检索结果-内蒙古大学图书馆

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Collaborative Object Detection and Recognition of Autonomous Underwater Vehicle Based on YOLO Algorithm

Research on Collaborative Object Detection and Recognition o...

引用

第33届中国控制与决策会议

作者： TANG Leisheng XU Hongli WU Han TAN Dongxu Gao Lei Shengyang Institute of Automation Chinese Academy of Science SHENYANG JIANZHU UNIVERSITY Information & Control Engineering Faculty Northeastern University Shenyang Ligong University School of Automation and Electrical Engineering

Autonomous underwater vehicle(AUV) is an important tool for human to explore and research marine *** to the influence of underwater environment,it is impossible to realize the rapid detection and recognition of AUV and the recognition of cooperative *** solve this problem,underwater light vision and underwater image enhancement technology are proposed to realize the rapid detection and recognition of underwater vehicles,so as to realize the recognition of cooperative *** this paper,YOLO algorithm which has a good effect on target detection precision and the recognition speed is used to recognize the underwater vehicle on the Yolo *** the original data set,histogram equalization and CLAHE algorithm are used to enhance the *** are respectively loaded into the same training model and trained on the yolov2 and yolov3 *** analysis of the experimental results shows that the underwater image enhancement technology based on the YOLOv3 network and the CLAHE algorithm can meet the requirements of rapid recognition for underwater vehicle detection and recognition.

关键词： Underwater Vehicle YOLO Neural Network Real-time Detection Target Recognition

来源：评论

学校读者我要写书评

暂无评论

Solar Radiation Forecasting Based on Random Forest and XGBoost

Solar Radiation Forecasting Based on Random Forest and XGBoo...

引用

International Conference on Green Technology and Sustainable Development (GTSD)

作者： Nhat-Truong Nguyen Thai Cat Tuong Dao Le Nhut Tuyen Nguyen Thanh-Dat Nguyen Minh-Vuong Le Isobel Timothea French Van-Tuong Doan Van Hoang Kim Vo Nghi C. Tran Duc-Hung Pham Van-Trung Nguyen Department of Renewable Energy Ho Chi Minh City University of Technology and Education Vietnam Department of Control Engineering and Automation Ho Chi Minh City Industry and Trade College Vietnam LILAMA2 International Technology College Dongnai Viet Nam Institute of Cognitive Neuroscience National Central University Taiwan College of Information and Communication Technology Can Tho University Viet Nam Faculty Electrical and Electronic Engineering Hung Yen University of Technology and Education VietNam

ISBN: (数字)9798350386073

ISBN: (纸本)9798350386080

Renewable energy offers a viable alternative to depleting fossil fuels, contributing to global warming and greenhouse gas emissions. Thus, solar energy is widely favored as a renewable energy source. However, the output power of solar systems is unstable and is highly dependent on environmental circumstances such as radiation, humidity, temperature, and wind. Therefore, accurately estimating solar radiation is crucial for successful integration of the solar system into existing electrical grid systems. In this study, two different machine learning models, XGBoost and Random Forest, were used to predict solar radiation data in Ho Chi Minh City, Vietnam. The results show that RMSE and MAE of the Random Forest model (61.09 and 24.37) is smaller compared to XGBoost (61.31 and 25.08). Regression value of the two models is close to 0.955. In summary, this paper demonstrates that these two machine learning algorithms effectively forecast solar radiation, with the Random Forest model showing better performance.

关键词： Renewable energy sources Temperature distribution Temperature dependence Urban areas Humidity Predictive models Solar system

来源：评论

学校读者我要写书评

暂无评论

TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework

arXiv

引用

arXiv 2023年

作者： Zhao, Yang Yang, Jiaxi Wang, Wenbo Yang, Helin Niyato, Dusit 2 Fusionopolis Way Innovis #08-04 Singapore138634 Singapore Shenzhen Institute for Advanced Study School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Mechanical and Electrical Engineering Yunnan Key Laboratory of Intelligent Control and Application Kunming University of Science and Technology Kunming650050 China Department of Information and Communication Engineering Xiamen University Xiamen361005 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

Industrial systems require reliable predictive maintenance strategies to enhance operational efficiency and reduce downtime. Existing studies rely on heuristic models which may struggle to capture complex temporal dependencies. This paper introduces an integrated framework that leverages the capabilities of the Transformer and Deep Reinforcement Learning (DRL) algorithms to optimize system maintenance actions. Our approach employs the Transformer model to effectively capture complex temporal patterns in IoT sensor data, thus accurately predicting the Remaining Useful Life (RUL) of equipment. Additionally, the DRL component of our framework provides cost-effective and timely maintenance recommendations. Numerous experiments conducted on the NASA C-MPASS dataset demonstrate that our approach has a performance similar to the ground-truth results and could be obviously better than the baseline methods in terms of RUL prediction accuracy as the time cycle increases. Additionally, experimental results demonstrate the effectiveness of optimizing maintenance actions. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Heat Transfer Optimization of end Winding Rotor Generator by the Use of Modified Axial Spacer: A Case Study 1

Heat Transfer Optimization of end Winding Rotor Generator by...

