检索结果-内蒙古大学图书馆

International Conference on Transportation Information and Safety (ICTIS)

作者： Xinan Zhou Xiaoqian Lu Yicheng Song Hongtai Yang School of Transportation and Logistics National United Engineering Laboratory of Integrated and Intelligent Transportation National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781665497145

At the beginning of 2020, with the rapid spread of COVID-19 around the world, the passenger flow of subway has suffered from a serious impact. Based on the subway passenger flow data in Chicago, this article analyzes the impact of COVID-19 on rail transit passenger flow. ArcGIS is used to visualize the spatial-temporal distribution of the passenger flow of different stations during different time periods. Based on the fluctuation characteristics of passenger flow before and after the outbreak of COVID-19, one of the deep learning methods, the LSTM (Long-Short Term Memory) neural network model, is constructed to predict the passenger flow of each station in the scenario of no virus. The decline of passenger flow is calculated for each station. Stepwise regression model is constructed to determine factors that explain the decline in passenger flow, and significant factors are obtained: the original passenger flow, number of houses and jobs within 800m buffer zone, number of bus stops within 800m buffer zone, whether the station is a transfer station, distance from the station to the city center, and the number of low-income people. The results of the study show that after the outbreak of COVID-19, the passenger flow of the subway in Chicago experience a “cliff-like” decline in the short term. The passenger flow in most areas dropped by more than 80%, and the passenger flow of some severely impacted stations dropped by more than 90%. Characteristics of the station and built environment factors of different stations influence the decline of passenger flow.

关键词： COVID-19 Rails Solid modeling Graphical models Fluctuations Neural networks Government

来源：评论

学校读者我要写书评

暂无评论

The difference between customers and subscribers in Boston tourists using shared bicycles under COVID-19: Trip frequency and its determinants

The difference between customers and subscribers in Boston t...

引用

International Conference on Transportation Information and Safety (ICTIS)

作者： Lanzhen Jiang Hongtai Yang Rong Zheng Jinghai Huo School of Transportation and Logistics National United Engineering Laboratory of Integrated and Intelligent Transportation National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781665497145

The COVID-19 pandemic has changed the frequency of tourists using shared bicycles to a certain extent. This paper uses the cycling data of Boston, USA from June 2020 to December 2020, taking users in areas without bicycle sites as tourists. Using customers and subscribers among tourists to share bicycle trip data on a daily basis, taking into account the weather, the built environment of bicycle sites, and the number of COVID-19 cases per week, a negative binomial regression model is used to explore these factors during the epidemic. The relationship between regional customers and subscribers using shared bicycle trips and influencing factors. The results show that, first of all, during the pandemic, there is a double-peak tide phenomenon in the usage of shared bicycles by subscribers among tourists, and customers use more in the evening peak. Secondly, the population density and employment density around bicycle sites have a significant positive impact on the shared bicycle use of customers and subscribers. For every 1% increase in the population, subscriber usage increases by 4.55%, and every 1 % increase in employment Density, customer usage increased by 4.22 %. In addition, the number of bus stations and subway stations has a restraining effect on the use of shared bicycles. Finally, the number of epidemics will increase the usage of customers and subscribers to a certain extent, with subscribers increasing by 0.25% and customer usage increasing by 2.92 %. The research results can timely analyze the usage of bicycles shared by different users among tourists during the pandemic, and can help transportation agencies adjust services in different regions to better control the spread of the virus.

关键词： COVID-19 Pandemics Sociology Employment Bicycles Safety Statistics

来源：评论

学校读者我要写书评

暂无评论

A benchmark for gait recognition under occlusion collected by multi-kinect SDAS

arXiv

引用

arXiv 2021年

作者： Li, Na Zhao, Xinbo National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University China

