检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

arXiv

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

Driver-Specific Risk Recognition in Interactive Driving Scenarios using Graph Representation

学校读者我要写书评

暂无评论

arXiv

arXiv 2021年

作者： Li, Jinghang Lu, Chao Li, Penghui Zhang, Zheyu Gong, Cheng Gong, Jianwei School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Key Laboratory of Transport Industry of Big Data Appli cation Technologies for Comprehensive Transport the School of Traffic and Transportation Beijing Jiaotong University China

This paper presents a driver-specific risk recognition framework for autonomous vehicles that can extract inter-vehicle interactions. This extraction is carried out for urban driving scenarios in a driver-cognitive manner to improve the recognition accuracy of risky scenes. First, clustering analysis is applied to the operation data of drivers for learning the subjective assessment of risky scenes of different drivers and generating the corresponding risk label for each scene. Second, the graph representation model (GRM) is adopted to unify and construct the features of dynamic vehicles, inter-vehicle interactions and static traffic markings in real driving scenes into graphs. The driver-specific risk label provides ground truth to capture the risk evaluation criteria of different drivers. In addition, the graph model represents multiple features of the driving scenes. Therefore, the proposed framework can learn the risk-evaluating pattern of driving scenes of different drivers and establish driver-specific risk identifiers. Last, the performance of the proposed framework is evaluated via experiments conducted using real-world urban driving datasets collected by multiple drivers. The results show that the risks and their levels in real driving environments can be accurately recognized by the proposed framework. Copyright © 2021, The Authors. All rights reserved.

关键词： Risk assessment

Stvanet: A Spatio-Temporal Visual Attention Framework with Large Kernel Attention Mechanism for Citywide Traffic Dynamics Prediction

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Yang, Hongtai Jiang, Junbo Zhao, Zhan Pan, Renbin School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Institute of System Science and Engineering Southwest Jiaotong University Chengdu611756 China Department of Urban Planning and Design The University of Hong Kong Hong Kong Special Administrative Region Hong Kong School of Business Administration Southwestern University of Finance and Economics Chengdu611130 China

Enhancing the efficiency and safety of the Intelligent transportation System requires effective modeling and prediction of citywide traffic dynamics. Most studies employ convolutional neural networks (CNNs) with a 3D convolutional structure or spatio-temporal models with self-attention mechanisms to capture the spatio-temporal information of traffic distribution. Although 3D CNNs excel at capturing local contextual information, they are computationally complex due to the large number of parameters and cannot capture long-range dependence. By contrast, although self-attention mechanisms originally designed to address challenges in natural language processing can capture long-range dependence, their application to 2D image structures requires breaking down the inherent 2D context into a 1D sequence, increasing the computational complexity and neglecting the adaptability between local contextual information and channels. Accordingly, we propose a spatio-temporal visual attention neural network (STVANet), a novel spatio-temporal visual attention 2D CNN, which integrates a unique visual attention module with a large kernel attention (LKA) mechanism and a feedforward component to capture long-range dependence and channel information in urban traffic data while preserving the 2D image structure. LKA-based spatio-temporal attention networks extract spatial and temporal features from weekly, daily, and recent hourly periods, and aggregate them with weighted consideration of external features to make predictions. Evaluation of real-world datasets demonstrates STVANet’s superiority over baseline models, showcasing its potential in citywide traffic prediction. © 2023, The Authors. All rights reserved.

关键词： Convolution

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

SSRN 2022年

关键词： Urban transportation

Simulation of Toll Lane Capacity of Highway Toll Station

学校读者我要写书评

暂无评论

Simulation of Toll Lane Capacity of Highway Toll Station

IEEE International Conference on Intelligent transportation engineering (ICITE)

作者： Lei Wang Peng Wang Jiandong Zhao School of Traffic and Transportation Beijing Jiaotong University Beijing China School of Mechanical and Electronic Control Engineering Beijing Jiaotong University Beijing China School of Traffic and Transportation Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing China

ISBN: (数字)9781728194097

ISBN: (纸本)9781728194103

Toll stations are important facilities for highway transportation. There are many current charging methods, and traditional capacity calculations are based on a single charging method. As the service time of each charging method is different, the capacity of toll stations will be affected. Therefore, it is necessary to determine the capacity under a variety of charging methods. In this paper, a simulation model of toll station is established based on VISSIM simulation software, and then a simulation study is conducted on the lane capacity of various charging methods. The results show that the longer the service time, the lower the capacity of the charging method. The capacity of the lane using the mobile QR code is the smallest, and the higher the proportion of users who pay by the QR code, the smaller the lane capacity. The study provides a reference for the calculation of toll capacity.

