Search

Your search keyword '"Lu, Jian"' showing total 553 results
Start Over Author "Lu, Jian" Publisher ieee
553 results on '"Lu, Jian"'

19. A Context-Aware Framework for Risky Driving Behavior Evaluation Based on Trajectory Data.

Author

Xue, Qingwen, Gao, Kun, Xing, Yingying, Lu, Jian, and Qu, Xiaobo

Abstract

Risky driving behaviors are one of the key contributors to traffic accidents. The rapid and accurate identification of them is important to improve the safety of the driving environment. This study introduces a context-aware framework for the evaluation of risky driving behaviors based on trajectory data. It consists of three models to identify the context, determine risky maneuvers, and evaluate risky driving behaviors. We first propose a surrogate-based method to label risky maneuvers considering context factors. Then, the features of driving trajectories are extracted as the input features for the evaluation of risky behavior. Based on the labeling result and maneuver features, supervised machine learning algorithms are leveraged to model their relationships for evaluations. Three feature extraction methods and five classifiers are compared in this article to select the most suitable one. Last, a context-aware evaluation framework is proposed to recognize risky driving behaviors incorporating context. The trajectory data extracted from unmanned aerial vehicles are used to validate the proposed framework. The results show that the accuracy of risky driving behaviors evaluation could reach 97%. The proposed framework in this study can effectively evaluate risky driving behaviors based on trajectory data with the consideration of context factors. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

32. Auditing Network Embedding: An Edge Influence Based Approach.

Author

Wang, Yaojing, Yao, Yuan, Tong, Hanghang, Xu, Feng, and Lu, Jian

Subjects
VIRTUAL networks, AUDITING
Abstract

Learning node representations in a network has a wide range of applications. Most of the existing work focuses on improving the performance of the learned node representations by designing advanced network embedding models. In contrast to these work, this article aims to provide some understanding of the rationale behind the existing network embedding models, e.g., why a given embedding algorithm outputs the specific node representations and how the resulting node representations relate to the structure of the input network. In particular, we propose to discern the edge influence for two widely-studied classes of network embedding models, i.e., skip-gram based models and graph neural networks. We provide algorithms to effectively and efficiently quantify the edge influence on node representations, and further identify high-influential edges by exploiting the linkage between edge influence and network structure. Experimental evaluations are conducted on real datasets showing that: 1) in terms of quantifying edge influence, the proposed method is significantly faster (up to $2,000\times$ 2 , 000 × ) than straightforward methods with little quality loss, and 2) in terms of identifying high-influential edges, the identified edges by the proposed method have a significant impact in the context of downstream prediction task and adversarial attacking. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

43. Crash Risks Evaluation of Urban Expressways: A Case Study in Shanghai.

Author

Cheng, Zeyang, Yuan, Jinghui, Yu, Bo, Lu, Jian, and Zhao, Yi

Abstract

Proactive traffic safety management systems can reduce crashes by identifying crash precursors, evaluating real-time crash risks, and implementing suitable interventions. The basic prerequisite for developing such a system is to propose a reliable crash risk evaluation model that takes real-time traffic flow data as input. Previous studies have primarily focused on real-time crash prediction using some statistical or machine-learning methods. However, further quantitative evaluation and classification of crash risks have been ignored. In this study, we conduct a systematic crash risk evaluation workflow, including crash risk prediction, crash risk quantification, and crash risk classification. Specifically, the crash risk prediction using an extended logit model is proposed, from which CAS, CSD, UAS, DAS, DTV are identified to be contributing factors of crash risks. Then a crash risk quantification model based on the parameter evaluation of the extended logit model is developed. The crash risks of urban expressways and their spatial-temporal evolution trends are quantified. Finally, the crash risks are classified into high crash risk level, moderate crash risk level, and low crash risk level by the k-means cluster algorithm. Then the threshold boundaries of different crash risk levels are determined. The research results provide a proactive guidance for traffic safety management of urban expressways. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results