检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2023年第4期8卷 1289-1302页

作者： Huang, Ting-Qing Wang, Chuan-Sheng Chen, Zhao-Qi Zhang, Fu-Quan Meng, Xiang-Long Grau, Antoni Chen, Yang Huang, Jing-Wei College of Computer and Control Engineering Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China Department of Automatic Control Technical Polytechnic University of Catalonia Autonomous Region of Catalonia Barcelona Spain College of Computer and Big Data Fuzhou University Fuzhou University Town No. 2 Wulong Jiangbei Avenue Fuzhou China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music No. 2 Wannianchang Street Chenghua District Sichuan Province Chengdu City China Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou University Town NO. 200 Xiyuangong Road Fuzhou China Fujian Province University No. 599 Quanxiu Road Juyuanzhou Ecological Civilization District Fujian Province Fuzhou City China College of Electronic Engineering Shandong University of Science and Technology No. 579 Qianwangang Road Huangdao District Qingdao China School of Mechanical and Automotive Engineering Fujian University of Technology No. 33 Xuefu South Road University New District Fujian Province Fuzhou City China

When EEG signals are used to assess the level of student engagement in online teaching tasks, they are often interfered by noise. It is a challenge to effectively remove these noises. Currently, deep learning methods have been applied to the field of EEG denoising. However, existing methods still have some problems. The denoised signals still have obvious noise residue, or the original EEG signals are damaged, and the model fitting speed is too slow. Image dehazing, as a typical denoising task in the field of image enhancement, has achieved great success in recent years. Therefore, inspired by advanced models in this field, we introduce CNN into EEG denoising tasks. In this paper, we take GCANet, an excellent image enhancement model, as an example. The dilated convolutions and gate fusion subnetworks included in GCANet enable more efficient EEG signal denoising. The results demonstrate that the proposed model effectively reduces noise while preserving essential features. Furthermore, in comparison to other state-of-the-art models, our proposed model exhibits enhanced robustness and faster convergence, as evidenced by achieving lower loss values after five epochs. Its good performance provides a new development idea for the field of EEG denoising. © 2023, Taiwan Ubiquitous Information CO LTD. 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

Dynamic Analysis of the Tapered Roller Bearings Driven by Digital Twin

SSRN

引用

SSRN 2024年

作者： Zhao, Wentao Zhang, Chao Wang, Jianguo Gu, Fengshou Peyrano, Oscar García Wang, Shuai Lv, Da School of Mechanical Engineering Inner Mongolia University of Science and Technology Baotou China Inner Mongolia Key Laboratory of Intelligent Diagnosis and Control of Mechatronic System Baotou China Centre for Efficiency and Performance Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom Balseiro Institute Cuyo University San Carlos de Bariloche Argentina

The article suggests a technique that utilizes digital twins to analyze the dynamic properties of tapered roller bearings. Developing digital twin of bearings requires a thorough analysis of multiple aspects like radial clearance, temperature, lubrication, centrifugal force, flexible body, and mixed load. By comparing the results of advanced dynamic models, it has been noticed that the simulation results of digital twins more closely resemble the real operating condition of bearings. In addition, the study findings on dynamic properties exhibit a greater degree of precision and dependability. The dynamic properties of bearings are significantly influenced by radial clearance. The results indicate that the use of digital twin technology provides a new method for studying the changing properties of bearings. © 2024, The Authors. All rights reserved.

关键词： Rollers (machine components)

来源：评论

学校读者我要写书评

暂无评论

An Event-Triggered Fault Detection Method for State-Saturated systems with Time-Delay and Nonlinearities

An Event-Triggered Fault Detection Method for State-Saturate...

引用

第40届中国控制会议

作者： Weilu Chen Jun Hu Dongyan Chen Xiaoyang Yu Zhihui Wu School of Measurement and Communication Harbin University of Science and Technology Department of Mathematics Harbin University of Science and Technology Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology

The fault detection problem is addressed in this paper for a class of state-saturated systems with time-delay and nonlinearities under communication *** particular,the phenomenon of state saturation is introduced to characterize the physical limitations of the ***,the event-triggered communication strategy is adopted to achieve the purpose of saving network resources and preventing data ***,an event-based fault detection filter is *** selecting the appropriate Lyapunov functional,several sufficient conditions are obtained such that the addressed augmented system is globally asymptotically stable with a satisfactory H performance ***,the filter parameters are gained through solving certain matrix ***,the effectiveness of the proposed fault detection approach is demonstrated by a numerical example.