关键词： Solid modeling Analytical models Credit cards Software Roads transportation Simulation

Cooperative Ramp Merging in Mixed Traffic: Hybrid Model Predictive Control and Real Time Computations

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Sun, Zhanbo Gao, Ziyan Li, Zheyi Huang, Tianyu School of Transportation and Logistics Southwest Jiaotong University China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China Intelligent autonomous vehicle group Sensetime Shanghai China Department of Civil and Environmental Engineering Carnegie Mellon University United States Civil Aviation Flight University of China China

This paper focuses on the problem of decision making in mixed traffic with conventional human-operated vehicles (HVs) and connected automated vehicles (CAVs). To better handle the stochasticity in HV behaviors, the paper applies a closed-loop optimal control approach to extend the previously developed deterministic cooperative decision-making framework for mixed traffic (Deterministic-CDMMT). The proposed framework is illustrated using a ramp merging example. This framework can be described as an optimization problem in which a merge sequencing problem and a trajectory planning problem are embedded and solved by a bi-level hybrid centralized-decentralized model predictive control (HMPC) approach. The upper-level merge sequencing problem is solved using a dynamic-programming-based approach. Considering real-time computational performance, three solution methods, including dynamic programming (DP), dynamic matrix predictive control (DMC), and simplified discrete control (SDC), are developed to solve the lower-level trajectory planning problem. Simulation results show that compared to open-loop control, the proposed framework can effectively address the uncertainty caused by the stochastic driving behaviors of HVs. In addition, it is found that hybrid centralized-decentralized control can reduce the computational time to the millisecond-level and provide a similar, system-efficient performance compared to centralized control, potentially meeting real-time computational requirements. © 2023, The Authors. All rights reserved.

关键词： Model predictive control

A-Map: Interactive Visual Exploration of Intercity Accessibility Dynamics Based on Railway Network data

学校读者我要写书评

暂无评论

A-Map: Interactive Visual Exploration of Intercity Accessibi...

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Kaichen Nie Hanning Shao Yuchu Luo Min Tian Hao Wu Wei Zeng Xin Fu Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) School of AI Peking University Hong Kong University of Science and Technology Guangzhou Chang’an University National Engineering Laboratory for Big Data Analysis and Application Peking University

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Railway transportation is closely linked to everyday lives while also aiding domain experts in analyzing national or regional development. However, discrepancies between travel time reduced by railways and actual distance pose challenges in visualizing the accessibility. Existing methods either struggle to simultaneously depict the accessibility relationships among all cities or disregard genuine geographical positions, leading to spatial cognitive confusion. In this work, we propose a novel approach to balance between the geographical positions and travel time between cities. We construct linear cartograms to represent accessibility while preserving better local railway network structures compared with existing methods. We further propose the A-Map system, enabling users to interactively explore the extensive development of China’s railway system over decades. We validate the effectiveness of our proposed layout algorithm from qualitative metric evaluation and illustrate the applicability of our system with results.

关键词： Measurement Visualization Heuristic algorithms Urban areas Layout transportation data visualization

Dynamic OD Prediction for Urban Networks Based on Automatic Number Plate Recognition data: Paramertic vs. Non-parametric Approaches

学校读者我要写书评

暂无评论

Dynamic OD Prediction for Urban Networks Based on Automatic ...

International Conference on Intelligent transportation

作者： Fangfang Zheng Jing Liu Henk van Zuylen Kun Wang Xaobo Liu Jie Li School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University P.R. China School of Transportation and Logistics Southwest Jiaotong University P.R. China Department of Transport and Planning Delft University of Technology Delft the Netherlands Civil Engineering College Hunan University Changsha Hunan Province P.R. China

OD flows provide important information for traffic management and planning. In this paper, we propose four OD prediction models based on the data obtained by Automated Number Plate Recognition (ANPR) cameras. The principal component analysis (PCA) is applied to reduce the dimension of the original OD matrices and to separate the main structure patterns from the noisier components. A state-space model is established for the main structure patterns and the structure deviations, and is incorporated in the Kalman filter framework to make prediction. We further develop three K- Nearest Neighbor (K-NN) based pattern recognition approaches. The proposed four approaches are validated with three days' field ANPR data from Changsha city, P.R. China. The results show that on one hand our proposed approaches are able to make accurate prediction of OD flows under different demand conditions. On the other hand, the prediction accuracy is highly dependent on the quality of the available OD data: the Kalman filter model performs better for regular and periodic OD patterns; while for irregular OD matrices K-NN models could make more accurate prediction.

关键词： Predictive models Principal component analysis Mathematical model data models Kalman filters Market research Covariance matrices