检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zang, Di Wei, Chenguang Zhao, Jiayi Zhang, Junqi Tang, Keshuang Zhu, Hong Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science and Technology Tongji University No. 4800 Cao’an Road Shanghai200092 China Key Laboratory of Road and Traffic Engineering Ministry of Education College of Transportation Engineering Tongji University No. 4800 Cao’an Road Shanghai200092 China

The ability of road networks to withstand external disturbances is a crucial measure of transportation system performance, where resilience distinctly emerges as an effective perspective for its unique insights into the system's resistance and recovery capabilities. In the face of unforeseen resilience disturbance events, predictive and accurate assessment of road network resilience is essential for better traffic regulation and emergency response management. However, existing resilience assessment methods of road networks are insufficient: they lack reliable real-time big-data analysis, do not possess predictive capabilities for guiding decision-making, and have a narrow view with single-dimensional resilience indicators. To address these issues, focusing on rainfall disturbance scenarios, this work introduces a novel resilience assessment method, which is predictive and real-time, consisting of two components: a traffic indicator prediction model and a comprehensive resilience assessment model. Firstly, we propose a two-stage traffic indicator prediction model, namely the Conditional Diffusion-Reconstruction-based Graph Neural Network (CDRGNN), which particularly enhances disturbance-scenario prediction accuracy, thereby providing reliable foresight in aid of the following assessments. Subsequently, we develop a resilience assessment model featuring structural-functional comprehensive resilience indicators established on the shortest-path aggregation, and the overall resilience assessment is performed through comparative analysis using indicators obtained in real time with historical non-disruptive resilience benchmarks. In a case study focusing on heavy rainfall disturbances on a road network in California, USA, abundant experiments and visualizations are conducted to demonstrate the rationality of our proposed comprehensive resilience indicators as well as the precision and reliability of these predictive resilience assessment outcomes. © 2024, The Authors. All

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Predictive Resilience Assessment Featuring Diffusion Reconstruction for road Networks Under Rainfall Disturbances

SSRN

引用

SSRN 2024年

The ability of road networks to withstand external disturbances is a crucial measure of transportation system performance, where resilience distinctly emerges as an effective perspective for its unique insights into the system's resistance and recovery capabilities. In the face of unforeseen resilience disturbance events, predictive and accurate assessment of road network resilience is essential for better traffic regulation and emergency response management. However, existing resilience assessment methods of road networks are insufficient: they lack reliable real-time big-data analysis, do not possess predictive capabilities for guiding decision-making, and have a narrow view with single-dimensional resilience indicators. To address these issues, focusing on rainfall disturbance scenarios, this work introduces a novel resilience assessment method, which is predictive and real-time, consisting of two components: a deep learning traffic indicator prediction model and a comprehensive resilience assessment model. Firstly, we propose a two-stage traffic indicator prediction model, namely the Conditional Diffusion-Reconstruction-based Graph Neural Network (CDRGNN), which particularly enhances disturbance-scenario prediction accuracy, thereby providing reliable foresight in aid of the following assessments. Subsequently, we develop a resilience assessment model featuring structural-functional comprehensive resilience indicators established through shortest-path aggregation, and the overall resilience assessment is performed through comparative analysis using indicators obtained in real-time with historical non-disruptive resilience benchmarks. In a case study focusing on heavy rainfall disturbances on a road network in California, the United States, abundant experiments and visualizations are conducted to demonstrate the rationality of our proposed comprehensive resilience indicators as well as the precision and reliability of these predictive resilience assessment outcom

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Decision-making Framework

arXiv

引用

arXiv 2024年

作者： Xu, Chengkai Deng, Zihao Liu, Jiaqi Kong, Aijing Huang, Chao Hang, Peng The Department of Traffic Engineering Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji University Shanghai201804 China The Department of Traffic Engineering Tongji University Shanghai201804 China The State Key Lab of Intelligent Transportation System Beijing100088 China Department of Industrial and System Engineering The Hong Kong Polytechnical University 999077 Hong Kong

