检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Yu, Qiang Song, Shiming Ma, Chenxiang Pan, Linqiang Tan, Kay Chen Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Image Information Processing and Intelligent Control Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China The Department of Computer Science City University of Hong Kong Hong Kong

Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones. With a more brain-like processing paradigm, spiking neurons are more promising for improvements on efficiency and computational capability. They extend the computation of traditional neurons with an additional dimension of time carried by all-or-nothing spikes. Could one benefit from both the accuracy of analog values and the time-processing capability of spikes? In this paper, we introduce a concept of augmented spikes to carry complementary information with spike coefficients in addition to spike latencies. New augmented spiking neuron model and synaptic learning rules are proposed to process and learn patterns of augmented spikes. We provide systematic insight into the properties and characteristics of our methods, including classification of augmented spike patterns, learning capacity, construction of causality, feature detection, robustness and applicability to practical tasks such as acoustic and visual pattern recognition. The remarkable results highlight the effectiveness and potential merits of our methods. Importantly, our augmented approaches are versatile and can be easily generalized to other spike-based systems, contributing to a potential development for them including neuromorphic computing. Copyright © 2020, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Discriminative Competitive Representation for Image Classification

Discriminative Competitive Representation for Image Classifi...

引用

第三十八届中国控制会议

作者： Zhongli Ma Xue Qinlin Jiang Tao Jing She Zuoyong Li School of Control Engineering Chengdu University of Information Technology Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University College of Automation Harbin Engineering University

For collaborative representation based image classification methods, it is very important to represent the image well. In this paper, we propose a novel representation method called discriminative competitive representation(DCR) for image classification. It divides the set of all training samples into two competitive subsets to represent a test sample, and then uses the representation result to perform classification. This method can obtain an approximate representation of a test sample and enable representation components to be discriminative and competitive, which is beneficial to correct classification of the test sample. Specifically, the main idea of the DCR method is that it makes test set and training set have low correlation. One notable advantage of the DCR method is that it exploits a mathematically tractable way to obtain discrimination of classes. The image classification experiments show that the DCR method can obtain a higher accuracy than conventional sparse representation methods.

关键词： Discriminative competitive representation image classification sparse representation low correlation

来源：评论

学校读者我要写书评

暂无评论

Application of Image processing technology in Building Surface Crack Detection 6

Application of Image Processing Technology in Building Surfa...

引用

2019 6th International Conference on Advanced Composite Materials and Manufacturing Engineering, ACMME 2019

作者： Xiong, Xin Huang, Li Tian, Jinrong Infrastructure and Logistics Management Wuhan University of Science and Technology Wuhan Hubei430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan Hubei430081 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan Hubei430081 China

The phenomenon of cracks on the surface of buildings is widespread. The existence of cracks affects the normal use of buildings, shortening the service life, seriously damaging the structure of buildings, resulting in safety accidents. Therefore, regular detection and reinforcement of cracks on the surface of buildings is a necessary link to ensure safety. At present, the detection of building surface cracks is mainly carried out by manpower with means of equipment assisted. However, there are some problems in manpower detection, such as high manpower consumption, low *** paper presents a method of detecting and inspecting cracks on building surface based on image processing technology in machine vision, which includes image gray transformation, image denoising etc. Curve fitting and least square method are used to obtain crack parameters, so as to improve the inspecting efficiency and realize the automation of building surface inspection. © Published under licence by IOP Publishing Ltd.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Cooperative Motion Planning of Connected and Automated Vehicles at a Signal-Free and Lane-Free Intersection

引用

IFAC-PapersOnLine 2018年第24期51卷 60-67页

作者： Li, Bai Zhang, Youmin Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Canada

Compared with a conventional intersection, a signal-free and lane-free intersection enables the vehicles to drive more flexibly, thereby to promote the throughput and to reduce congestions. This work proposes a fault-tolerant cooperative motion planning method for a number of connected and automated vehicles (CAVs) which are passing through a signal-free and lane-free intersection. Partial loss of actuator effectiveness is considered as the fault type. Even a subtle fault may significantly affect the overall team performance. Thus correctly judging whether each faulty/healthy CAV can still achieve its original goal is impossible until a corresponding motion replanning problem turns out to be solvable or not. To maximize the completeness of the original task, we propose a parallel computation framework, wherein the fault-recovery motion replanning problems in multiple levels of task completeness are tried simultaneously. Concretely, i) each faulty/healthy CAV should accomplish its original goal; ii) only each healthy CAV is required to accomplish its original goal; and iii) all the faulty/healthy CAVs try to stop safely without the need to achieve any original goals. Problems iii), ii), and i) are ranking with increasing computational difficulty. Among all the three problems, the achievable solution to the most difficult one is implemented as the fault-recovery strategy. © 2018

关键词： Motion planning automation Fault tolerance Vehicles Automated vehicles Co operative control connected Intersection managements Optimal controls

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode control of Uncertain Switched Systems with Partly Known Sojourn Probabilities

Sliding Mode Control of Uncertain Switched Systems with Part...