Human gait is one of important biometric characteristics for human identification at a distance. In practice, occlusion usually occurs and seriously affects accuracy of gait recognition. However, there is no available database to support in-depth research of this problem, and state-of-arts gait recognition methods have not paid enough attention to it, thus this paper focuses on gait recognition under occlusion. We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions (self-occlusion, active occlusion, and passive occlusion) by our multiple synchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS) that can be also applied in security situations. Because Azure Kinect DK can simultaneously collect multimodal data to support different types of gait recognition algorithms, especially enables us to effectively obtain camera-centric multi-person 3D poses, and multi-view is better to deal with occlusion than single-view. In particular, the OG RGB+D database provides accurate silhouettes and the optimized human 3D joints data (OJ) by fusing data collected by multi-Kinects which are more accurate in human pose representation under occlusion. We also use the OJ data to train an advanced 3D multi-person pose estimation model to improve its accuracy of pose estimation under occlusion for universality. Besides, as human pose is less sensitive to occlusion than human appearance, we propose a novel gait recognition method SkeletonGait based on human dual skeleton model using a framework of siamese spatio-temporal graph convolutional networks (siamese ST-GCN). The evaluation results demonstrate that SkeletonGait has competitive performance compared with state-of-art gait recognition methods on OG RGB+D database and popular CAISA-B database. This database will be available at https://***/cvNXE/*** Codes 68T

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Navigation Line Extraction Algorithm for Corn Spraying Robot Based on Improved Yolov8s Network

SSRN

引用

SSRN 2023年

作者： Diao, Zhihua Guo, Peiliang Zhang, Baohua Zhang, Dongyan Yan, Jiaonan He, Zhendong Zhao, Suna Zhao, Chunjiang Zhang, Jingcheng School of Electrical Information Engineering Zhengzhou University of Light Industry Zhengzhou450002 China Nanjing211800 China National Engineering Research Center for Agro-Ecological Big Data Analysis & Application Anhui University Hefei230601 China Information Technology Research Center Beijing Academy of Agriculture and Forestry Sciences Beijing100097 China School of Automation Hangzhou Dianzi University Hangzhou310000 China

Aiming at the shortcomings of the existing navigation line extraction algorithm for corn spraying robot in complex farmland environment, such as poor extraction effect and poor adaptability, this paper proposed a navigation line extraction algorithm for corn spraying robot based on improved YOLOv8s network. This algorithm proposes to use corn plant core as the identification target to locate corn plants. Firstly, a new spatial pyramid structure ASPPF is proposed in this paper, and an improved YOLOv8s model ASPPF-YOLOv8s is proposed for more accurate detection of corn plant cores. Secondly, the center coordinates of the network detection box were used to locate the corn crop row feature points. Finally, the least squares method was used to fit the corn crop row lines. Experimental results showed that ASPPF-YOLOv8s network had a good effect on corn plant cores extraction under different growth periods and environmental pressures. MAP and F1 of ASPPF-YOLOv8s network increased from 86.4% and 86% of YOLOv7 network, 88.8% and 87% of YOLOv8s network, 88.6% and 89% of ASPP-YOLOv8s network to 90.2% and 91%. The average fitting time and average angle error of the centerline of crop row were reduced from 82.6ms and 0.97°for method of Zhang et al., 74.8ms and 0.75°for method of Hu et al., 67ms and 2.03°for method of Yang et al. to 45ms and 0.63°by using the center coordinates of corn plant core detection box combined with least square method. The accuracy rate increased from 91.4% for method of Zhang et al., 93.6% for method of Hu et al. and 87.35% for method of Yang et al. to 94.35%. It shows that the navigation line extraction algorithm proposed in this paper can meet the requirements of real-time and accuracy of visual navigation of corn spraying robot, and can be used to extract navigation line of corn spraying robot in complex farmland environment. © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Power Grid Critical State Search Based on Improved Particle Swarm Optimization 6th

Power Grid Critical State Search Based on Improved Particle ...

引用

6th International Conference on Advanced Intelligent Systems and Informatics, AISI 2020

作者： Luo, Jie Deng, Hui-Qiong Li, Qin-Bin Zheng, Rong-Jin Li, Pei-Qiang Chang, Kuo-Chi School of Information Science and Engineering Fujian University of Technology Fuzhou350108 China Fujian Provincial University Engineering Research Center of Smart Grid Simulation Analysis and Integrated Control Fuzhou350108 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9783030586683

