检索结果-内蒙古大学图书馆

IEEE/CAA Journal of Automatica Sinica 2017年第1期4卷 1-5页

作者： Fei-Yue Wang Jie Zhang Qinglai Wei Xinhu Zheng Li Li IEEE State Key Laboratory of Management and Control for Complex Systems(SKL-MCCS) Institute of AutomationChinese Academy of Sciences(CASIA) School of Computer and Control Engineering University of Chinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences(SKL-MCCSCASIA) Qingdao Academy of Intelligent Industries Department of Computer Science and Engineering University of Minnesota Department of Automation Tsinghua University

Deep reinforcement learning is a focus research area in artificial intelligence. The principle of optimality in dynamic programming is a key to the success of reinforcement learning methods. The principle of adaptive dynamic programming ADP is first presented instead of direct dynamic programming DP , and the inherent relationship between ADP and deep reinforcement learning is developed. Next, analytics intelligence, as the necessary requirement, for the real reinforcement learning, is discussed. Finally, the principle of the parallel dynamic programming, which integrates dynamic programming and analytics intelligence, is presented as the future computational intelligence. © 2014 Chinese Association of Automation.

关键词： Artificial intelligence Neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved generic acceptance function for Multi-point Metropolis algorithm

Improved generic acceptance function for Multi-point Metropo...

引用

2012 2nd International Conference on Electronic and Mechanical Engineering and Information Technology, EMEIT 2012

作者： Zhang, Yinghua Zhang, Wensheng State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Science BeiJing China

ISBN: (纸本)9789078677604

The key of designing MCMC algorithm is the choice of acceptance function. In this work, Selection criteria of acceptance function is given, and an improved Multi-point Metropolis algorithm with generic acceptance function is proposed, which is called GAF-MPM. Then GAF-MPM is showed to satisfy Detailed Balance Condition to ensure its convergence, the strict proof is given in this work. Further, several different acceptance functions are given, and we discuss the effect on the convergence speed, acceptance rate of the samples and the correlation due to the choice of different acceptance functions. Finally, its correctness and effectiveness is proven through numerical experiments. © the authors.

关键词： Detailed Balance Condition MCMC Metropolis hastings Multi-point

来源：评论

学校读者我要写书评

暂无评论

Visual fatigue assessment based on multi-task learning 31

Visual fatigue assessment based on multi-task learning

引用

31st Stereoscopic Displays and Applications Conference, SD and A 2020

作者： Wang, Danli Wang, Xueyu Song, Yaguang Xing, Qian Zheng, Nan State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

In recent years, with the rapid development of stereoscopic display technology, its applications have become increasingly popular in many fields, and, meanwhile, the number of audiences is also growing. The problem of visual fatigue is becoming more and more prominent. Visual fatigue is mainly caused by vergence-accommodation conflicts. An evaluation experiment was conducted, and the electroencephalogram (EEG) data of the subjects were collected when they were watching stereoscopic content, and then the stereoscopic fatigue state of the subjects during the viewing process was analyzed. As deep learning is proved to be an effective end-to-end learning method and multi-task learning can alleviate the problem of lacking annotated data, the authors establish a user visual fatigue assessment model based on EEG by using multi-task learning, which can effectively obtain the user's visual fatigue status, so as to make the comfort designs to avoid the harm caused by user's visual fatigue. © Society for Imaging Science and Technology 2019

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Nonlinear metric learning with deep independent subspace analysis network for face verification

Nonlinear metric learning with deep independent subspace ana...

引用

作者： Cai, Xinyuan Wang, Chunheng Xiao, Baihua Shao, Yunxue State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Face verification is the task of determining whether two given face images represent the same person or not. It is a very challenging task, as the face images, captured in the uncontrolled environments, may have large variations in illumination, expression, pose, background, etc. The crucial problem is how to compute the similarity of two face images. Metric learning has provided a viable solution to this problem. Until now, many metric learning algorithms have been proposed, but they are usually limited to learning a linear transformation. In this paper, we propose a nonlinear metric learning method, which leams an explicit mapping from the original space to an optimal subspace using deep Independent Subspace Analysis (ISA) network. Compared to the linear or kernel based metric learning methods, the proposed deep ISA network is a deep and local learning architecture, and therefore exhibits more powerful ability to learn the nature of highly variable dataset. We evaluate our method on the Labeled Faces in the Wild dataset, and results show superior performance over some state-of-the-art methods.© 2013 The Institute of Electronics, Information and Communication Engineers.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A hybrid heading control scheme for a biomimetic underwater vehicle 26

A hybrid heading control scheme for a biomimetic underwater ...

