global Stability Model Uncertainty Robustness

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Learning for Anomaly Detection in Complex Industrial process: Methodology and Benchmark

arXiv

引用

arXiv 2024年

作者： Wu, Gaochang Zhang, Yapeng Deng, Lan Zhang, Jingxin Chai, Tianyou State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia

Anomaly detection in complex industrial processes plays a pivotal role in ensuring efficient, stable, and secure operation. Existing anomaly detection methods primarily focus on analyzing dominant anomalies using the process variables (such as arc current) or constructing neural networks based on abnormal visual features, while overlooking the intrinsic correlation of cross-modal information. This paper proposes a cross-modal Transformer (dubbed FmFormer), designed to facilitate anomaly detection by exploring the correlation between visual features (video) and process variables (current) in the context of the fused magnesium smelting process. Our approach introduces a novel tokenization paradigm to effectively bridge the substantial dimensionality gap between the 3D video modality and the 1D current modality in a multiscale manner, enabling a hierarchical reconstruction of pixel-level anomaly detection. Subsequently, the FmFormer leverages self-attention to learn internal features within each modality and bidirectional crossattention to capture correlations across modalities. By decoding the bidirectional correlation features, we obtain the final detection result and even locate the specific anomaly region. To validate the effectiveness of the proposed method, we also present a pioneering cross-modal benchmark of the fused magnesium smelting process, featuring synchronously acquired video and current data for over 2.2 million samples. Leveraging crossmodal learning, the proposed FmFormer achieves state-of-the-art performance in detecting anomalies, particularly under extreme interferences such as current fluctuations and visual occlusion caused by heavy water mist. The presented methodology and benchmark may be applicable to other industrial applications with some amendments. The benchmark will be released at https://***/GaochangWu/FMF-Benchmark. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

An online rock lithological detecting method using color and texture analysis

An online rock lithological detecting method using color and...

引用

Chinese Control and Decision Conference, CCDC

作者： Bo Lu Junwu Zhou Qingkai Wang Gang Yu Kang Li School of Information Science and Engineering Northeastern University BGRIMM Technology Group Beijing China BGRIMM Technology Group State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

In the crushing and comminution process, different lithological rocks strongly affect the performance of crushing equipment. However, traditional lithological identification cannot be analyzed in a timely manner for processing control. Many rock lithological classification methods using color images have been proposed in the past, but few have successfully connected their results with online equipment monitoring. In this paper, we have developed an automatic vision system to evaluate rock lithology in real-time using color and texture features. The results show that the proposed method based on color and texture is robust and outperforms previous methods that rely on any single feature alone. This will help achieve reliable and precise control of the Semi-autogenous mill (SAG) feeding process.

关键词： Image color analysis Machine vision process control Color Rocks Real-time systems Minerals

来源：评论

学校读者我要写书评

暂无评论

A Deep Neural Network-Assisted Diagnosis Method for Cardiovascular Disease Based on the Optimization of the TAdam Algorithm

A Deep Neural Network-Assisted Diagnosis Method for Cardiova...

引用

2023 China automation Congress, CAC 2023

作者： Hu, Yumei Li, Xing Zhang, Yang Zhu, Yuxuan Sun, Yuechao College of Computer Science and Technology Dongguan University of Technology Dongguan China School of Electrical Engineering & Intelligentization Dongguan University of Technology Dongguan China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang China School of Mechanical Engineering of Dgut Dongguan University of Technology Dongguan China Northeastern University College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350303759

Cardiovascular disease is a sudden and extremely disabling and deadly disease that hinders the development of public health care in China and poses a serious threat to the health of users. Therefore, this paper proposes a deep neural network-assisted diagnosis of cardiovascular disease based on TAdam algorithm optimization under a distributed medical monitoring network to enable rapid identification of cardiovascular patients, timely detection and reporting of the condition. This paper addresses the problems that deep neural network models are susceptible to the influence of their structure and hyperparameters and poor generalization convergence, firstly, the mainstream optimization algorithms based on deep learning are sorted out, and finally the T Adam algorithm is used to optimize the model. By comparing the common gradient optimization algorithms SGD (Stochastic Gradient Descent), Adagrad (Adaptive Gradient Algorithm), RMSprop (Root Mean Square propagation), Adam (Adaptive Moment Estimation) and the improved TAd am optimization algorithm trained and tested on the same dataset, the experimental results show that the TAdam algorithm exhibits the fastest convergence speed and the best generalization performance on the cardiovascular disease dataset. The method proposed in this paper enables rapid diagnosis of the user's disease risk and feedback to the relevant personnel to maximise user safety. © 2023 IEEE.

关键词： Deep neural networks

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：