检索结果-内蒙古大学图书馆

IEEE Transactions on Sustainable Computing 2025年第3期10卷 534-546页

作者： Tian, Jiwei Shen, Chao Wang, Buhong Ren, Chao Xia, Xiaofang Dong, Runze Cheng, Tianhao Xi’an Jiaotong University Ministry of Education Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an710049 China Air Force Engineering University Air Traffic Control and Navigation College Xi’an710051 China Air Force Engineering University Information and Navigation College Xi’an710043 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Xidian University School of Computer Science and Technology Xi’an710126 China

Although conventional false data injection attacks can circumvent the detection of bad data detection (BDD) in sustainable power grid cyber physical systems, they are easily detected by well-trained deep learning-based detectors. Still, state estimation models with deep leaning-based detectors are not secure due to the vulnerabilities and fragility of deep learning models. Using the related laws of conventional false data injection attacks and adversarial sample attacks, this paper proposes the targEted adVersarial fAlse Data injEction (EVADE) strategy to explore targeted adversarial false data injection attacks for state estimation in Smart Grid. The proposed EVADE attack strategy selects key state variables based on adversarial saliency maps to improve the attack efficiency and perturbs as few state variables as possible to reduce the attack cost. In this way, the EVADE attack strategy can bypass the detection of BDD and neural attack detection (NAD) methods (that is, maintaining deep stealthy) with a high success rate and achieve the attack target simultaneously. Experimental results demonstrate the effectiveness of the proposed strategy, posing serious and pressing concerns for sustainable cyber physical power system security. © 2016 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Research on Arc Fault Simulation Device Based on Closed-loop Feedback control 5

Research on Arc Fault Simulation Device Based on Closed-loop...

引用

5th IEEE International Conference on Automation, Electronics and Electrical engineering, AUTEEE 2022

作者： Jingjing, Su Zhihong, Xu School of Computer and Control Engineering Minjiang University Fuzhou China Fujian Key Laboratory of New Energy Generation and Power Conversion Fuzhou China College of Electrical Engineering and Automation Fuzhou University Fuzhou China

ISBN: (纸本)9781665471978

An efficient arc fault simulation device is beneficial to the research on the mechanism and detection technology of arc faults. In order to simulate the arc fault caused by insulation aging, an arc fault simulation device based on closed-loop feedback control was developed. The device consists of two high-voltage carbonization circuits and a test circuit, which are used for pretreating cable specimens and testing the effects of carbonization respectively. In order to improve the success rate of cable carbonization channels formation, arc voltage, arc current-zero period and arc current rise rate are taken as the basis for arc fault judgment. Finally, the characteristics of carbonized arc are analyzed by using time domain and frequency domain analysis methods. The results show that the developed cable carbonization device can generate continuous burning arc and reduce the interference of human factors in the experiment process, which lays a foundation for further research on the formation mechanism of fault arc. © 2022 IEEE.

关键词： Carbonization

来源：评论

学校读者我要写书评

暂无评论

Performance Creativity Enhancement Method Based on Emotional Analysis and Concentration

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 1019-1048页

作者： Liu, Chang Zhang, Longfei Huang, Tianyu Wu, Yufeng Zhang, Fuquan Lin, Qi Department of Computer Science and Technology Beijing Institute of Technology 100081 China Beijing Key Laboratory of Digital Performance and Simulation Technology 100081 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Informatics King’s College London LondonWC2R 2LS United Kingdom

Intelligent performance creativity is a new research direction of the intersection of technology and art. At present, the cutting-edge technologies such as computer simulation, emotional computing and machine learning have been applied to the evaluation and enhancement of intelligent performance creativity. The application of these technologies has greatly increased the diversity of performance forms and the complexity of performance content. For the traditional stage performance, due to the lack of timely feedback from the audience, it is difficult for the director to enhance the creativity effec-tively. In order to solve this problem, this paper proposes concentration level enhancement method (CLEM). The CLEM extracts and analyzes the physiological and emotional characteristics of the audience by collecting the multimodal physiological signal data of the audience. Through the analysis of the features, the concentration information of the audience is obtained and the concentration level (CL) is defined. Based on the physiological and emotional induction mechanism, a performance creativity enhancement strategy is proposed, which enhances the performance creativity in two aspects: " Visual-based" and " Content-based". Through the concentration level enhancement method, compare the audience’s performance attention changes before and after the performance creativity enhancement, select the effective strategies to enhance the performance creativity, and provide the director with quantifiable performance creativity enhancement feedback results. The experimental results show that the CLEM proposed in this paper can effectively induce significant changes in the audience’s emotion, and the selected creative enhancement strategy can significantly improve the audience’s concentration and achieve the purpose of enhancing the creativity of the performance. © 2023, Journal of Network Intelligence.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Methodology of Field-Oriented control Design With Parameter Variation Analysis for Interior Permanent Magnet Synchronous Machine Drives