In hybrid traffic environments where human-driven vehicles (HDVs) and autonomous vehicles (AVs) coexist, achieving safe and robust decision-making for AV platooning remains a complex challenge. Existing platooning systems often struggle with dynamic formation management and adaptability, especially in unpredictable, mixed-traffic conditions. To enhance autonomous vehicle platooning within these hybrid environments, this paper presents TriCoD, a twin-world safety-enhanced Data-Model-Knowledge Triple-Driven Cooperative Decision-making Framework. This framework integrates deep reinforcement learning (DRL) with model-driven approaches, enabling dynamic formation dissolution and reconfiguration through a safety-prioritized twin-world deduction mechanism. The DRL component augments traditional model-driven methods, enhancing both safety and operational efficiency, especially under emergency conditions. Additionally, an adaptive switching mechanism allows the system to seamlessly shift between data-driven and model-driven strategies based on real-time traffic demands, thereby optimizing decision-making ability and adaptability. Simulation experiments and hardware-in-the-loop tests demonstrate that the proposed framework significantly improves safety, robustness, and flexibility. A detailed account of the validation results for the model can be found in Our Website. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Dynamic Modulus of Asphalt Mixtures Based on Sparrow Search Algorithm Optimized Light Gradient Boosting Machine

SSRN

引用

SSRN 2023年

作者： Zhang, Ke Min, Zhaohui Hao, Xiatong Huang, Wei Henning, Theunis F.P. Intelligent Transportation System Research Center Southeast University Southeast University Road #2 Nanjing211189 China School of Transportation Southeast University Southeast University Road #2 Nanjing211189 China Nanjing Modern Multimodal Transportation Laboratory Baoshansi Road #56 Nanjing211100 China Department of Civil and Environmental Engineering University of Auckland Private Bag 92019 Auckland1142 New Zealand

The dynamic modulus of asphalt mixture is a key parameter to evaluate its viscoelastic and fatigue performance. This parameter can be determined by laboratory measurements or model forecasting. The utilization of prediction models offers an efficient alternative that can avoid time-taking experiments. Therefore, it is very important to accurately predict the dynamic modulus. This study aims to propose a prediction model with high accuracy, robustness and interpretability considering the hyper-parameter optimization. A new hybrid model is developed combining the Sparrow Search Algorithm (SSA) and Light Gradient Boosting Machine (LightGBM). The input variables are evaluated using the Pearson Correlation Coefficient (PCC). The accuracy and robustness of the prediction model are accessed. And relative significance analysis is conducted to measure the effect of input parameters on dynamic modulus prediction. The research findings indicate that the SSA-LightGBM has the best precision and robustness in dynamic modulus prediction compared with the previous regression and machine learning models. The asphalt binder type is very important for dynamic modulus prediction. The complex shear modulus is found to be the most critical feature for predicting dynamic modulus, followed by test temperature, binder viscosity, performance grade (PG) at high temperature, and performance grade (PG) at low temperature. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Geometric Optimization of Patterned Conductive Polymer Composite-based Strain Sensors Toward Enhanced Sensing Performance

arXiv

引用

arXiv 2025年

作者： Shang, Jia-Chen School of Transportation Science and Engineering Beihang University 37 Xueyuan Road Haidian District Beijing100191 China Beijing Key Laboratory for High-efficient Power Transmission and System Control of New Energy Resource Vehicle Beijing100191 China

The patterned design of flexible sensors enables customized performance to meet diverse application demands. However, when multiple geometric parameters and sensing metrics are involved, experimental approaches to establish structure-performance relationships become costly and inefficient. Here, a novel universal piezoresistive model—overcoming limitations of commonly used models that are only applicable to small strains and linear responses—is developed to capture the relationship between conductivity tensor components and strain. A numerical method incorporating this model simulates the electromechanical properties of conductive composites and predicts patterned strain sensors behavior. To validate this approach, a flexible strain sensor based on laser-induced graphene technology is fabricated and tested. Additionally, a rapid, cost-effective workflow combining Latin hypercube sampling and Pareto-optimal solutions is demonstrated for multi-parameter and multiobjective optimization of the sinusoidal-patterned sensor. This study provides valuable insights for investigating the structure-performance relationship of strain sensors and advances optimization methods for sensor designs. Copyright © 2025, The Authors. All rights reserved.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Research on modelling and simulation of single-mode power split hybrid system