引用

Asian control Conference

作者： Haijuan Zhao Yugang Niu Yuanyuan Zou The Key Laboratory of Advanced Control and Optimization for Chemical Process East China University of Science and Technology Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781728102634

This paper is concerned with the sliding mode control (SMC) problem for a class of uncertain switched systems subject to partly known sojourn probabilities. The sojourn probability is the probability of a switched system staying in each subsystem, which may be available or unavailable. A key issue is how to design a sliding mode controller to guarantee the stability performance of the reconstructed switched systems subject to the partly known sojourn probabilities. To this end, by using a set of stochastic variables, the switched system model is reconstructed with partly known sojourn probabilities. And then, the sliding mode control law is constructed to ensure the reachability of the designed common sliding surface. Furthermore, the sufficient condition is derived to ensure the mean-square stability of the closed-loop system under the partly unknown sojourn probabilities. Finally, a numerical example is provided to illustrate the proposed method.

关键词： Switched systems Switches Closed loop systems Stability analysis Sliding mode control Trajectory

来源：评论

学校读者我要写书评

暂无评论

Analysis and Evaluation of Individual Performance in Team Task

Analysis and Evaluation of Individual Performance in Team Ta...

引用

第三十八届中国控制会议

作者： Xi Li A. Mahmood Lin Wang Sien Lin Zhi Yang Xiaofan Wang Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Talkingbrain Neuro-Technology Inc

Opinion expression in team task plays an essential role in individual performance evaluation. So this study set out to answer the question: How to evaluate individual performance mostly from interaction standpoint. The goals are twofold: 1. to determine whether the three aspects of communication skills, namely "how to speak", "what to say" and "who to communicate",are effective features for evaluating individual performance;2. to design a methodology evaluating individual performance by computation. For the former, the effectiveness of features in speaking cues, communication patterns and speech content are evaluated based on Team Cooperation Database. As for the latter, the evaluation is implemented utilizing Support Vector Machines with mean accuracy 88% which outperforms other six machine learning models, significantly improving accuracy over the baseline. Experimental results indicate that communication patterns and speaking cues are major factors affecting individual performance. Additionally, it can also be concluded that individuals who speak after listening the opinions of others and share their ideas with teammates widely and fully can gain more acceptance in performance evaluation.

关键词： Team Cooperation Dataset individual performance evaluation communication skills turn-taking network

来源：评论

学校读者我要写书评

暂无评论

Correction to: Novel neural adaptive terminal sliding mode control for TCP network systems with arbitrary convergence time

引用

Neural Computing and Applications 2023年第1期36卷 519-519页

作者： Qi, Xuelei Li, Chen Chen, Bao Ni, Wei Ma, Hongjun College of Information Science and Engineering Northeastern University Shenyang People’s Republic of China Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sydney Australia School of Automation Science and Engineering South China University of Technology Guangzhou People’s Republic of China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong Guangzhou People’s Republic of China

来源：评论

学校读者我要写书评

暂无评论

Inverse-system method for identification of damping-rate functions in non-Markovian quantum systems

引用

Physical Review A 2020年第4期102卷 042227-042227页

作者： Shibei Xue Lingyu Tan Rebing Wu Min Jiang Ian R. Petersen Department of Automation Shanghai Jiao Tong University Shanghai 200240 People's Republic of China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 People's Republic of China Department of Automation Tsinghua University Beijing 100084 People's Republic of China Center for Quantum Information Science and Technology TNList Beijing 100084 People's Republic of China School of Electronic and Information Engineering Soochow University Suzhou 215006 People's Republic of China Research School of Electrical Energy and Materials Engineering The Australian National University Canberra 0200 Australia

Identification of complicated quantum environments lies in the core of quantum engineering, which systematically constructs an environment model with the aim of accurate control of quantum systems. In this paper, we present an inverse-system method to identify damping rate functions, which describe non-Markovian environments in time-convolution-less master equations. To access information on the environment, we couple a finite-level quantum system to the environment and measure time traces of local observables of the system. By using sufficient measurement results, an algorithm is designed, which can simultaneously estimate multiple damping rate functions for different dissipative channels. Further, we show that identifiability for the damping rate functions corresponds to the invertibility of the system and a necessary condition for identifiability is also given. The effectiveness of our method is shown in examples of an atom and three-spin-chain non-Markovian systems.

关键词： Open quantum systems Quantum control

来源：评论

学校读者我要写书评

暂无评论

A Forest Fire Detection Method Based on a Deep Learning Approach

A Forest Fire Detection Method Based on a Deep Learning Appr...

引用

第30届中国过程控制会议（CPCC 2019）

作者： Honggang Yu Zhentian Jiao Youmin Zhang Jing Xin Lingxia Mu Shangbin Jiao Han Liu Ding Liu Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Department of Mechanical Industrial and Aerospace Engineering Concordia University

Forest fire detection has great practical significance in actual production and ***, many current solutions are still not reliable in practice and usually affected by many *** paper presents a forest fire detection method based on deep learning approach using aerial images taken by Unmanned Aerial Vehicles(UAVs).We train a full image fire classifier by exploiting YOLOv3, a latest fast and accurate real-time object detection algorithm using deep learning neural ***, the feature map of a certain size is obtained by feature extraction network, such as 13×*** the input image is divided into 13×13 grid ***, if the central coordinate of an object in the ground truth falls in a grid cell, the grid cell will predict the object, because each grid cell will predict a fixed number of bounding *** the largest bounding box with ground truth IOU(Intersection Over Union) is used to predict *** fire patch detector developed in this paper obtains 91% mAP(mean Average Precision) on the data sets used and the FPS(Frames Per Second) average can reach 80.

关键词： Forest fire detection YOLOv3 deep learning Unmanned Aerial Vehicle(UAV)

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：