关键词： State-saturated systems Fault detection Event-triggered mechanism Time-delay

来源：评论

学校读者我要写书评

暂无评论

Research on Uncertainty Measurement Methods of Aircraft HWIL system

Research on Uncertainty Measurement Methods of Aircraft HWIL...

引用

2020中国仿真大会

作者： Geng huapin Tong jiahui Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory

Uncertainty is an inherent attribute of a simulation system which causes inconsistency between the predicated result of the system and its actual result,affecting the robustness and reliability of the *** on analysis of the uncertainty characteristics of the hardware-in-loop(HWIL) system of an aircraft,a framework of uncertainty measurement and analysis is proposed for the HWIL system,and three types of methods are studied which are suitable for measuring the randomness,cognition,and hybrid uncertainties of the HWIL *** a typical simulation object,various methods of measuring uncertainty are investigated,with their effectiveness validated,which lays the ground for further studying the influence of the uncertainty measurement result on the system.

关键词： HWIL system uncertainty measurement method

来源：评论

学校读者我要写书评

暂无评论

MOSFET/TFET Mixed Power Clamp Circuit For ESD and Surge Protection

MOSFET/TFET Mixed Power Clamp Circuit For ESD and Surge Prot...

引用

Design and system (IEDS), International EOS/ESD Symposium on

作者： Zhaonian Yang Yaping Yue Shi Pu Xiaohan Yang Yue Zhang Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China Shandong Inspur Intelligence Research Institute Co. Ltd. Xi'an China Xi'an Xiangteng Microelectronics Co. Ltd. Xi'an China

ISBN: (数字)9781585373383

ISBN: (纸本)9781665469814

In this paper, a high sensitive voltage detector is proposed and its electrical characteristics are investigated using technology computer-aided design (TCAD) simulation. Germanium (Ge) source and line configuration TFET is adopted to obtain an ultra sensitive detection capability. Corresponding operating principle is explained and the impact of the key parameters on the voltage detector is also discussed. The simulation results show that the new proposed Ge source line TFET based voltage detector has a low leakage current and high detection sensitivity under the electrostatic discharge (ESD) and surge events compared to traditional detectors.

关键词： TFETs Sensitivity Simulation Surge protection Detectors Voltage Germanium

来源：评论

学校读者我要写书评

暂无评论

Self-Attention based Temporal Intrinsic Reward for Reinforcement Learning

Self-Attention based Temporal Intrinsic Reward for Reinforce...

引用

Chinese Automation Congress (CAC)

作者： Zhuo Jiang Daiying Tian Qingkai Yang Zhihong Peng School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781665426480

This paper proposes a self-attention based temporal intrinsic reward model for reinforcement learning (RL), to synthesize the control policy for the agent constrained by the sparse reward in partially observable environments. This approach can solve the problem of temporal credit assignment to some extent and deal with the low efficiency of exploration. We first introduce a sequence-based self-attention mechanism to generate the temporary features, which can effectively capture the temporal property of the task for the agent. During the training process, the temporary features are employed in each sampled episode to elaborate the intrinsic rewards, which is combined with the extrinsic reward to help the agent learn a feasible policy. Then we use the meta-gradient to update this intrinsic reward model in order that the agent can achieve better performance. Experiments are given to demonstrate the superiority of the proposed method.

关键词： Training Automation Reinforcement learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Latent Causal Factors from the Intricate Sensor Feedback of Contact-Rich Robotic Assembly Tasks

SSRN

引用

SSRN 2023年

作者： Chen, Yurou Yu, Jiyang Lin, Zhenyang Shen, Liancheng Liu, Zhiyong The State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Beijing Institute of Spacecraft System Engineering China Academy of Space Technology Beijing China

Achieving precise robotic assembly is paramount for safety and performance in industrial settings. Conventional assembly methods require tedious manual adjustment of many parameters, and it is challenging to meet the assembly requirements with tight clearance. Robot learning has been at the forefront of research, showing potential for automation and intelligence in robotic operations. However, intricate information such as force feedback is indispensable for high-precision robot assembly tasks, and current learning methods grapple with processing this complex observation data due to discontinuous force changes during operation and the inherent noise from the force sensor. To alleviate the low learning efficiency from the problematic observations, we propose introducing the concept of latent causal factors that cause the sensor observations and truly matter in assembly tasks. This paper analyses the impact of discontinuous and noisy observations and offers two ways to infer causal factors. Based on the implied latent factors, we propose a method that learns high-precision assembly policies from interacting with the environment. The algorithm's performance is evaluated in simulated and real-world nut assembly environments, demonstrating significant improvements over the previous methods. This research also underscores the promise of causal inference in addressing intricate industrial challenges%. © 2023, The Authors. All rights reserved.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Gvi: Guideable Visual Interpretation on Medical Tomographic Images to Improve the Performance of Deep Network