引用

International Journal of Vehicle Performance 2021年第3-4期7卷 279-302页

作者： Chu, Aihua Yuan, Yinnan Chen, Xiang Tong, Zhang Geng, Wenran Cheng, Huijun School of Automotive and Traffic Engineering Jiangsu University 301 Xuefu Road Jingkou District Zhenjiang21203 China School of Rail Transportation Soochow University 8 Jixue Road Xiangcheng District Suzhou215131 China Corun Hybrid System Technology Co. LTD. 2888 Wanfeng Road Fengjing Industrial Park Jinshan District Shanghai201501 China

Aiming at an optimised single-mode compound power split hybrid system, the main operating mode of the hybrid system and the torque control strategy were developed in this paper. LMS/AMESim was used to establish the plant model of the vehicle as well as the key components of the hybrid system, while the vehicle control model was established in Matlab/Simulink. In addition, the fuel economy of a certain SUV under the NEDC road spectrum was simulated by the co-simulation model, and the simulation results were compared with the experimental results on the auto chassis dynamometer. The results demonstrated that the established simulation model is an accurate reflection of the physical reality under different road spectrum conditions. Application of the model can greatly reduce the difficulty of control strategy design and improve the efficiency of vehicle development. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Leveraging Big Data Technologies for Economic Growth in the Digital Era

Leveraging Big Data Technologies for Economic Growth in the ...

引用

Creative Communication and Innovative Technology (ICCIT), IEEE

作者： Mardiana Joko Siswanto Muhammad Farhan Kamil Bintang Nandana Henry Ahmad Ramadan Maulana Arif Komara Faculty of Accountancy University of Raharja Tangerang Indonesia Road Transportation System Engineering Polytechnic of Road Transportation Safety Tegal Indonesia Faculty of Digital Business Kreatif Desain Tangerang Indonesia Faculty of Information Technology Kreatif Desain Tangerang Indonesia Faculty of Information Technology Pandawan Sejahtera Indonesia Tangerang Indonesia Faculty of Digital Business CAI Sejahtera Indonesia Tangerang Indonesia

ISBN: (数字)9798350367492

ISBN: (纸本)9798350367508

The digital economy is undergoing rapid transformation driven by the widespread adoption of Big Data technologies, significantly influencing various sectors including retail, finance, and manufacturing. The background of this study explores the impact of Big Data technologies on enhancing profitability and efficiency in these sectors through personalized customer service and predictive analytics. The research objective is to provide a comprehensive review of current literature and case studies to analyze the role of standardized data exchanges and a common definition of Big Data in facilitating industry-wide integration. The method employed in this study involves a systematic literature review and analysis of case studies to evaluate the implementation and impact of Big Data technologies. The results indicate that implementing Big Data technologies leads to improved operational efficiency, significant cost reductions, and enhanced customer experiences. However, challenges such as data privacy concerns, integration complexities, and skill shortages need to be addressed. The conclusion of this study suggests that adopting standardized data governance frameworks, investing in skill development, and leveraging scalable technologies are essential for maximizing the potential of Big Data technologies. These measures are crucial for navigating data-driven environments and promoting sustainable economic growth and innovation.

关键词： Technological innovation Protocols Profitability Navigation Customer services Collaboration Big Data Predictive analytics Standards Business

来源：评论

学校读者我要写书评

暂无评论

Integrating Evaluation, Optimization, and Solution of Network Signal Control: A Multi-Agent-Based Path-Level Coordination Model

SSRN

引用

SSRN 2024年

作者： Yao, Jiarong Tan, Chaopeng Wu, Hao Cao, Yumin Tang, Keshuang Li, Fuliang School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Department of Transport and Planning Delft University of Technology Gebouw 23 Stevinweg 1 Delft2628 CN Netherlands The Key Laboratory of Road and Traffic Engineering The Ministry of Education College of Transportation Engineering Tongji University No. 4800 Cao’an road Shanghai201804 China Singapore Guangdong Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-sen University No. 135 Xingang Xi Road Guangzhou510275 China

