检索结果-内蒙古大学图书馆

International Conference on transportation Information and Safety (ICTIS)

作者： Yexin Lin Yugang Liu Liying Tang Shuai Zheng Bin Chen Hongtai Yang School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu China Institute of Transportation Development Strategy &#x0026 Planning of Sichuan Province Chengdu China

ISBN: (纸本)9781665497145

The symmetric intersection (SI) is a type of unconventional intersection that could increase capacity of the intersection. Although this type of intersection is promising, the bicycle crossing method has not been designed for SI, which prevents it from implementation. In this study, we propose three bicycle crossing designs for the purpose of eliminating the conflict between bicycles and vehicles, and optimize the corresponding signal timing. The first is to reverse the bicycle lane on the right-hand-traffic arterial, so that left-turning bicycles can pass at any time, which can reduce the flow of bicycles through the conflicting area of the intersection. The second is to use an advanced stop line, which moves the stop line backwards and sets up a bicycle waiting area in the front to reduce the conflict between bicycles and vehicles. The third is to set up an exclusive phase for bicycles to separate vehicles and bicycles. A linear programming model that maximizes the capacity of the intersection for vehicles considering constraints such as signal phase and cycle duration is established to calculate the signal timing. A case study is performed to determine the optimal signal timing of each condition. The results show that the scheme of advanced stop lines could reduce delays and increase capacity of the intersection for bicycles, but the capacity for vehicles is reduced, and thus should be used when the traffic demand of motor vehicles is not high. In the condition of high-throughput vehicles, the exclusive phase for bicycles perform better.

关键词： transportation Bicycles Programming Linear programming Safety Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

A Modelling Approach for Coordinated Car Flow Assignment between Technical Stations Based on the Optimization of the Departure Mode Strategy

SSRN

引用

SSRN 2022年

作者： Xue, Feng Cheng, Daibing Yang, Zongqin Ma, Xiaochen Chen, Chongshuang School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China Transportation and Urban Planning Group Eindhoven University of Technology Eindhoven5612AZ Netherlands School of Mathematics Southwest Jiaotong University Chengdu611756 China

This study analysed the characteristics and departure conditions of different accumulation modes and design a freight train cooperative operation scheme between technical stations based on a hybrid accumulation mode. A coordinated freight train assignment model between technical stations is proposed with the objective function of minimizing the dwell time of cars at two technical stations. Considering the characteristics of the car flow connection problem, the standard grey wolf optimization algorithm coding method and individual location update formula are improved, and are used for optimization. The classification sequence and assignment plan of freight trains are obtained. The results of a case study show that the total dwell time of the vehicles at two technical stations has been reduced by 35.82 h, and the number of punctual outbound trains in the phase plan has been increased by two. The cooperative flow assignment improves the efficiency of the car flow organization compared with the single station flow assignment. © 2022, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Medical Image Classification: Advances, Challenges and Opportunities

SSRN

引用

SSRN 2023年

作者： Zhang, Xiaobo Zhao, Xiaole Wu, Yunyang Zheng, Hailong Li, Yang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Artificial Intelligence Research Institute Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

Medical images are private integrations comprising private patient information owned by various hospitals and relevant research institutes, and the generated image data can be utilized to infer physical health conditions. In recent years, more and more AI researchers have used medical images as datasets for their analysis purposes, which will cause relevant personnel to worry about their privacy. As a distributed machine learning framework, federated learning can effectively solve the problem of data privacy. It participates in and completes model training without sharing personal data, with strong universality and good results. In this work, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Wilhelm Conrad Röntgen (X-Ray) as well as other typical medical imaging modes are used as research objects to summarize, analyze and look forward to the previous work related to federal learning in the field of medical image analysis. On the one hand, this survey classifies and compares the existing federal learning framework and algorithm for different medical image datasets;on the other hand, it discusses the relevant federal studies that are widely used in medical images, analyses the problems that need to be solved in the field of medical images, and looks forward to future studies. © 2023, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Tseng Splitting Method with Double Inertial Steps for Solving Monotone Inclusion Problems

arXiv

引用

arXiv 2022年

作者： Wang, Zhong-Bao Lei, Zhen-Yin Long, Xin Chen, Zhang-You Department of Mathematics Southwest Jiaotong University Chengdu Sichuan611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu Sichuan611756 China School of Mathematical Sciences University of Electronic Science and Technology of China Chengdu Sichuan611731 China

