检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Haoran Zhang, Qichao Zhao, Dongbin Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

This paper investigates the automatic exploration problem under the unknown environment, which is the key point of applying the robotic system to some social tasks. The solution to this problem via stacking decision rules is impossible to cover various environments and sensor properties. Learning based control methods are adaptive for these scenarios. However, these methods are damaged by low learning efficiency and awkward transferability from simulation to reality. In this paper, we construct a general exploration framework via decomposing the exploration process into the decision, planning, and mapping modules, which increases the modularity of the robotic system. Based on this framework, we propose a deep reinforcement learning based decision algorithm which uses a deep neural network to learning exploration strategy from the partial map. The results show that this proposed algorithm has better learning efficiency and adaptability for unknown environments. In addition, we conduct the experiments on the physical robot, and the results suggest that the learned policy can be well transfered from simulation to the real robot. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Neural Network Model Through Piecewise Linear Approximation

arXiv

引用

arXiv 2020年

作者： Guo, Mengzhuo Zhang, Qingpeng Liao, Xiuwu Zeng, Daniel Dajun School of Management Xi’an Jiaotong University School of Data Science City University of Hong Kong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Department of Management Information Systems Eller College of Management University of Arizona

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory explanations on the same predictions given different methods and data samples, and (b) focus on using simpler models to provide higher descriptive accuracy at the sacrifice of prediction accuracy. To address these issues, we propose a hybrid interpretable model that combines a piecewise linear component and a nonlinear component. The first component describes the explicit feature contributions by piecewise linear approximation to increase the expressiveness of the model. The other component uses a multi-layer perceptron to capture feature interactions and implicit nonlinearity, and increase the prediction performance. Different from the post-hoc approaches, the interpretability is obtained once the model is learned in the form of feature shapes. We also provide a variant to explore higher-order interactions among features to demonstrate that the proposed model is flexible for adaptation. Experiments demonstrate that the proposed model can achieve good interpretability by describing feature shapes while maintaining state-of-the-art accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Correction: Deep learning radiomics of multimodal ultrasound for classifying metastatic cervical lymphadenopathy into primary cancer sites: a feasibility study

引用

Ultraschall in der Medizin - European Journal of Ultrasound 2024年第3期45卷 e2-e2页

作者： Yangyang Zhu Zheling Meng Hao Wu Xiao Fan Wenhao lv Jie Tian Kun Wang Fang Nie Medical Center of Ultrasound Lanzhou University Second Hospital Lanzhou China CAS Key Laboratory of Molecular Imaging The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of the Chinese Academy of Sciences School Beijing China Gansu Province Medical Engineering Research Center for Intelligence Ultrasound Lanzhou China

来源：评论

学校读者我要写书评

暂无评论

Deep Kalman Filter with Optical Flow for Multiple Object Tracking

Deep Kalman Filter with Optical Flow for Multiple Object Tra...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Yaran Chen Dongbin Zhao Haoran Li State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing

Deep matching and Kalman filter-based multiple object tracking (DK-tracking) have been demonstrated to be promising. However, most of existing DK-tracking trackers assume that objects are slow-varying movement with a constant velocity. The assumption is hard to be satisfied in the real world, especially in the image space due to the sight distance. In this paper, we propose a novel multiple object tracking method combining deep feature matching, Kalman filter and flow information, which is called DK-flow-tracking, to improve tracking performance. In DK-flow-tracking, optical flow in consecutive frames is used to provide accurate object motion information for guiding Kalman filter to track objects. Experiments are performed on public datasets: MOT2016, MOT2017, and the proposed method achieves better performances compared to the DK-tracking with the assumption of a constant velocity movement.

关键词： Kalman filters Optical flow Target tracking Feature extraction Object tracking Optical filters

来源：评论

学校读者我要写书评

暂无评论

Discriminative graph regularized broad learning system for image recognition

引用

Science China(Information Sciences) 2018年第11期61卷 179-192页

作者： Junwei JIN Zhulin LIU C.L.Philip CHEN Faculty of Science and Technology University of Macau Dalian Maritime University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

Broad learning system(BLS) has been proposed as an alternative method of deep learning. The architecture of BLS is that the input is randomly mapped into series of feature spaces which form the feature nodes, and the output of the feature nodes are expanded broadly to form the enhancement nodes, and then the output weights of the network can be determined analytically. The most advantage of BLS is that it can be learned incrementally without a retraining process when there comes new input data or neural nodes. It has been proven that BLS can overcome the inadequacies caused by training a large number of parameters in gradient-based deep learning algorithms. In this paper, a novel variant graph regularized broad learning system(GBLS) is proposed. Taking account of the locally invariant property of data, which means the similar images may share similar properties, the manifold learning is incorporated into the objective function of the standard BLS. In GBLS, the output weights are constrained to learn more discriminative information,and the classification ability can be further enhanced. Several experiments are carried out to verify that our proposed GBLS model can outperform the standard BLS. What is more, the GBLS also performs better compared with other state-of-the-art image recognition methods in several image databases.

关键词： broad learning system deep learning graph regularization image recognition feature extraction incremental learning

来源：评论

学校读者我要写书评

暂无评论

Parameter estimation survey for multi-joint robot dynamic calibration case study

引用

中国科学:化学（英文版） 2019年第10期62卷 98-112页

作者： Shaolin ZHANG Shuo WANG Fengshui JING Min TAN The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031 China

Accurate model parameters are the basis of robot *** linear and nonlinear models have been proposed to calibrate the inertial parameters and friction parameters of multi-joint ***,methods of choosing a model and calculating its parameters still have few *** paper reviews typical linear/nonlinear models and different calculation methods for robot dynamic *** simulations,the features of different methods are analyzed,including torque error,parameter error,model adaptability,solution time,and anti-interference ability of the calibration ***,an experiment performed on a six-degree-of-freedom industrial manipulator is used as an example to illustrate how to select the model for a specified *** comparisons and experiments provide references for the parameter calibration of multi-joint robots.