road network signal coordination helps boost traffic progression efficiency and is significant for urban traffic control and management. However, current fixed-time network signal coordination, mainly realized by control subarea partitioning, fails to describe the intrinsic property of urbanite trip reflected by vehicle paths, while some path-based road network signal coordination methods depend strongly on so-called critical paths derived from subjective experience. Therefore, a multi-agent path-based coordination (MAPC) model is proposed to simultaneously determine critical paths and enable signal coordination, which tackles the drawback of segregation between control and evaluation in existing studies. Under a multi-agent control framework, a concept of all-way movement path-unit intersection cluster (AMPIC) is introduced as the agent in a network coordination system, considering the control efficiency correlation of paths interacting within intersections. Aiming at delay minimization, the MAPC model realizes network coordination through self-optimization of AMPIC agents and an optimization iterator that coordinates the traffic progression between neighboring agents. In this way, the network coordination problem is transformed into a separable nonconvex optimization problem, which is solved by an alternating direction method of multipliers (ADMM) with path searching to fulfill the optimization iteration across the network. Evaluation was done through a simulation case of real-world network calibrated by empirical data. Through horizontal comparison with the Synchro model and the MULTIBAND model. Results showed that the MAPC model considerably outperformed by more than 35.8% and 22.3% in average vehicular delay and number of stops, with accurate identification of the dominating path flows needed coordination within the network. © 2024, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

arXiv

引用

arXiv 2024年

作者： Liu, Jiaqi Hang, Peng Na, Xiaoxiang Huang, Chao Sun, Jian The College of Transportation Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji University Shanghai201804 China The Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Department of Industrial and System Engineering The Hong Kong Polytechnical University 999077 Hong Kong

The development of autonomous vehicles has shown great potential to enhance the efficiency and safety of transportation systems. However, the decision-making issue in complex human-machine mixed traffic scenarios, such as unsignalized intersections, remains a challenge for autonomous vehicles. While reinforcement learning (RL) has been used to solve complex decision-making problems, existing RL methods still have limitations in dealing with cooperative decision-making of multiple connected autonomous vehicles (CAVs), ensuring safety during exploration, and simulating realistic human driver behaviors. In this paper, a novel and efficient algorithm, Multi-Agent Game-prior Attention Deep Deterministic Policy Gradient (MA-GA-DDPG), is proposed to address these limitations. Our proposed algorithm formulates the decision-making problem of CAVs at unsignalized intersections as a decentralized multi-agent reinforcement learning problem and incorporates an attention mechanism to capture interaction dependencies between ego CAV and other agents. The attention weights between the ego vehicle and other agents are then used to screen interaction objects and obtain prior hierarchical game relations, based on which a safety inspector module is designed to improve the traffic safety. Furthermore, both simulation and hardware-in-the-loop experiments were conducted, demonstrating that our method outperforms other baseline approaches in terms of driving safety, efficiency, and comfort. Copyright © 2024, 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

Number of road Accidents Predicting Using Deep Learning-Based LSTM Development Models

Number of Road Accidents Predicting Using Deep Learning-Base...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Joko Siswanto Hendry Untung Rahardja Irwan Sembiring Kristoko Dwi Hartomo Hindriyanto Dwi Purnomo Ade Iriani Road Transportation System Engineering Politeknik Keselamatan Transportasi Jalan Tegal Indonesia Faculty of Information Technology Satya Wacana Christian University Salatiga Indonesia Faculty of Science and Technology University of Raharja Tangerang Indonesia

road accidents cause chaos and state financial losses every year. road accidents cannot be stopped but can be controlled with predictions. The existing road accident prediction model accuracy for the medium and long term still has many discrepancies, and it is rarely done. A comparison of the deep learning algorithms of the LSTM, Bi-LSTM, ConvLSTM, and Att-LSTM models with hidden layer variations is used to select the suitable model to make predictions. Use data from the road accident dataset in Thailand in 2011-2022, which can be accessed freely on Kaggle. The results show that the BiLSTM model with 4 hidden layers can predict the number of road accidents in the medium and long term with the highest accuracy. MSLE is used to measure the accuracy of the model with variations without hidden layers, 2 hidden layers, and 4 hidden layers to find the best model for predicting the number of road accidents for the medium and long term.

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：