检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Tang, Zhenhui Wang, Jingcheng Wu, Shunyu The Department of Automation The Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University No.800 Dongchuan Road Shanghai200240 China The SJTU Sanya Yazhou Bay Institute of Deepsea Science and Technology Sanya572024 China The Autonomous Systems and Intelligent Control International Joint Research Center Xi’an Technological University Xi’an710021 China

Recognizing fault types of machinery system is a fundamental but challenging task in industrial application. Although remarkable progress has been attained by learning fault features and predicting the corresponded fault type with deep neural networks, the existing fault diagnosis pipelines usually learn non-discriminative information. Contextual sequence dependency between the localized time fragments is often ignored. To deal with these problem, a recurrent attention framework with reinforcement learning is proposed to find a series of informative features of local time fragments related to different faults in an iterative manner. Fault labels are further predicted on these time fragments. The proposed framework also explicitly models long-term dependencies among these attentional time fragments to capture historical fault information. Experiments on two typical machinery systems, bearing system and hydraulic system, show that the proposed framework achieves superior diagnosis performance and increases no computation burden on CPU. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition from an Open-Set Perspective

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Jun Xu, Chi Cheng, Li China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Vision and Learning Laboratory Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

Existing hand gesture recognition methods predominantly rely on a close-set assumption, which in essence limits the viewpoints, gesture categories, and hand shapes at test time to closely resemble those seen during training. This requirement is however rarely met in practice, as images are often captured from unconstrained viewpoints, with novel gestures and unseen hand shapes that can differ significantly from the training data. This motivates us to investigate an open-set hand gesture recognition problem, where hand gestures are still recognizable from unconstrained viewpoints, and novel gesture classes and hand shapes can be incrementally learned with just a few examples. To address this, we propose a viewpoint influence elimination network that extracts view-independent features, significantly improving performance in scenarios with unconstrained viewpoints. Moreover, a joint-weighted classification scheme is introduced to augment the cosine similarity metric for evaluating few-shot incremental learning of novel gestures and shapes. Finally, as existing hand gesture recognition datasets primarily adhere to the close-set assumption, a new hand gesture recognition dataset, OHG, is introduced in this paper, that includes a wide range of viewpoints, diverse gesture classes, and distinct hand shapes. Experimental hand gesture recognition results demonstrate the superior performance of our approach in both unconstrained viewpoint and few-shot incremental learning scenarios. The source code and the OHG dataset are to be made available at https://***/zhoujun-7/OSHGR. © 1999-2012 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Yuanyang Wang, Zhi Zhu, Yuanheng Chen, Chunlin Zhao, Dongbin The Department of Control Science and Intelligent Engineering School of Management and Engineering Nanjing University Nanjing210093 China The Research Center for Novel Technology of Intelligent Equipment Nanjing University Nanjing210093 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the discrete atomic actions, the explosion in the number of discrete actions can possess undesired properties and induce a higher variance for the policy gradient estimator. In this paper, we introduce a straightforward architecture that addresses this issue by constraining the discrete policy to be unimodal using Poisson probability distributions. This unimodal architecture can better leverage the continuity in the underlying continuous action space using explicit unimodal probability distributions. We conduct extensive experiments to show that the discrete policy with the unimodal probability distribution provides significantly faster convergence and higher performance for on-policy reinforcement learning algorithms in challenging control tasks, especially in highly complex tasks such as Humanoid. We provide theoretical analysis on the variance of the policy gradient estimator, which suggests that our attentively designed unimodal discrete policy can retain a lower variance and yield a stable learning process. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Bandit Convex Optimization With Time-Varying Constraints

引用

IEEE Transactions on control of Network systems 2025年

作者： Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Ministry of Education Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai201210 China Southeast University School of Automation Nanjing210096 China University of Groningen Engineering and Technology Institute Groningen Faculty of Science and Engineering GroningenAG 9747 Netherlands KTH Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm10044 Sweden KTH Royal Institute of Technology Digital Futures Stockholm10044 Sweden

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms solving this problem require that each agent broadcasts its decision to its neighbors at each iteration. However, communication resources are often limited. To better utilize communication resources, we propose a distributed event-triggered online primal-dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results. © 2014 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Reducing the Influence of Individual Variability in sEMG-Based Fatigue Detection Using Transfer Learning

Reducing the Influence of Individual Variability in sEMG-Bas...

