检索结果-内蒙古大学图书馆

Parallel Distance: A New Paradigm of Measurement for Parallel Driving

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1169-1178页

作者： Teng Liu Hong Wang Bin Tian Yunfeng Ai Long Chen the Vehicle Intelligence Pioneers Inc. Qingdao 266109 the Department of Automotive Engineering Chongqing UniversityChongqing 400044China the Mechanical and Mechatronics Engineering Department Waterloo UniversityN2L 3G1Canada the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510006China

In this paper, a new paradigm named parallel distance is presented to measure the data information in parallel driving system. As an example, the core variables in the parallel driving system are measured and evaluated in the parallel distance framework. First, the parallel driving 3.0 system included control and management platform, intelligent vehicle platform and remote-control platform is introduced. Then,Markov chain(MC) is utilized to model the transition probability matrix of control commands in these systems. Furthermore, to distinguish the control variables in artificial and physical driving conditions, different distance calculation methods are enumerated to specify the differences between the virtual and real signals. By doing this, the real system can be guided and the virtual system can be im-proved. Finally, simulation results exhibit the merits and multiple applications of the proposed parallel distance framework.

关键词： Artificial and physical system parallel distance parallel driving 3.0 parallel system rotational and accelerator signal

来源：评论

学校读者我要写书评

暂无评论

A Simplified Variant for Graph Convolutional Network Based Knowledge Graph Completion Model

A Simplified Variant for Graph Convolutional Network Based K...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Yashen Wang Qiang Li Yi Zhang Xuecheng Zhang Zhuoya Ju Jian Sun National Engineering Laboratory for Risk Perception and Prevention (RPP) Key Laboratory of Cognition and Intelligence Technology (CIT) China Academy of Electronics and Information Technology Artificial Intelligence Institute of CETC Beijing China The State Key Laboratory for Management and Control of Complex Systems Scientific and Technological Innovation Center of ARI Institute of Automation Chinese Academy of Sciences Beijing China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing China Khoury College of Computer Science Northeastern University U.S.A Scientific and Technological Innovation Center of ARI Beijing China Qi An Xin Technology Group Inc. Beijing China

Knowledge graphs (KGs) serve as useful resources for various applications including machine learning, data mining, and artificial intelligence. Knowledge Graph Completion (KGC) aims at reasoning over known (observed) facts and infer the missing (unobserved) relationships, to improve KG's coverage. Many recent works have laid stress on leveraging Graph Convolutional Networks (GCNs) for KGC task, which obtain good representation learning ability for graph-structured data, and have achieved satisfactory results. However, GCN-based researches continue to improve these lines of models by introducing an increasingly complex feature space. Especially, the hyper-parameter space of conventional GCN-based KGC model is too huge, resulting in low computational efficiency and excessive storage pressure. To overcome this problem, this paper investigates a simplified and generic variant for GCN-based KGC model, and shows that simple changes in the architecture of the underlying architecture (with a Subtraction Operator and an Addition Operator), can compte with state-of-the-art GCN-based models. Therefore, this paper proposes a easy-to-accomplish plug-in unit, which could be loaded into any current GCN-based KGC architectures, and help them maximize the maintenance of native model's original performance while significantly reducing parameter scale.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Algorithm for the Fabric Spreading and Cutting Problem in Apparel Factories

引用

IEEE/CAA Journal of Automatica Sinica 2019年第4期6卷 961-968页

作者： Xiuqin Shang Dayong Shen Fei-Yue Wang Timo R. Nyberg the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of Sciences (CAS)Beijing 100190China the Qingdao Academy of Intelligent Industries Qingdao 266109China IEEE the Beijing Enineering Research Center of Intelligent Systems and Technology Institute of AutomationCASBeijing 100190China the Cloud Computing Center CASDongguan 523808China the School of Science at Aalto University AaltoFinland

We study the fabric spreading and cutting problem in apparel *** the sake of saving the material costs,the cutting requirement should be met exactly without producing additional garment *** reducing the production costs,the number of lays that corresponds to the frequency of using the cutting beds should be *** propose an iterated greedy algorithm for solving the fabric spreading and cutting *** algorithm contains a constructive procedure and an improving *** the constructive procedure creates a set of lays in sequence,and then the improving loop tries to pick each lay from the lay set and rearrange the remaining lays into a smaller lay *** improving loop will run until it cannot obtain any smaller lay set or the time limit is *** experiment results on 500 cases show that the proposed algorithm is effective and efficient.