引用

IEEE Access 2025年 13卷 89524-89541页

作者： Busarello, Tiago Davi Curi Bubshait, Abdullah Varaprasad, Oruganti V. S. R. Alsaleem, Abdulhakeem Simoes, Marcelo Godoy Federal University of Santa Catarina Department of Control Automation and Computation Engineering Florianopolis88040-900 Brazil King Faisal University College of Engineering Department of Electrical Engineering Al Ahsa31982 Saudi Arabia Group Department of Electrical Computer and Software Engineering OshawaONL1G 0C5 Canada Qassim University College of Engineering Department of Electrical Engineering Buraydah52571 Saudi Arabia University of Vaasa School of Technology and Innovations Vaasa65200 Finland

This paper proposes a comprehensive methodology for Field-Oriented control (FOC) with parameter variation analysis for Interior Permanent Magnet Synchronous Machines (IPMSM). The modeling approach for an IPMSM is first presented, followed by a step-by-step procedure for designing a vector-controlled strategy. The formulation is based on a dq-rotating reference frame aligned with the rotor shaft position. A key distinction of this methodology from traditional approaches is that the current controller is designed in the time domain based on desired time constants, while the speed control is formulated within a frequency response domain framework. The proposed hybrid approach enables accurate tuning of the Proportional-Integrator (PI) controllers for both current and speed control loops. Additionally, a parameter variation analysis is conducted to enhance the proposed methodology. The validity region for the design procedure is presented, ensuring that for any wide speed variation of the machine, loop gains are properly tuned. One of the main advantages of the proposed methodology is that it provides a fast, reliable, and accurate technique for implementing IPMSM drive systems. Results from a controller Hardware-in-the-Loop (C-HIL) setup with an external microcontroller are presented. The comprehensive design approach is validated under two different IPMSM parameter sets, demonstrating its effectiveness. © 2013 IEEE.

关键词： Vector control (Electric machinery)

来源：评论

学校读者我要写书评

暂无评论

Improving Date Fruit Classification Using Cycle GAN-Generated Dataset

引用

computer Modeling in engineering & Sciences 2022年第4期131卷 331-348页

作者： Dina M.Ibrahim Nada M.Elshennawy Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Computers and Control Engineering Department Faculty of EngineeringTanta UniversityTanta37133Egypt

Dates are an important part of human *** are high in essential nutrients and provide a number of health *** fruits are also known to protect against a number of diseases,including cancer and heart *** fruits have several sizes,colors,tastes,and *** are a lot of challenges facing the date *** of the most significant challenges is the classification and sorting of *** there is no public dataset for date fruits,which is a major limitation in order to improve the performance of convolutional neural networks(CNN)models and avoid the overfitting *** this paper,an augmented date fruits dataset was developed using Deep Convolutional Generative Adversarial Networks(DCGAN)and CycleGAN approach to augment our collected date fruit *** augmentation is required to address the issue of a restricted number of images in our datasets,as well as to establish a balanced *** are three types of dates in our proposed dataset:Sukkari,Ajwa,and *** dataset augmentation,we train our created dataset using ResNet152V2 and CNN models to assess the classification process for our three categories in the *** train these two models,we start with the original ***,the models were trained using the DCGAN-generated dataset,followed by the CycleGAN-generated *** resulting results demonstrated that when using the ResNet152V2model,the CycleGAN-generated dataset had the highest classification performance with 96.8%accuracy,followed by the CNN model with 94.3%accuracy.

关键词： Dates fruits data augmentation DCGAN CycleGAN,deep learning convolution neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation 38

Efficient Adaptation of Pre-trained Vision Transformer via H...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Wei Sun, Yuan Yang, Yiting Zhang, Xing Lin, Zhijun Yan, Qingsen Zhang, Haokui Wang, Peng Yang, Yang Shen, Hengtao College of Information and Control Engineering Xi'an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Computer Science and Technology Tongji University China

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One-Dimensional EEG Artifact Removal Network Based on Convolutional Neural Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第1期9卷 142-159页

作者： Xiong, Jun Meng, Xiang-Long Chen, Zhao-Qi Wang, Chuan-Sheng Zhang, Fu-Quan Grau, Antoni Chen, Yang Huang, Jing-Wei School of Computer and Data Science Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China College of Electronic Engineering Shandong University of Science and Technology No. 579 Qianwangang Road Huangdao District Qingdao China College of Computer and Big Data Fuzhou University Fuzhou University Town No. 2 Wulongjiang North Road Fuzhou China Department of Automatic Control Technical Polytechnic University of Catalonia Autonomous Region of Catalonia Barcelona Spain Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China Fujian Province University No. 1 Campus New Village Longjiang Street Fuqing China School of Mechanical and Automotive Engineering Fujian University of Technology No. 33 Xuefu South Road University New District Fuzhou China