SSRN

引用

SSRN 2024年

作者： Liu, Hui Wei, Fan Yan, Lixin Wang, Sushan Jia, Chongfu Zhang, Lina Peng, Jiansheng Xu, Yi School of Control Science and Engineering Dalian University of Technology Dalian China Liaoning Key Laboratory of Integrated Circuit and Biomedical Electronic System Dalian China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China Department of Cardiovascular Radiology The First Affiliated Hospital of Dalian Medical University Dalian China Department of Radiology The First Affiliated Hospital of Dalian Medical University Dalian China Department of Artificial Intelligence and Manufacturing Hechi University Hechi China

In medical image analysis, the demand for interpretable deep neural networks is rapidly growing. However, a major challenge is that most existing interpretative methods are applied after training, leading to a lack of integration with the model's learning process. As a result, these methods often fail to highlight regions within complex medical images critical for decision-making, such as abnormal tissues or lesions, which are essential for accurate diagnoses and treatment planning. This paper introduces Guided Visual Interpretation (GVI), a framework designed to enhance both the performance and interpretability of deep networks. Building on a deep network model with image-level labels, GVI incorporates a small amount of pixel-level annotations combined with attention mechanisms. These mechanisms facilitate visual interpretation through forward propagation, directing the model's focus to the most relevant regions. By aligning the network's decision-making with human cognitive processes, GVI improves interpretability. In our study, an attention layer was added after the convolutional layers of a pre-trained classification network. GVI is trained using a hybrid supervision approach that integrates pixel-level annotations with a large amount of image-level data. Experimental results on both private and public datasets show that GVI generates visual explanations consistent with human decision-making principles and achieves superior classification accuracy compared to traditional methods. These findings highlight GVI's potential to improve interpretability and diagnostic performance in critical fields like medical imaging. © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Accurate Identification and Localization of Transmission Lines Under complex Lighting for Distribution Network Power Supply Operation Robots

Accurate Identification and Localization of Transmission Lin...

引用

Chinese Automation Congress (CAC)

作者： Tianhe Liu Xin Chen Chenyu Hu Xu Jian Shengzu Li Gang Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Wuhan Power Supply Company China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate identification and position of transmission lines is critical for robots to safely and effectively perform distribution network operations. However, such tasks are often challenged by complex lighting conditions, where depth information can be easily lost. Transmission lines have limited texture features and reflective surfaces, making it difficult to match image feature points. To address these challenges, this paper proposes a visual perception system for weak texture targets under complex lighting, based on an “eye-on-hand” configuration and a depth complementation algorithm. Furthermore, a high-precision identification and localization method for transmission line grasping points is developed, utilizing the fusion of binocular visual color maps and depth maps. The proposed method has been shown to effectively solve the problem of identifying and localizing the grasping points of transmission lines under complex lighting conditions. Experiments demonstrated that the method can improve the localization accuracy to within $\pm 4\text{mm}$ , outperforming other algorithms. The method is characterized as simple and efficient, and it enhances the environmental adaptability of distribution network robots.

关键词： Location awareness Visualization Power transmission lines Accuracy Image color analysis Lighting Distribution networks Grasping Wire Robots

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cruise control of Virtual Coupled High-Speed Trains

Adaptive Cruise Control of Virtual Coupled High-Speed Trains

引用

2021 China Automation Congress, CAC 2021

作者： Wang, Di Cao, Yuan Su, Shuai State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Beijing China School of Electric and Information Engineering Beijing Jiaotong University Beijing China Frontiers Science Center for Smart High-speed Railway System State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

ISBN: (纸本)9781665426473

The adaptive cruise formation control problem for multiple high-speed trains (MHSTs) with input, speed and minimum tracking distance constraints under virtual coupling (VC) is proposed in this paper. First, the dynamic equation of MHSTs is created based on the law of kinematics. The communication topology is modeled by graph theory. Next, the speed limit, minimum tracking distance with adjacent trains are dealt with by using the ideas of the potential function. The resistance and unknown disturbances are dealt with by using adaptive control. Then, a cruise control protocol for MHSTs to track the expected trajectory is designed. The Lyapunov theory is used to prove the system stability. Finally, numerical experiments are conducted, which illustrates that the control protocol is effective. © 2021 IEEE

关键词： Graph theory

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：