关键词： Construction and improvement cutting and packing fabric spreading and cutting heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Digital Twin and Its Application in Transportation Infrastructure

Digital Twin and Its Application in Transportation Infrastru...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Yan Gao Shuyue Qian Zihan Li Ping Wang Feiyue Wang Qing He Key Laboratory of High-Speed Railway Engineering Ministry of Education Southwest Jiaotong University School of Civil Engineering Southwest Jiaotong University Chengdu China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China

A prevailing challenge lies in how to properly design, construct and maintain transportation infrastructure engineering. Due to the development of sensor technology and computing technology, the amount of equipment monitoring data has multiplied and it causes difficulties in real-time state assessment and prediction under the traditional modeling condition. The introduction of Digital Twin technology, which aims to reflect the performance of the real-world product by simulating a virtual space, can solve these problems effectively. This paper reviews recent applications of four types of transportation infrastructure: railways, highways, bridges, and tunnels. Also, the existing research gaps are identified.

关键词： Road transportation Digital twin Transportation Predictive models Real-time systems Rail transportation Data models

来源：评论

学校读者我要写书评

暂无评论

Food-trade-associated COVID-19 outbreak from a contaminated wholesale food supermarket in Beijing

引用

Journal of Biosafety and Biosecurity 2021年第1期3卷 58-65页

作者： Shan Lu Weijia Wang Yanpeng Cheng Caixin Yang Yifan Jiao Mingchao Xu Yibo Bai Jing Yang Hongbin Song Ligui Wang Jiaojiao Wang Bing Rong Jianguo Xu State Key Laboratory of Infectious Disease Prevention and Control Chinese Center for Disease Control and PreventionNational Institute for Communicable Disease Control and PreventionBeijingPR China Shanghai Public Health Clinical Center Shanghai Institute for Emerging and Re-emerging Infectious DiseasesShanghaiPR China Research Units of Discovery of Unknown Bacteria and Function Chinese Academy of Medical SciencesBeijingPR China University of Connecticut StorrsCTUSA Scholl of Public Health Shanxi Medical UniversityTaiyuanShanxi ProvincePR China Center for Disease Control and Prevention of Chinese People’s Liberation Army Fengtai DistrictBeijingPR China The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingPR China Department of Epidemiology Center for Global HealthSchool of Public HealthNanjing Medical UniversityNanjingPR China Institute of Public Health Nankai UniversityTianjingPR China Department of Epidemiology and Biostatistics School of Public HealthNanjing Medical UniversityNanjingPR China

The re-emerging outbreak of COVID-19 in Beijing,China,in the summer of 2020 originated from a SARSCoV-2-infested wholesale food *** postulated that the Xinfadi market outbreak has links with food-trade *** Susceptible to the disease,Infectious,and Recovered coupled Agent Based Modelling(SIR-ABM)analysis for studying the diffusion of SARS-CoV-2 particles suggested that the trade-distancing strategy effectively reduces the reproduction number(R0).The retail shop closure strategy reduced the number of visitors to the market by nearly *** addition,the buy-local policy option reduced the infection by more than 70%in ***,retail closures and buy-local policies could serve as significantly effective strategies that have the potential to reduce the size of the outbreak and prevent probable outbreaks in the future.

关键词： COVID-19 outbreak Transmission mechanism Food distribution network control measures Agent Based Modelling

来源：评论

学校读者我要写书评

暂无评论

Attention based Graph Covolution Networks for Intelligent Traffic Flow Analysis

Attention based Graph Covolution Networks for Intelligent Tr...

引用

IEEE International Conference on automation Science and Engineering (CASE)

作者： Hongxin Zhang Jiaxin Liu Ying Tang Gang Xiong State Key Lab of CAD & CG Zhejiang University China College of Software Engineering Zhejiang University of Technology China State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

Predicting traffic flow is one of the fundamental issue to smart cities. However it is still challenging in vehicular cyber-physical systems because of ever-increasing urban traffic data. Most previous models for traffic flow prediction suffers the problem with variance error depends on time and location. In this paper, a novel graph convolution network (GCN) approach is proposed for predicting citywide traffic flow. Our key idea is to introduce spatial and temporal attention to the GCN model to lessen the impact of urban data complexity. A framework of flow-based graph convolutional network is established to improve traffic flow prediction while investigating the spatial and temporal correlation of traffic flow. We further propose practical strategies that efficiently learn parameters of the model. Experimental results demonstrate that the proposed approach to traffic flow prediction outperforms state-of-the-art approaches.

关键词： Predictive models Data models Analytical models Convolution Urban areas Chebyshev approximation Roads

来源：评论

学校读者我要写书评

暂无评论

DeepFatigueNet: A model for automatic visual fatigue assessment based on raw single-channel EEG

DeepFatigueNet: A model for automatic visual fatigue assessm...