引用

Pervasive and intelligent Computing (PICom), IEEE Conference on

作者： Renwei Lin Feng Wang Seiichi Kawata Juan Zhao Jinhua She Daisuke Chugo 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 School of Engineering Tokyo University of Technology Hachioji Tokyo Japan School of Engineering Kwansei Gakuin University Sanda Hyogo Japa

ISBN: (数字)9798331522742

ISBN: (纸本)9798331522759

In the field of sEMG fatigue detection, deep learning algorithms have emerged as prominent tools due to their unparalleled capability to automatically learn discriminative features from extensive datasets. However, the practicality of fatigue detection in everyday life remains limited, as it demands a substantial effort from users to generate vast amounts of sEMG data. In this paper, we propose the hypothesis that by aggregating sEMG data from multiple users, it becomes feasible to extract general informative features from the resulting large dataset, thus enhancing the ability to detect fatigue. To achieve this, transfer learning is employed on the aggregated data from various users, leveraging the power of deep learning algorithms to learn discriminative features from large datasets. The approach involves initially training the model using one individual's sEMG data, followed by fine-tuning using minimal data from other individuals, allowing for efficient personalized adaptation with significantly less time compared to retraining from scratch. This study designs a transfer learning model using sEMG data from the Tokyo Institute of Technology and demonstrates noteworthy efficiency improvements, reducing the required time by an average of 74.31%, while achieving an average accuracy of 95.32%. These experimental results emphasize the potential of transfer learning to enhance the practicality and widespread applicability of sEMG fatigue detection in real-world applications.

关键词： Training Deep learning Adaptation models Accuracy Transfer learning Muscles Fatigue Feature extraction Data models Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-agent coverage control for enhanced geohazard monitoring: a brief review

引用

control Theory and Technology 2021年第3期19卷 418-420页

作者： Chao Zhai Zhaoxu Wang Jie Dou School of Automation China University of GeosciencesWuhan430074China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems WuhanChina Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhanChina Three Gorges Research Center for Geo-Hazards Ministry of EducationChina University of GeosciencesWuhan430074China

In recent years,cooperative coverage control of multi-agent system(MAS)has attracted plenty of researchers in various fields[1,2].Different from multi-agent consensus or synchronization,multi-agent coverage control cares about how to coordinate a team of agents for effectively monitoring or covering a given terrain,which inevitably gives rise to the interaction between individual dynamics and external ***,environmental uncertainties that include static uncertainties and dynamic uncertainties and limited sensing capabilities of a single agent make it a great challenge to design control algorithms of MAS for achieving the desired coverage performance.

关键词： agent plenty coverage

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Based Fuzzy Atmosfield in Human-Robot Interaction

Multi-Modal Based Fuzzy Atmosfield in Human-Robot Interactio...

引用

Chinese control Conference (CCC)

作者： Xin-Heng Li Zhen-Tao Liu School of Automation China University of Geosciences (Wuhan) 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

Recently, the emotional robot has basic functions of perceiving and expressing emotions, but it still hard to communicate naturally between humans and robots. One major reason is that communication atmosphere is seldom considered in Human-robot Interaction (HRI). We propose Multi-modal (i.e., music background, speech, and semantics) Based Fuzzy Atmosfield (FA), which can not only realize the dynamic adjustment of FA but also dynamically regulate human emotions. In the experiment, a Pepper robot is used and one hundred volunteers are invited for HRI, and soothing piano pieces are used as background music. Questionnaires were filled by the volunteers after the experiments, from which the results show that 90% of the volunteers felt the dynamic changes in the communication atmosphere and 77% of the volunteers felt significant emotional regulation, which demonstrates the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WDNet: A Water Depth Perception Network with Global Information

WDNet: A Water Depth Perception Network with Global Informat...