引用

1st International Conference on Industrial Automation, Smart Grid and its Application, ICIASGA 2020

作者： Baskoro, Y. Jaya, I. Glowacz, A. Sulowicz, M. Caesarendra, W. PT Indonesia Power Indonesia Department of Automatic Control and Robotics AGH University of Science and Technology Kraków30-059 Poland Institute of Electromechanical Energy Conversion Faculty of Electrical and Computer Engineering Cracow University of Technology Warszawska 24 Cracow31-155 Poland Faculty of Integrated Technologies Universiti Brunei Darussalam Jalan Tungku Link Gadong Brunei Darussalam BE1410 Brunei

This paper presents a case study of a rotor fault occurring in the rotor generator of a steam power plant located in Lontar, Banten Province, Indonesia. The steam power plant has 3 x 315 MV capacity and uses hydrogen in the cooling system. The issue arising during the operation was caused by heat transfer exceeding the normal level. The grounding of the rotor occurred through rising vibration and temperature, tripping the generator unit. During repairs, the axial spacer was replaced with a new model, where it is longer than the original, adding a bar spacer at a previously unavailable position and creating a cooling track profile. This is a case study on the replacement of the axial spacer model aimed at preventing the expansion of the winding, so as not to touch with each other, through the installation of a longer axial spacer and the addition of the spacer bar, and lastly adding the track profile to the cooling hydrogen gas flow thereby maximizing the cooling process from the end winding rotor generator. Heat transfer is an analysed parameter related to the model change of the axial spacer. The addition of a track cooling gas flow has been able to maximize the heat transfer process, which is simulated in this paper. The performance of the rotor generator increased through several parameters after the replacement of the axial spacer model. © Published under licence by IOP Publishing Ltd.

关键词： Cooling

来源：评论

学校读者我要写书评

暂无评论

Position Sensorless control of Permanent Magnet Synchronous Motor Based on Adaptive Filtering Sliding Mode Observer

Position Sensorless Control of Permanent Magnet Synchronous ...

引用

Chinese control and Decision Conference, CCDC

作者： Anna Wang Yingjie Xiong Tao Zhang College Of Information Science and Engineering Northeastern University Shenyang China School of Electrical Engineering Dalian University of Technology Dalian China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665478977

In the position sensorless control strategy of permanent magnet synchronous motor (PMSM), the back-EMF method based on sliding mode observer (SMO) is favored because of its robustness. In this paper, a SMO based on the piecewise sigmoid function is designed. Based on the back-EMF observation error, the gain adaptation of the SMO is realized, which effectively reduces the high-frequency chattering problem of the conventional SMO. The low-pass filter of the conventional SMO is improved, and an adaptive filter based on the back-EMF low-pass filter is proposed. According to the back-EMF observation error, the cut-off frequency of the low-pass filter is changed in real-time, and the estimation of rotor position is improved. After Matlab/Simulink simulation verification, the control strategy is feasible and achieves a better control effect.

关键词： Adaptation models Low-pass filters Adaptive filters Rotors Sensorless control Observers Permanent magnet motors

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Based Fault Prognosis for Industrial Systems:A Concise Overview

引用

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 330-345页

作者： Kai Zhong Min Han Bing Han Faculty of Electronic Information and Electrical Engineering Dalian University of TechnologyDalian 116024China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of TechnologyDalian 116024China State Key Laboratory of Navigation and Safety Technology Shanghai Ship and Shipping Research InstituteShanghai 200135China

Fault prognosis is mainly referred to the estimation of the operating time before a failure occurs,which is vital for ensuring the stability,safety and long lifetime of degrading industrial *** to the results of fault prognosis,the maintenance strategy for underlying industrial systems can realize the conversion from passive maintenance to active *** the increased complexity and the improved automation level of industrial systems,fault prognosis techniques have become more and more ***,the datadriven based prognosis approaches,which tend to find the hidden fault factors and determine the specific fault occurrence time of the system by analysing historical or real-time measurement data,gain great attention from different industrial *** this context,the major task of this paper is to present a systematic overview of data-driven fault prognosis for industrial ***,the characteristics of different prognosis methods are revealed with the data-based ones being ***,based on the different data characteristics that exist in industrial systems,the corresponding fault prognosis methodologies are illustrated,with emphasis on analyses and comparisons of different prognosis ***,we reveal the current research trends and look forward to the future challenges in this *** review is expected to serve as a tutorial and source of references for fault prognosis researchers.