引用

SID Symposium, Seminar, and Exhibition 2019, Display Week 2019

作者： Song, Yaguang Wang, Danli Yue, Kang Zheng, Nan The State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781510896161

Three-dimension (3D) display has become increasingly popular in many fields. However, watching 3D content continuously can lead to visual fatigue that is harmful to users’ vision system. Visual fatigue assessment aims at monitoring users’ brain states based on the electroencephalogram (EEG) signals to identify different fatigue levels and avoid severe fatigue. Most of existing studies on the modeling of visual fatigue assessment rely on manual features extracted from EEG, which is time-consuming and needs prior knowledge. Convolutional Neural Networks (CNNs) which have been used in computer vision, speech recognition have attracted increasing interest. There is still a lack of attempts to employ end- to-end EEG analysis on visual fatigue assessment In this paper, we propose a deep learning model DeepFatigueNet to perform automatic feature extraction and classification from raw single-channel EEG. The DeepFatigueNet is evaluated on our own visual fatigue dataset and compared with the state-of-the-art deep learning methods for EEG-based tasks. The overall accuracy of DeepFatigueNet reaches 75.9% on the three-classification task exceeding other models. The experimental results demonstrate the effectiveness of our model and show the potential of deep convolutional neural networks for end-to-end visual fatigue assessment. © 2019 SID-the Society for Information Display. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection: Joint Segmentation and Classification Framework via Deep Ensemble Network

Glaucoma Detection: Joint Segmentation and Classification Fr...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Siyu Li Zhen Li Limin Guo Gui-Bin Bian Beijing University of Technology Beijing PR China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

Clinical research shows that glaucoma is primarily caused by pathological changes in the optic nerve structure, which may bring about irreversible damage of sight. In relevant literature research, the cup-to-disc ratio (CDR) is mainly used as an important indicator for glaucoma detection, which needs to segment optic disc (OD) and optic cup (OC) region clearly and accurately. However, due to the low contrast image of boundary, the segmentation of OD and OC is still a challenging problem. In this paper, a novel hybrid model based on the ensemble random-forest deep-neural-network (RF-DNN) is proposed for OD and OC segmentation, which can calculate more accurately for glaucoma detection. At the same time, the advantages of DNN and ensemble RF are combined to carry out the corresponding feature extraction and classification, which employs the winner-takes-all strategically to the segmentation and classification for glaucoma detection. Finally, the experiment result shows that the proposed method has reached the best evaluation level in terms of OD and OC segmentation results on ORIGA dataset and SCES dataset, which achieves highest diagnosis accuracy with AUC of 0.96 and 0.98 on ORIGA dataset and SCES dataset, respectively.

关键词： Feature extraction Image segmentation Training Optical imaging Decoding Neural networks Robots

来源：评论

学校读者我要写书评

暂无评论

Device Placement Optimization for Deep Neural Networks via One-shot Model and Reinforcement Learning

Device Placement Optimization for Deep Neural Networks via O...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Zixiang Ding Yaran Chen Nannan Li Dongbin Zhao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

With the development of deep learning that employs deep neural networks (DNN) as powerful tool, its computational requirement grows rapid together with the increasing size (e.g. depth and parameter) of DNN. Currently, model and data parallelism are employed for accelerating the training and inference process of DNN. However, the above techniques make placement decision on devices for DNN based on heuristics and intuitions by machine learning experts. In this paper, we propose an novel approach for designing device placement of DNN in an automatic way. For a DNN, we employ a sequence-to-sequence model as controller to sample device placement from a one-shot model, which contains all possible device placements with respect to a specific hardware environment (e.g. CPU and GPU). Then, reinforcement learning treats the execution time of sampled device placement as reward to guide the sequence-to-sequence model for finding better one. The proposed approach is employed to optimize the device placement for both model and data parallelism of Inception-V3 on ImageNet. Experimental results show that the optimal placements discovered by our method can outperform hand-crafted one.

关键词： Parallel processing Data models Computational modeling Optimization Reinforcement learning Hardware Training

来源：评论

学校读者我要写书评

暂无评论

DGST: Discriminator Guided Scene Text detector

arXiv

引用

arXiv 2020年

作者： Zhao, Jinyuan Wang, Yanna Xiao, Baihua Shi, Cunzhao Jia, Fuxi Wang, Chunheng State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences China

Scene text detection task has attracted considerable attention in computer vision because of its wide application. In recent years, many researchers have introduced methods of semantic segmentation into the task of scene text detection, and achieved promising results. This paper proposes a detector framework based on the conditional generative adversarial networks to improve the segmentation effect of scene text detection, called DGST (Discriminator Guided Scene Text detector). Instead of binary text score maps generated by some existing semantic segmentation based methods, we generate a multi-scale soft text score map with more information to represent the text position more reasonably, and solve the problem of text pixel adhesion in the process of text extraction. Experiments on standard datasets demonstrate that the proposed DGST brings noticeable gain and outperforms state-of-the-art methods. Specifically, it achieves an F-measure of 87% on ICDAR 2015 dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：