引用

26th Annual International Ocean and Polar Engineering Conference, ISOPE 2016

作者： Wang, Rui Wang, Shuo Wang, Yu State Key Laboratory of Management Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781880653883

This paper addresses the novel design of a biomimetic underwater vehicle (BUV) propelled by undulatory fins and its heading control problems. Inspired by the cuttlefish, which can perform flexible motions by undulatory propulsion in narrow spaces, our BUV with two undulatory fins is designed. The specific implementation of mechanical structure is elaborated. Moreover, a hybrid heading control which combines active disturbance rejection control (ADRC) with fuzzy strategy is proposed to achieve accurate heading control for this BUV. In the end, experimental results demonstrate the feasibility and effectiveness of the mechanism and control system. © Copyright 2016 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Fins (heat exchange)

来源：评论

学校读者我要写书评

暂无评论

A SINS Error Correction Approach Based on Dual-Threshold ZV Detection and Cubature Kalman Filter

A SINS Error Correction Approach Based on Dual-Threshold ZV ...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Xu, Ruijie Chen, Shichao Sun, Wenqiao Lv, Yisheng Luo, Jialiang Tang, Ying Institute of Automation Chinese Academy of Sciences College of Information Science & Technology Beijing University of Chemical Technology The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Transportation and Economics Research Institute The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation Chinese Academy of Sciences China University of Geosciences Beijing School of Information Engineering The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Rowan University Department of Electrical and Computer Engineering Glassboro United States

ISBN: (纸本)9798350337020

Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation system (SINS) are widely used to locate people in complex interior or heavily occluded outdoor scenarios due to its light weight and low power consumption. However, IMU of SINS are noisy, and the sampling data error is large, which is a divergence of the error with time. Therefore, it will generate a positioning accumulation error, which affects the final positioning accuracy. The problem of cumulative IMU errors is usually dealt with by Zero-Velocity Update (ZUPT). The zero-velocity detection part of basic ZUPT method usually uses a single threshold to determine the gait of pedestrian, which often has the problem of gait misjudgment and omission. To address these problems, this paper proposes a composite conditional detection method to solve the problem of misjudgment in the zero-velocity interval. In addition, we redesign the zero-velocity update algorithm and uses the Cubature Kalman filter (CKF) for pedestrian positioning error correction. The experimental results demonstrate that the proposed ZUPT method based on dual-threshold detection can better detect the interval between pedestrian motion and stationery than ones with single threshold. The zero-velocity update algorithm based on CKF has higher performance than conventional EKF and UKF methods, which constrains the cumulative error of SINS to about 0.2% of the whole walking distance. © 2023 IEEE.

关键词： Cubature Kalman Filter Inertial Pedestrian Navigation Zero-Velocity Update

来源：评论

学校读者我要写书评

暂无评论

Learning convolutional domain-robust representations for cross-view face recognition

Learning convolutional domain-robust representations for cro...

引用

作者： Chen, Xue Wang, Chunheng Xiao, Baihua Gao, Song State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

This paper proposes to obtain high-level, domain-robust representations for cross-view face recognition. Specially, we introduce Convolutional Deep Belief Networks (CDBN) as the feature learning model, and an CDBN based interpolating path between the source and target views is built to model the correlation of cross-view data. The promising results outperform other state-of-the-art methods. Copyright © 2014 The Institute of Electronics, Information and Communication Engineers.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Recognize User Intents in Online Interactions from Massive Social Media Data 2

Recognize User Intents in Online Interactions from Massive S...