关键词： dynamic parameter calibration friction calibration robot dynamics industrial manipulator dynamic models

来源：评论

学校读者我要写书评

暂无评论

Group Feature Learning and Domain Adversarial Neural Network for aMCI Diagnosis System Based on EEG

Group Feature Learning and Domain Adversarial Neural Network...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Chen-Chen Fan Haiqun Xie Liang Peng Hongjun Yang Zhen-Liang Ni Guan’an Wang Yan-Jie Zhou Sheng Chen Zhijie Fang Shuyun Huang Zeng-Guang Hou State Key Laboratory 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 First People's Hospital of Foshan Foshan China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China

Medical diagnostic robot systems have been paid more and more attention due to its objectivity and accuracy. The diagnosis of mild cognitive impairment (MCI) is considered an effective means to prevent Alzheimer's disease (AD). Doctors diagnose MCI based on various clinical examinations, which are expensive and the diagnosis results rely on the knowledge of doctors. Therefore, it is necessary to develop a robot diagnostic system to eliminate the influence of human factors and obtain a higher accuracy rate. In this paper, we propose a novel Group Feature Domain Adversarial Neural Network (GF- DANN) for amnestic MCI (aMCI) diagnosis, which involves two important modules. A Group Feature Extraction (GFE) module is proposed to reduce individual differences by learning group- level features through adversarial learning. A Dual Branch Domain Adaptation (DBDA) module is carefully designed to reduce the distribution difference between the source and target domain in a domain adaption way. On three types of data set, GF-DANN achieves the best accuracy compared with classic machine learning and deep learning methods. On the DMS data set, GF-DANN has obtained an accuracy rate of 89.47%, and the sensitivity and specificity are 90% and 89%. In addition, by comparing three EEG data collection paradigms, our results demonstrate that the DMS paradigm has the potential to build an aMCI diagnose robot system.

关键词： Deep learning Neural networks Medical services Human factors Sensitivity and specificity Feature extraction Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Bitcoin exchange addresses identification and its application in online drug trading regulation 2

Bitcoin exchange addresses identification and its applicatio...

引用

23rd Pacific Asia Conference on Information systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019

作者： Liang, Jiaqi Li, Linjing Luan, Shu Gan, Lu Zeng, Daniel State Key Laboratory 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 Shenzhen China

A typical example of the impact of the use of Bitcoin on smart health is the darknet market, the website for Bitcoin-based drug sales, and the anonymity exacerbates regulatory difficulties. Bitcoin exchanges are critical portals that link the physical world with cyberspace through buying and selling Bitcoins using fiat money, such as USD and Euro. Thus, identifying exchange addresses in the Bitcoin transaction network is the primary step to detect drug trading in darknet markets. In this paper, we first validate that the exchange addresses are identifiable. Then we propose identification methods based on embedding representation of transaction network. Experimental results on a dataset with records of one-week transactions validated the effectiveness of our method. This work will offer the basis for subsequent applications in smart health. © Proceedings of the 23rd Pacific Asia Conference on Information systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019.

关键词： Bitcoin

来源：评论

学校读者我要写书评

暂无评论

The 110kV Live-Maintaining Robot control System Design for Substation Equipment in complex Working Conditions

The 110kV Live-Maintaining Robot Control System Design for S...

引用

Chinese control Conference (CCC)

作者： Chenyu Hu Xin Chen Chengyu Li Guangxian Huang Cheng Zhou Xu Jian School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Future Technology China University of Geosciences Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Xianning Power Supply Company Xianning China Operations and Maintenance Department State Grid Hubei Electric Power Co. Ltd Xianning Xian'an District Power Supply Company Xianning China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

Live-maintaining work is essential for continuous power supply to the substation. To improve the safety and efficiency of live-maintaining work, this paper proposes an equipotential live-maintaining robot system suitable for 110kV voltage levels. Considering the narrow space, complex working conditions and strong electromagnetic interference in substations, binocular vision technology, manipulator trajectory planning algorithm based on time-energy optimization, high voltage electromagnetic shielding technology are utilized to develop the system, and the live-maintaining robot is successfully applied in actual substation. By accurately identifying and locating the joint bolts and insulator, the robot system can achieve equipotential live-disassemble, live-assemble the joint bolts within 18 minutes and live-clean insulator within 5 minutes, demonstrating its the effectiveness and practicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Brief Research and Lookback of the Development of Iris Recognition

A Brief Research and Lookback of the Development of Iris Rec...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Li, Xiaoshuang Hu, Shenhua Lv, Chengkan Qin, Haojun Zhu, Fenghua Wang, Feiyue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing China School of Electrical Engineering and Aotumation Wuhan University Wuhan China

ISBN: (纸本)9781728128535

Personal identification has been used more and more widely in information society. Iris recognition, as one of numerous identification methods, has already been applied in many situations, because the iris patterns have stable, unique and non-invasive features. We analyze the general process of iris recognition in this paper, including image preprocessing, feature extraction, classification and recognition. We also study the progress in iris recognition brought by deep learning method. It is our belief that traditional approaches play a very significant role in iris recognition field, while deep learning methods will make a great difference to iris recognition. © 2019 IEEE.

关键词： Deep learning

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：