检索结果-内蒙古大学图书馆

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Huang, Qiheng An, Hao Guan, Ke Li, Yimei Fei, Dan Zhu, Fusheng Wang, He Beijing Jiaotong University State Key Laboratory of Rail Traffic Control and Safety Beijing100044 China Frontiers Science Center for Smart High-speed Railway System Beijing100044 China School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China Guangdong Communications & Networks Institute Guangzhou510700 China Beijing100028 China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

The unmanned aerial vehicle (UAV) swarms are broadly utilized for rescuing, detection, condition monitoring, and cognitive converting nowadays. For optimizing swarm cooperation, robust inter- Uavnetworks are required. This forms a strong motivation for channel characterization of the inter- Uavchannels. However, despite the UAV attitude being a influential factor of inter- Uavchannels, it is still rarely investigated at present. Thus, this study proposes the tapped delay line (TDL) channel models for four typical UAV attitudes including level, diving, climbing, and right banking at the 820 MHz band with a 40 MHz bandwidth based on channel measurements. Correspondingly, the model parameters such as gains, delays, and fading distribution of each tap are extracted and analyzed. The results provide valuable insights into the system design and evaluation of inter- Uavnetworks. © 2022 IEEE.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Compressive Sensing Reconstruction for Rolling Bearing Vibration Signal Based on Improved Iterative Soft Thresholding Algorithm

SSRN

引用

SSRN 2022年

作者： Wang, Haiming Yang, Shaopu Liu, Yongqiang Li, Qiang School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing010044 China State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures Shijiazhuang Tiedao University Shijiazhuang050043 China

A new method of acquisition and reconstruction based on compressive sensing theory is introduced in this paper. An improved ISTA (IISTA) is proposed. Firstly, an acceleration operator considering step size is proposed to estimate the gradient, which can accelerate convergence speed. Then for breaking the limitation of fixed internal gradient step size, a bidirectional search principle is introduced to backtrack its iteration step size. Finally, the constraints of the quadratic approximation model on the reconstruction objective function is proposed to adaptively determine optimal iteration step size. The effectiveness of the method is verified by the reconstruction of bearing vibration signals in different health states. The results show that the proposed method can achieve convergence faster, improve the sparsity of the regular term, and has a better reconstruction performance than the conventional ISTA under different sampling rates. © 2022, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Measurement and Analysis on Radio Coverage of 5G based Train Wireless Communication Network

Measurement and Analysis on Radio Coverage of 5G based Train...

引用

2021 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, APS/URSI 2021

作者： Zhang, Xiaokang Lin, Siyu School of Electronic and Information Engineering Beijing Jiaotong University China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University China Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University China

ISBN: (纸本)9781728146706

5G based train wireless communication network is built in the Electric Multiple Units (EMU) train for investigating the radio coverage scheme with omnidirectional antenna and directional antenna at 4.9GHz. We investigate the influence of using different types of antennas on the radio coverage inside and outside of the EMU. Based on the measurement results, the propagation characteristics in train are analyzed, and then the antenna scheme of train wireless communication network in EMU is suggested. The directional antenna is found to be more suitable for radio coverage in EMU, since it has the characteristics of longer coverage in the train and less radio interference to adjacent trains. © 2021 IEEE.

关键词： Radio interference

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach

arXiv

引用

arXiv 2022年

作者： Gong, Hailong Li, Zirui Lu, Chao Du, Guodong Gong, Jianwei School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Chair of Traffic Process Automation "Friedrich List" Faculty of Transport and Traffic Sciences TU Dresden Germany Institute of Dynamic System and Control ETH Zurich Sonneggstrasse 3 Zurich8092 Switzerland

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which fail in dealing with low-light conditions. This paper proposes a novel approach for trajectory prediction in low-illumination scenarios by leveraging multi-stream information fusion, which flexibly integrates image, optical flow, and object trajectory information. The image channel employs Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) networks to extract temporal information from the camera. The optical flow channel is applied to capture the pattern of relative motion between adjacent camera frames and modelled by Spatial-Temporal Graph Convolutional Network (ST-GCN). The trajectory channel is used to recognize high-level interactions between vehicles. Finally, information from all the three channels is effectively fused in the prediction module to generate future trajectories of surrounding vehicles in low-illumination conditions. The proposed multi-channel graph convolutional approach is validated on HEV-I and newly generated Dark-HEV-I, egocentric vision datasets that primarily focus on urban intersection scenarios. The results demonstrate that our method outperforms the baselines, in standard and low-illumination scenarios. Additionally, our approach is generic and applicable to scenarios with different types of perception data. The source code of the proposed approach is available at https://***/TommyGong08/MSIF. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning Channel Estimation for IRS-Assisted Integrated Sensing and Communication system

arXiv

引用

arXiv 2024年

作者： Liu, Yu Al-Nahhal, Ibrahim Dobre, Octavia A. Wang, Fanggang The State Key Laboratory of Rail Traffic Control and Safety Frontiers Science Center for Smart High-Speed Railway System Beijing Jiaotong University Beijing100044 China The Faculty of Engineering and Applied Science Memorial University St. JohnsNLA1C 5S7 Canada