引用

Chinese control Conference (CCC)

作者： Zhihui Huang Yifeng Tang Chuancong Tang Yifan Xu ChuanShang Luo Bin Liu Hai-Tao Zhang the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation the Engineering Research Center of Autonomous Intelligent Unmanned Systems Huazhong University of Science and Technology Wuhan China

Deep perception of the unmanned surface vehicle's surroundings is an inaccessible part of its fully autonomous navigation mission. The existing methods, whether based on traditional stereo matching or deep learning, do not fully consider the characteristics of water environment, resulting in severe error depths in weak textures (sky, calm lake) and water reflections regions, that increases the risk of running aground or collision. What is worse that there is not a public dataset for depth estimation in the water environment. Therefore, this work proposes a self-supervised model for depth estimation named Water Depth Perception Network (WDNet) to address these problems. The decoder of this network has a wider receptive field and can effectively handle the depth error in the weak texture region. Besides, the WDNet is trained with a novel and effective loss function which assist the network to reduce errors in sky and water region, and some indexes are proposed to evaluate the model's performances in sky and water region. Finally, our proposed WDNet achieves a 0.1056 absolute relative error in ranging, the average number of error pixels in the sky area drops from 15803.87 to 580.91, which only accounted for 0.29% of the image, and the error in water region drops from 51.04 to 6.75, all of them are superior to the performance of baseline model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Koopman Operator Learning control of the Piezoelectric Actuator

Koopman Operator Learning Control of the Piezoelectric Actua...

引用

Chinese control Conference (CCC)

作者： Xiang Huang Hai-Tao Zhang Engineering Research Center of Autonomous Intelligent Unmanned Systems the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The piezoelectric actuator is one kind of device that can drive nanoscale motion. However, the nonlinear hysteresis effect induced by its natural material greatly degrades its positioning accuracy. To handle this challenging issue, this work develops a Koopman model predict control (Koopman- MPC) framework for the piezoelectric actuator. Specifically, the Koopman operator theory is adapted for modeling the piezoelectric actuator dynamics. A simple yet powerful linear model spanned in a high-dimensional space is thus constructed to characterize the hysteresis dynamics. Subsequently, upon the established Koopman model, an MPC scheme is put forward for tracking control of piezoelectric actuators. Therein, by sustained optimizing a cost function containing future outputs and control increments, the control input is obtained. Moreover, extensive tracking simulations are carried out on a simulated piezoelectric actuator for verifying the feasibility and effectiveness of the Koopman- Mpc scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi view 3D reconstruction method for weak texture objects based on "eye-in-hand" model

Multi view 3D reconstruction method for weak texture objects...

引用

2021 China Automation Congress, CAC 2021

作者： Gong, Xuan Chen, Xin Jian, Xu He, Wenpeng School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9781665426473

Size measurement and defect detection of ceramics are required in the production process of ceramic products. Therefore, it is necessary to perform high-precision and fast three-dimensional reconstruction of such targets with smooth surfaces and weak textures. However, the reconstruction of a large number of point clouds from multiple perspectives is time-consuming due to the matching of adjacent feature points. Based on this, a fast point cloud registration strategy based on the "eye-in-hand" model is proposed, which can obtain RGB-D images at multi-view around weak-textured objects with RGB-D camera for rapid point cloud registration and reconstruction. Meanwhile, a 3D point cloud segmentation method based on voxel-grid and euclidean distance clustering is applied to divide the scene point and obtain an accurate 3D model. The experimental results indicate that the multi view 3D reconstruction speed of this method is faster and the accuracy of objects point cloud is within 2 mm. Hence, this method can be well applied in reconstructing the 3D point clouds model for ceramic products. © 2021 IEEE

关键词： Textures

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：