This article proposes a method to find the closest critical initial running state of power grid, aiming at the possible chain reaction failure caused by branch fault in power system. First of all, assuming the initial failure of power grid, considering the specific performance of relay protection, analyze the critical state of the branch in cascading trip in detail, the electrical distance between the current running state and the interlocking fault expressed in the form of nodal injection power is given. Secondly, on the basic of the relationship between the nodal injections power and the system safety, a safety level model that the system will not trigger cascading failures is established. Finally, the improved simplified mean particle swarm optimization algorithm is used to solve the model, and an example is analyzed on IEEE-14 node system. An example shows the effectiveness and feasibility of the proposed method, which provides a reference for further prevention of cascading trip accidents. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Outages

来源：评论

学校读者我要写书评

暂无评论

Accelerating and Securing Federated Learning via Intelligent Reflecting Surface

Accelerating and Securing Federated Learning via Intelligent...

引用

International Conference on Communication technology (ICCT)

作者： Yingying Wu Bomin Mao School of Cybersecurity Northwestern Poly technical University Xi'an Shaanxi China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Cybersecurity Northwestern Poly technical University Xi'an China Yangtze River Delta Research Institute of Northwestern Poly technical University Taicang Jiangsu China

Federated Learning (FL) provides a privacy-protected way to train Machine Learning (ML) models, where multiple edge devices upload the model parameters to the central server without sharing their local data. However, the stochastic nature of wireless channels and frequent communications involved in FL incur high latency while model parameters can be intercepted by eavesdroppers, which leads to privacy leakage. To address the above issues, we exploit the Intelligent Reflecting Surface (IRS) to reconfigure the wireless signal propagation, enabling secure transmission and fast convergence. In this paper, We aim to maximize the minimum secrecy rate at devices via jointly designing transmission power at devices and IRS phase shift. A Deep Reinforcement Learning (DRL) based algorithm is adopted to derive the optimal solution. Transmission power and IRS phase shift are treated as the action elements. These elements are dynamically adjusted through interactions between the agent and the environment, guided by a pre-defined optimal reward. Both the transmission power and IRS phase shift are obtained as outputs from the DRL neural network. Numerical results validate the efficiency of our proposed algorithm and demonstrate that the deployment of IRS can improve the transmission rate and secure the training of FL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

application and development of elastic fibers focusing on composition and structure 6

Application and development of elastic fibers focusing on co...

引用

2021 6th International Seminar on Advances in Materials Science and engineering, ISAMSE 2021

作者： Zhang, Jin Sun, Qinyue Wang, Yumin Dong, Xiongwei Xiong, Yi Zeng, Wei Department of Pharmacy Zhongnan Hospital Wuhan University Wuhan430071 China Science and Technology Institute Key Laboratory of Textile Fiber and Products Ministry of Education Laboratory for Electron Microscopy Wuhan Textile University Hubei Wuhan430073 China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information Engineering Anhui University Anhui Hefei230601 China School of Physics and Technology MOE Key Laboratory of Artificial Micro- and Nano-Structures Wuhan University Wuhan430072 China

Elastic fabric is comfortable to wear, and has been a consumer textile due to its good shape retention and wrinkle resistance after washing. This paper briefly introduces the types and performance characteristics of several common elastic fibers, and analyzes the relationship between the structure and elasticity of different elastic fibers. Finally, the development trend of elastic fibers is proposed. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Elasticity

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fault Diagnosis of Rotating Machine Via Expansive Dual-Attention Fusion Transformer Enhanced by Semi-Supervisedlearning

SSRN

引用

SSRN 2023年

作者： Liu, Sijie Li, Jin Zhou, Nan Chen, Geng Lu, Kuan Wu, Yafeng School of Power and Energy Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710129 China School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Two Shaanxi Xi’an710129 China