Integrated sensing and communication (ISAC), and intelligent reflecting surface (IRS) are envisioned as revolutionary technologies to enhance spectral and energy efficiencies for next wireless system generations. For the first time, this paper focuses on the channel estimation problem in an IRS-assisted ISAC system. This problem is challenging due to the lack of signal processing capacity in passive IRS, as well as the presence of mutual interference between sensing and communication (SAC) signals in ISAC systems. A three-stage approach is proposed to decouple the estimation problem into sub-ones, including the estimation of the direct SAC channels in the first stage, reflected communication channel in the second stage, and reflected sensing channel in the third stage. The proposed three-stage approach is based on a deep-learning framework, which involves two different convolutional neural network (CNN) architectures to estimate the channels at the full-duplex ISAC base station. Furthermore, two types of input-output pairs to train the CNNs are carefully designed, which affect the estimation performance under various signal-to-noise ratio conditions and system parameters. Simulation results validate the superiority of the proposed estimation approach compared to the least-squares baseline scheme, and its computational complexity is also analyzed. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Measurement and Analysis of 5G Radio Coverage with Inner End Door on Electric Multiple Units

Measurement and Analysis of 5G Radio Coverage with Inner End...

引用

2021 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, APS/URSI 2021

作者： Yu, Chengxiao Lin, Siyu School of Electronic and Information Engineering Beijing Jiaotong University China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University China Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University China

ISBN: (纸本)9781728146706

Internet of things (IoT) of 5G will be deployed at Electric Multiple Units (EMU) to reduce the number of cables. To ensure the coverage quality of the 5G in carriage, a measurement system, using omnidirectional and directional antenna respecticely, is built in the EMU. The measurement results of Reference Signal Receiving Power (RSRP) in the case of opening or closing inner end door scenario are analyzed for investigating the influence of inner end door. Based on the measurement results, we provide the suggsetions that Remote Radio Unit (RRU) should be deployed at each carriage and every two carriages in case of using omnidirectioanal and directional antenna respectively in closing inner end door scenario. © 2021 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Passenger Demands Oriented Optimization of Virtually Coupled Train Formation Scheduling

Dynamic Passenger Demands Oriented Optimization of Virtually...

引用

Chinese Automation Congress (CAC)

作者： Haobei Zhang Tao Tang Hongjie Liu Yinghui Lang School of Electronics and Information Engineering Beijing Jiaotong University Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China

The research on virtual coupling technology in metros is a hot topic recently. Intelligent automatic train units can flexibly form virtually coupled train formations (VCTFs) when needed, so that the train capacity would be able to adapt to passenger demands, which are changing dynamically with time and space. However, matching the capacity of trains with passenger demands is a difficult decision-making optimization problem. In this work, we propose a collaborative control problem to decide when and how to create a VCTF to meet the dynamic passenger demands in a metro system. A mathematical model is formulated which can simultaneously optimize the number of related train units in a VCTF, the train dwelling time at a station and the running time in a section. Performance indicators such as train load factor and number of stranded passengers are adopted to measure the satisfaction of the operators and passengers. Then, a multi-objective genetic algorithm is adopted to obtain the Pareto optimum solutions. Finally, simulation experiments are conducted, and the relationship between line efficiency and passenger demand in different discrete time periods is analyzed to verify the correctness and feasibility of the model. Compared with the traditional timetabling method, adopting the virtual coupling technology can better adapt the train capacity to meet the time changing passenger demands, which is welcomed by both metro operators and passengers in reality.

关键词： Couplings Road transportation Rails Adaptation models Analytical models Dynamic scheduling Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

A Space-Time Interval Based Protection Method for Virtual Coupling

A Space-Time Interval Based Protection Method for Virtual Co...