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Chenxi Cui Wenji Mao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences

ISBN: (纸本)9781509036202

Online interactions,especially user generated contents on social events,reveal a variety of communicative purposes ranging from expressing feelings to proposing *** intents in users' online interactive behavior from massive social media data can effectively identify users' motives and intents behind communication and provide important information to aid monitoring,analysis and decision making for a variety of ***,user intents recognition from online communication is inherently challenging due to the ambiguity in semantic processing and diversity of syntax ***,the massive online data are usually unlabeled,which greatly hinders the usage of typical machine learning based methods that can automate the recognition *** this paper,we tackle this problem by proposing a Speech Act Theory guided classification scheme,which regards online communication as performative actions of users and classifies user utterances according to their pragmatic *** the basis of this,we construct a dictionary of performative words,expand it using external knowledge sources and refine it by word embedding and similarity *** then use this dictionary to automatically label the online textual data with *** a large amount of the labeled data,we train feature based classifiers to identify user intents in their online *** experimental study using a microblog dataset on social events from Sina Weibo shows the effectiveness of our proposed method.

关键词： user intent recognition speech act theory online communication social media big data

来源：评论

学校读者我要写书评

暂无评论

Relaying Strategy Based on Estimated Information for Multi-Antenna Cooperative Networks

引用

China Communications 2017年第8期14卷 157-165页

作者： Shuangshuang Han Peng Zhang Feijin Shi Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of SciencesBeijingChina and Qingdao Academy of Intelligent Industries School of Computer Engineering Weifang University Communications Headquarters Ministry of Foreign Affairs of the People's Republic of China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina and Research Center of Computational Experiments and Parallel SystemsThe National University of Defense Technology

A sphere-based list forwarding scheme for multiple-input multiple-output(MIMO) relay networks is proposed and analyzed. Firstly, an estimate forwarding(EF) method is proposed, which forwards the minimum mean squared error(MMSE) estimate of the source data to the destination. Since it performs like amplify-and-forward(AF) and decode-and-forward(DF) for the low and high signal-to-noise ratio(SNR) regions, respectively, the EF relay thus outperforms conventional AF and DF across all SNRs without the need for switching algorithms for different SNRs. Because computational complexity is however high for relays with a large number of antennas(large MIMO) and/or high order constellations, list EF for large MIMO relay networks is proposed. It computes a list sphere decoder based MMSE estimate and retains the advantages of the exact EF relay at a negligible performance loss. The proposed list EF could offer a flexible trade-off between the performance and computational complexity.

关键词： MIMO system cooperative network soft information

来源：评论

学校读者我要写书评

暂无评论

A policy gradient algorithm integrating long and short-term rewards for soft continuum arm control

引用

Science China(Technological Sciences) 2022年第10期65卷 2409-2419页

作者： DONG Xiang ZHANG Jing CHENG Long XU WenJun SU Hang MEI Tao School of Electrical Engineering and Automation Anhui UniversityHefei 230601China State Key Laboratory for Control and Management of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Robotics Research Center Peng Cheng LaboratoryShenzhen 518055China

The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous control problems, which can learn an effective control policy with an unknown system model. However, it is often affected by the high sample complexity and requires huge amounts of data to train, which limits its effectiveness in soft arm control. An improved policy gradient method, policy gradient integrating long and short-term rewards denoted as PGLS, is proposed in this paper to overcome this issue. The shortterm rewards provide more dynamic-aware exploration directions for policy learning and improve the exploration efficiency of the algorithm. PGLS can be integrated into current policy gradient algorithms, such as deep deterministic policy gradient(DDPG). The overall control framework is realized and demonstrated in a dynamics simulation environment. Simulation results show that this approach can effectively control the soft arm to reach and track the targets. Compared with DDPG and other model-free reinforcement learning algorithms, the proposed PGLS algorithm has a great improvement in convergence speed and performance. In addition, a fluid-driven soft manipulator is designed and fabricated in this paper, which can verify the proposed PGLS algorithm in real experiments in the future.

关键词： soft arm control Cosserat rod deep reinforcement learning policy gradient algorithm high sample complexity

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：