关键词： Data-driven fault prognosis feature extraction industrial systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Fixed-time Observer-based Sliding Mode controller for Nonlinear Underactuated Hovercraft

A Novel Fixed-time Observer-based Sliding Mode Controller fo...

引用

Theoretical and Applied Computer Science and engineering (ICTASCE), International Conference on

作者： Ali Soltani Sharif Abadi Ayesha Hameed Andrew Ordys Krzysztof Kukielka Pooyan Alinaghi Hosseinabadi Barbara Pierscionek Institute of Automatic Control and Robotics Faculty of Mechatronics Warsaw University of Technology Warsaw Poland School of Engineering and Information University of New South Wales Technology Canberra ACT Australia Faculty of Health Education Medicine and Social Care Medical Technology Research Centre Anglia Ruskin University East Anglia United Kingdom

Using information from the state observer to the controller in real-time is an open field for research and fundamental for solving many problems in control theory. control of underactuated systems is challenging since the degree of freedom (DOF) of these systems is more than their control inputs. In this paper, a fixed-time sliding mode controller for nonlinear underactuated hovercraft systems and a fixed-time sliding mode observer are described. The estimated states of the observer are used in the controller in real-time. The controller and observer work together to track the hovercraft's desired trajectory and estimate the states of the hovercraft. The observer and controller are chattering-free, fast-tracking, and smooth controlling. The Lyapunov theory is used to prove the controller's stability and the observer. The performance of the algorithm is demonstrated in a simulation example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and fuzzy control of permanent magnet synchronous motors 10

Modeling and fuzzy control of permanent magnet synchronous m...

引用

10th International Conference on Power Electronics, Machines and Drives, PEMD 2020

作者： Juki, Domagoj-Kreimir Varga, Toni Beni, Tin Štil, Vedrana Jerkovi Baruki, Marinko Automation and Control Institute TU Wien Vienna Austria Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Osijek Croatia

ISBN: (纸本)9781839535635

This paper deals with Permanent Magnet Synchronous Motor modeling and control. The derived nonlinear dq model is a combination of Finite Element Method simulation data with the classical dq model. The so derived model keeps the precision of the Finite Element Method simulations and also the fast execution times of the dq model. The Finite Element Method data is included in the dq model using Artificial Neural Networks. The derived model is also used for controller design. The chosen controller is a PI like Fuzzy Logic controller, which is tuned using Genetic Algorithm optimization. The Permanent Magnet Synchronous Motor with Fuzzy Logic controller operation is tested using Real-Time (Model-in-the-Loop) simulations. © PEMD *** right reserved.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

A novel explainable ECG classification with spatio-temporal transformers and hybrid loss optimization

引用

Biomedical Signal Processing and control 2025年 110卷

作者： Inam Abousaber Hany El-Ghaish Haitham F. Abdallah Dept. of Information Technology Faculty of Computers and Information Technology University of Tabuk Tabuk Saudi Arabia Dept. of Computer and Control Faculty of Engineering Tanta University 31526 Gharbiya Tanta Egypt Dept. of Electrical Engineering Higher Institute of Engineering and Technology Kafrelsheikh 33511 Egypt

This paper presents a novel deep learning framework for ECG arrhythmias detection, integrating Spatio-Temporal Adaptive Embedding (STAE) Transformers and Variational Autoencoders (VAEs) to improve classification accuracy and address class imbalance. Traditional ECG classification models struggle to capture long-range temporal dependencies and handle imbalanced datasets, leading to poor sensitivity for rare arrhythmias. The proposed system employs STAE Transformers to model intricate temporal and spatial relationships within ECG signals to overcome these challenges. At the same time, VAEs generate diverse and realistic ECG samples to enhance model generalization, particularly for underrepresented arrhythmias. Additionally, combining Focal Loss and Dice Loss, a Hybrid Loss Function further optimizes performance by focusing on hard-to-classify arrhythmias. The model is evaluated on the MIT-BIH Arrhythmias Database and PTB Diagnostic ECG Database using 5-fold cross-validation, achieving an accuracy of 99.56% and a macro F1-score of 95.40%, outperforming existing state-of-the-art methods, with a 3.5% improvement in sensitivity for rare arrhythmias. To ensure interpretability, SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM) are utilized, highlighting the QRS complex and RR intervals as the most critical features and confirming that the model focuses on clinically relevant waveform regions. These results demonstrate the effectiveness of our approach in developing an accurate, interpretable, and robust deep learning system for ECG arrhythmias detection, paving the way for more reliable clinical decision support systems.

关键词：

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：