In this paper, based on double inertial extrapolation steps strategy and relaxed techniques, we introduce a new Tseng splitting method with double inertial extrapolation steps and self-adaptive step sizes for solving monotone inclusion problems in real Hilbert spaces. Under mild and standard assumptions, we establish successively the weak convergence, nonasymptotic O(√1n) convergence rate, strong convergence and linear convergence rate of the proposed algorithm. Finally, several numerical experiments are provided to illustrate the performance and theoretical outcomes of our algorithm. © 2022, CC BY-NC-SA.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Road rage patterns in Nigeria: A multi-level latent class analysis

引用

Case Studies on Transport Policy 2025年 20卷

作者： Labbo, Muwaffaq Safiyanu Jiang, Xinguo Wada, Surajo Abubakar de Dieu, Gatesi Jean Bala, Nuhu D. Management Science and Engineering Post-Doctoral Research Station China Three Gorges University Yichang 443002 China Department of Civil Engineering Aliko Dangote University of Science and Technology Kano Wudil Nigeria School of Transportation and Logistics Southwest Jiaotong University West Park High-Tech District Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology West Park High-Tech District Chengdu 611756 China Department of Civil Engineering Ahmadu Bello University Kaduna State Zaria 810107 Nigeria

Road crashes remain a serious concern in Nigeria, and road user behavior is a significant contributing factor. This study explores the relationship between risky driving behaviors and emotional experiences among Nigerian drivers, with a specific focus on anger expression patterns and their association with anger-induced situations. Employing a nuanced approach through multilevel latent class analysis (MLCA), the research identifies three high-level groups and four low-level classes of drivers. Among the low-level classes, Easily Angered Drivers, Travel Impatience Drivers, Prudent Drivers, and Calm Drivers exhibit distinct characteristics, while the high-level groups encompass the Physical and Verbal anger expression group, the Anger Control group, and the Use of Vehicle to express anger group. Multinomial regression results reveal that male drivers are more likely to belong to the Physical and Verbal anger expression group, aligning with prior research. Travel Impatience Drivers demonstrate a tendency to express anger physically or verbally, especially amid travel-related frustrations. Easily Angered Drivers, particularly in younger age groups, are more likely to exhibit physical and verbal anger expression and vehicular aggression. This tendency may stem from deficiencies in driver training systems, which often fail to equip novice drivers with adequate emotional regulation strategies and conflict management skills on the road. Proposed interventions include improving driver training, rigorous traffic law enforcement, and public awareness campaigns to foster responsible driving. © 2025 World Conference on Transport Research Society

关键词： Anger Expression Anger Induced Situations Multi Level Latent Class Analysis Risky Driving Behavior Road Rage Road Safety

来源：评论

学校读者我要写书评

暂无评论

Exploring the Joint Choice Behaviour of Passengers with Potential Travel Tendency Under Metro Service Disruption

SSRN

引用

SSRN 2022年

作者： Zheng, Shuai Liu, Yugang Yi, Hongbo Liang, Yiliang Yang, Hongtai Xu, Yihe School of Transportation and Logistics Southwest Jiaotong University Sichuan Province Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Province Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Province Chengdu610031 China Institute of Transportation Development Strategy and Planning of Sichuan Province Sichuan Province Chengdu610000 China

Understanding the behaviour of passengers during metro disruption can help operators adopt remedial strategies. Passengers with potential travel tendencies will re-plan the departure time, trip-chaining, and travel modes after getting disruption information, limited in previous social behaviour studies. Innovatively, we conducted an offline questionnaire survey, set 12 scenarios, and considered the weather factors to collect the travel behaviour of residents in Chongqing, China fully. A cross-nested logit model is established to explore the joint choice tendency. The results show that when the utility changes, passengers will tend to change the structure of trip-chaining preferentially and choose immediate departure and simple trip-chaining during peak hours. Additionally, the elasticity analysis shows that passengers are more sensitive to the change of travel mode utility. This study helps urban planners and managers based on joint travel behaviour to adopt more effective strategies to maintain the service reliability and sustainable development of urban traffic systems. © 2022, The Authors. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Travel Joint Choice Behaviour of Potential Passengers Under Metro Disruption

SSRN

引用

SSRN 2022年

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via self-paced learning and low-redundant regularization

arXiv

引用

arXiv 2021年

作者： Li, Weiyi Chen, Hongmei Li, Tianrui Wan, Jihong Sang, Binbin School of Computing and Artificial Intelligence Southwest Jiaotong University China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China