引用

Chinese Automation Congress (CAC)

作者： Jiayu Wang Hongjie Liu Tao Tang Xiaolin Luo Ming Chai School of Electronics and Information Engineering Beijing Jiaotong University Beijing China National Engineering Research Centerof Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

As a recent hot topic in railways, Virtual Coupling (VC) is aimed at providing more frequent rail services by operating trains closer. Given that current protection methods cannot fulfill the requirements of VC in terms of safety and efficiency, the implementation of VC urgently calls for an advanced protection method that allows successive trains to drive closer on the premise of safety. Therefore, to improve efficiency, after the force analysis of the train, a train emergency braking model that can describe the real process of emergency braking is proposed. The train emergency braking distance calculated from this model is smaller compared with the traditional train emergency braking model. Then, to ensure train safety, the deficiencies of the existing relative braking distance(RBD) based protection methods are analyzed. After adding constraints of time and space to the train emergency braking process and using the train emergency braking model proposed in this paper, a space-time interval based protection method is proposed. Compared with the RBD protection method, this method can ensure that the trains can track closer under the premise of safety, which can fulfill the requirements of VC. Finally, experiments are conducted to verify the safety and efficiency of the proposed methods. When the braking performance of the preceding train is worse than that of the following train, the space-time interval based protection method avoids the train colliding during the braking process, while RBD based protection method cannot avoid train collision. Experimental results numerically show that the minimum safe distance can be reduced by 29%, compared with the RBD based protection method.

关键词： Couplings Resistance Rails Force Rail transportation Safety Trajectory

来源：评论

学校读者我要写书评

暂无评论

Risk Analysis of Lateral Collision of Military and Civil Aviation Aircraft Based on Event Model 1

引用

International Conference on Artificial Intelligence in China, ChinaAI 2019

作者： Zhao, Guhao Mao, Shaojie Mao, Yi Zhang, Xiaoqiang Wu, Yarong State Key Laboratory of Air Traffic Management System and Technology NanjingJiangsu210007 China Air Traffic Control and Navigation College Air Force Engineering University Xi’anShaanxi710077 China

ISBN: (数字)9789811501876

ISBN: (纸本)9789811501869

Collision risk analysis is an important part of airspace safety assessment. Based on Event model, the lateral position deviation probability of military aircraft is calculated. Combining with the probability model of lateral position deviation of civil aviation aircraft, the frequency of military aircraft collision box passing through separation sheet in high slope circling training is calculated. A collision risk assessment model between training flying aircraft in military training airspace and aircrafts flying in civil aviation route is constructed. Through the simulation calculation of the lateral collision risk of military and civil aviation, the size, layout, and use suggestions of military high slope circling training airspace are obtained, which can provide reference for the airspace safety assessment. © Springer Nature Singapore Pte Ltd 2020.

关键词： Civil aviation

来源：评论

学校读者我要写书评

暂无评论

Graph Reinforcement Learning Application to Co-operative Decision-Making in Mixed Autonomy traffic: Framework, Survey, and Challenges

arXiv

引用

arXiv 2022年

作者： Liu, Qi Li, Xueyuan Li, Zirui Wu, Jingda Du, Guodong Gao, Xin Yang, Fan Yuan, Shihua School of Mechanical Engineering Beijing Institute of Technology Beijing China Chair of Traffic Process Automation "Friedrich List" Faculty of Transport and Traffic Sciences TU Dresden Germany School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore639798 Singapore Institute of Dynamic System and Control ETH Zurich Zurich Switzerland

Proper functioning of connected and automated vehicles (CAVs) is crucial for the safety and efficiency of future intelligent transport systems. Meanwhile, transitioning to fully autonomous driving requires a long period of mixed autonomy traffic, including both CAVs and human-driven vehicles. Thus, collaboration decision-making for CAVs is essential to generate appropriate driving behaviors to enhance the safety and efficiency of mixed autonomy traffic. In recent years, deep reinforcement learning (DRL) has been widely used in solving decision-making problems. However, the existing DRL-based methods have been mainly focused on solving the decision-making of a single CAV. Using the existing DRL-based methods in mixed autonomy traffic cannot accurately represent the mutual effects of vehicles and model dynamic traffic environments. To address these shortcomings, this article proposes a graph reinforcement learning (GRL) approach for multi-agent decision-making of CAVs in mixed autonomy traffic. First, a generic and modular GRL framework is designed. Then, a systematic review of DRL and GRL methods is presented, focusing on the problems addressed in recent research. Moreover, a comparative study on different GRL methods is further proposed based on the designed framework to verify the effectiveness of GRL methods. Results show that the GRL methods can well optimize the performance of multi-agent decision-making for CAVs in mixed autonomy traffic compared to the DRL methods. Finally, challenges and future research directions are summarized. This study can provide a valuable research reference for solving the multi-agent decision-making problems of CAVs in mixed autonomy traffic and can promote the implementation of GRL-based methods into intelligent transportation systems. The source code of our work can be found at https://***/Jacklinkk/Graph_CAVs. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement 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：