The precise identification of faults is an essential component in the effective operation and maintenance of rotating machinery(RM). The growing adoption of deep learning can possibly be attributed to the abundance of automatically generated monitoring data and its strong capacity to effectively learn and detect errors. The efficacy of deep learning techniques is consistently high when a limited amount of fault data is available or when a two-stage diagnostic approach is utilized, including manual feature extraction followed by fault classification. To address these challenges, we offer a novel architecture called Expansive Dual-Attention Fusion Transformer (EDAF-Transformer). This structure combines Convolutional Attention Neural Network with Transfomer, and it is specifically designed to handle limited labeled data. Additionally, we boost the performance of EDAF-Transformer by the implementation of a semi-supervised approach. First, we introduce a primary theory transformer. Then Expansive Dual-branch Attention Module (EDAEM) consists of the Expansive multi-scale channel attention (EMSCA) with multi-scale learning, which is designed to expand the receptive field and fused multi-scale information. Therefore, the EDAFM and TwinSparse Self-Attneiton Fusion Transformer encoder Module are integrated in a cascaded manner to construct a deep network for intelligent fault diagnosis. Moreover, an uncertainty self-training semisupervised strategy based on a balanced unlabeled sample selection is implemented, which could further enhance the generalization of EDAF-Transformer and achieve a better performance. The proposed semi-EDAF-Transformer fault diagnosis method has been extensively tested on publicly available motor bearing data as well as a specially arranged transmission shaft dataset. These experiments demonstrate that this method outperforms other intelligent fault diagnosis methods. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dancing between Threats and Conflicts: How Chinese Energy Companies Invest Amidst Global Geopolitical Risks

SSRN

引用

SSRN 2023年

作者： Huang, Zhuo Ye, Chengfang Lai, Fujun Li, Yunzhong National School of Development Peking University Changsha Institute of Computing and Digital Economy Peking University Beijing100091 China School of Public Administration Xiangtan University Xiangtan411105 China School of Finance Yunnan University of Finance and Economics Kunming650221 China National Engineering Laboratory for Big Data Analysis and Application Peking University Changsha Institute of Computing and Digital Economy Peking University Beijing100091 China

In an increasingly interconnected world, global geopolitical risk (GPR) poses significant challenges to the investment decisions of energy companies. However, few studies have examined the effects of such risk, particularly global geopolitical acts (GPRA) and global geopolitical threat (GPRT), on Chinese energy companies. Utilizing data from publicly listed energy companies in China, this study fills this gap by investigating the effects of GPRA and GPRT on these companies’ investment decisions. The results indicate that GPRT significantly inhibits the investment activities of Chinese energy companies, whereas GPRA promotes them. Capital hedging demand is identified as the primary channel through which GPRA and GPRT affect these companies. Additionally, we determine that factors such as companies’ business credit capability, valuation, operational risk, and degree of internationalization, along with macroeconomic characteristics such as China’s economic opportunities and the business confidence index, moderate the relationships between GPRT, GPRA, and companies’ investment decisions. The findings of this study enhance our understanding of the impact of GPR on the investment decisions of Chinese energy companies and provide valuable insights for both policymakers and industry practitioners navigating the complex global energy landscape. © 2023, The Authors. All rights reserved.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Classification of Coastal Wetland Based on Multi-objective CNN and Decision Fusion Model

Hyperspectral Classification of Coastal Wetland Based on Mul...

引用

Information Systems and Computing technology (ISCTech), International Conference on

作者： Yabin Hu Junfang Yang Guangbo Ren Yi Ma Jianbu Wang Xiaoheng Zhu Lab of Marine Physics and Remote Sensing First Institute of Oceanography Ministry of Natural Resources Qingdao China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xian China College of Oceanography and Space Informatics China University of Petroleum Qingdao China College of Geodesy and Geomatics ShanDong University of Science and Technology Qingdao China

Coastal wetland play an irreplaceable role in maintaining biodiversity and improving climate. In this paper, we proposed a hyperspectral classification algorithm of coastal wetland based on multi-objective Convolutional Neural Networks (CNN) and decision fusion model. The algorithm is named that the multi-objective spatial-spectral CNN classification with binary morphological strategy decision fusion model algorithm (MB2SCNN-BMSDF). The multi-objective hyperspectral feature band selection model of coastal wetland based on spectral deviation algorithm is developed and constructed to effectively obtain hyperspectral sensitive bands for single target surface object types. On this basis, a CNN hyperspectral classification model that integrates multi-objective spatial spectral information, and a binary morphological decision fusion algorithm that combines spatial position information and fuzzy membership degrees are proposed, which solves the problems of salt and pepper noise and sand eye effect in the classification process, and reduces noise information. The results showed that the CNN classification of multi-objective spatial spectral information and the decision fusion model of binary morphology strategy have better classification effect and performance.

关键词：

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：