Much more attention has been paid to unsupervised feature selection nowadays due to the emergence of massive unlabeled data. The distribution of samples and the latent effect of training a learning method using samples in more effective order need to be considered so as to improve the robustness of the method. Self-paced learning is an effective method considering the training order of samples. In this study, an unsupervised feature selection is proposed by integrating the framework of self-paced learning and subspace learning. Moreover, the local manifold structure is preserved and the redundancy of features is constrained by two regularization terms. L2,1/2-norm is applied to the projection matrix, which aims to retain discriminative features and further alleviate the effect of noise in the data. Then, an iterative method is presented to solve the optimization problem. The convergence of the method is proved theoretically and experimentally. The proposed method is compared with other state of the art algorithms on nine real-world datasets. The experimental results show that the proposed method can improve the performance of clustering methods and outperform other compared algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Railway Network Delay Evolution: A Heterogeneous Graph Neural Network Approach

arXiv

引用

arXiv 2023年

作者： Li, Zhongcan Huang, Ping Wen, Chao Rodrigues, Filipe National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu610031 China Kgs. Lyngby2800 Denmark Institute for Transport Planning and Systems ETH Zurich Zurich8093 Switzerland High-speed Railway Research Centre University of Waterloo WaterlooN2L3G1 Canada

Railway operations involve different types of entities (stations, trains, etc.), making the existing graph/network models with homogenous nodes (i.e., the same kind of nodes) incapable of capturing the interactions between the entities. This paper aims to develop a heterogeneous graph neural network (HetGNN) model, which can address different types of nodes (i.e., heterogeneous nodes), to investigate the train delay evolution on railway networks. To this end, a graph architecture combining the HetGNN model and the GraphSAGE homogeneous GNN (HomoGNN), called SAGE-Het, is proposed. The aim is to capture the interactions between trains, trains and stations, and stations and other stations on delay evolution based on different edges. In contrast to the traditional methods that require the inputs to have constant dimensions (e.g., in rectangular or grid-like arrays) or only allow homogeneous nodes in the graph, SAGE-Het allows for flexible inputs and heterogeneous nodes. The data from two sub-networks of the China railway network, namely the Guangzhou South network (GZS-Net) and the Changsha South network (CSS-Net), are applied to test the performance and robustness of the proposed SAGE-Het model. The experimental results show that SAGE-Het exhibits better performance than the existing delay prediction methods and some advanced HetGNNs used for other prediction tasks;the predictive performances of SAGE-Het under different prediction time horizons (10/20/30 min ahead) all outperform other baseline methods;the accuracies are over 90% under the permissible 3-minute errors for the three prediction time horizons. Specifically, the influences of train interactions on delay propagation are investigated based on the proposed model. The results show that train interactions become subtle when the train headways increase (e.g., when the train headways are over 20 min, canceling the edges does not decrease the prediction performance). This finding directly contributes to decision-ma

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Understanding the Long-Distance Travel Mobility of Passengers Based on big Railway data: Travel Network and Motif Perspectives

SSRN

引用

SSRN 2022年

作者： Xu, Jin Song, Haonan Lu, Zhaoyang Department of Information System & Operation Management School of Economics and Management Southwest Jiaotong University Sichuan Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Sichuan Chengdu China Service Science and Innovation Key Laboratory of Sichuan Province Sichuan Chengdu China

With the booming construction of new railway lines and stations in China, the number of railway passengers is increasing. The large railway population shows certain mobility characteristics that we are interested in clarifying. Based on the theory of complex networks, this paper proposes a novel method to identify travel patterns from big railway data, which associates travel motifs with travel networks. This paper derives some meaningful results from the data analysis of more than three million railway travel records of a city in China. These results illustrate that higher motif complexity leads to a narrower travel radius for motif-based subnets. The higher the stability of the travel sequence is, the shorter the average length of the sequence. Four types of travel patterns are identified and classified by analyzing the motif of travel activities, i.e., labor, tourism, surrounding and commuting. The methodology and findings presented in this paper contribute to a better understanding of the long-distance travel mobility of railway passengers. The method designed in this paper can also be used to analyze traffic data from airlines, buses, subways, etc. © 2022, The Authors. All rights reserved.

关键词： Complex 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：