The electroencephalogram (EEG) serves as a significant tool in the realms of clinical medicine, cerebral investigation, and neurological disorders research. However, the EEG records we obtain are often easily contaminated by various artifacts, which can blur or distort the underlying EEG signals and make data interpretation difficult. Generally speaking, removing EEG artifacts is considered an essential step in brain signal analysis. Therefore, removing artifacts is crucial for obtaining accurate and reliable EEG signals for subsequent analysis. Recently, deep learning techniques have found widespread application across various domains for denoising tasks, including image denoising and EEG denoising. Many advanced algorithms have been developed in image denoising, which has achieved good results in enhancing low-quality images. Moreover, it has shown superior performance in EEG denoising. In contrast, few people have devoted themselves to studying EEG denoising, and existing convolutional neural network EEG denoising methods still have problems of overfitting and poor denoising effect in Electromyograph(EMG) and ElectroOculoGram(EOG) artifact removal. Therefore, this paper proposes a method called DWINet (De-artifacting with Image-based Network for EEG Signals) based on an image dehazing network DRHNet for removing artifacts from EEG signals. Specifically, our approach DWINet, addresses the de-artifacting issue in EEG signals by converting it as an image dehazing problem and utilizes the image dehazing capability of DRHNet to enhance the denoising performance of EEG signals. Experimental results demonstrate that the proposed method outperforms the compared algorithms in removing the ocular artifact in EEG signals and exhibits higher accuracy and robustness. © 2024, J. Network Intell. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MPC-based Optimization Design for 3D Collision Avoidance of a Mobile Manipulator Based-on Obstacle Velocity Estimation

MPC-based Optimization Design for 3D Collision Avoidance of ...

引用

2024 International Automatic control Conference, CACS 2024

作者： Song, Kai-Tai Lin, Chih-Hsuan Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University 1001 Ta Hsueh Road Hsinchu Taiwan

ISBN: (纸本)9798350354904

This paper presents an optimization design of 3D dynamic obstacle avoidance for a mobile manipulator based on model predictive control (MPC). The design enables a mobile manipulator to achieve optimized 3D collision avoidance motion with shorter avoidance path and faster avoidance time. A 3D LiDAR is installed onboard the robot to acquire environmental point cloud and estimate obstacle velocity. The MPC is designed to track an initial 3D path of the mobile manipulator and avoid any static and dynamic obstacles in real time. Experimental results show that the proposed method can simultaneously avoid static and dynamic obstacles in 3D space. Compared with baseline algorithms without velocity estimation, the proposed method reduces the avoidance path length by 8.27% and path execution time by 13.79%. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Path Planning and control of a 6-DOF Manipulator for Freeform Surface Polishing Based-on a Point Cloud Model

Path Planning and Control of a 6-DOF Manipulator for Freefor...

引用

2024 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2024

作者： Tsai, Fu-Yu Song, Kai-Tai Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University 1001 Ta Hsueh Road Hsinchu Taiwan

ISBN: (纸本)9798350362572

This paper presents a novel path generation method for robotic surface polishing based on point cloud data. In this method, an initial path is first planned to create waypoints via the point cloud. The method estimates the contact area to dynamically adjust initial path points to ensure uniform trajectory coverage on the surface. In this paper, the bilateral tool path generation (BTPG) algorithm is proposed based on a dual-thread strategy to expedite polishing path generation. Further, we introduce a method that generates smooth postures to enhance the stability of the robotic polishing pose. In this work, hybrid force/velocity control scheme is adopted to track polishing path and apply the assigned force on the workpiece freeform surface. Practical experimental results show that the proposed method achieves 95% improvement in path planning time and 85% in smoothness of the robot fourth joint's posture compared with the baseline slicing method. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

LV-UNet: A Lightweight and Vanilla Model for Medical Image Segmentation

LV-UNet: A Lightweight and Vanilla Model for Medical Image S...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Juntao Wang, Mengmeng Tian, Huizhong Cheng, Lingbo Liu, Yong Zhejiang University College of Control Science and Engineering Hangzhou China Zhejiang University of Technology College of Computer Science and Technology Hangzhou China Guangdong Medical University First Clinical Medical College Zhanjiang China

ISBN: (纸本)9798350386226

While large models have achieved significant progress in computer vision, challenges such as optimization complexity, the intricacy of transformer architectures, computational constraints, and practical application demands highlight the importance of simpler model designs in medical image segmentation. This need is particularly pronounced in mobile medical devices, which require lightweight, deployable models with real-time performance. However, existing lightweight models often suffer from poor robustness across datasets, limiting their widespread adoption. To address these challenges, this paper introduces LV-UNet, a lightweight and vanilla model that leverages pre-trained MobileNetv3-Large backbones and incorporates fusible modules. LV-UNet employs an enhanced deep training strategy and switches to a deployment mode during inference by re-parametrization, significantly reducing parameter count and computational overhead. Experimental results on ISIC 2016, BUSI, CVC-ClinicDB, CVC-ColonDB, and Kvair-SEG datasets demonstrate a better trade-off between performance and the computational load. The code will be released at https://***/juntaoJianggavin/LV-UNet. © 2024 IEEE.

关键词： Image segmentation

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：