Search

Your search keyword '"Zeng,Weiliang"' showing total 30 results
Start Over Author "Zeng,Weiliang" Publisher elsevier bv
30 results on '"Zeng,Weiliang"'

10. Clinical characteristics, tolerance mechanisms, and molecular epidemiology of reduced susceptibility to chlorhexidine among Pseudomonas aeruginosa isolated from a teaching hospital in China

Author

Zheng, Xiangkuo, primary, Zhang, Xiaoya, additional, Zhou, Beibei, additional, Liu, Shixing, additional, Chen, Weifeng, additional, Chen, Liqiong, additional, Zhang, Ying, additional, Liao, Wenli, additional, Zeng, Weiliang, additional, Wu, Qing, additional, Xu, Chunquan, additional, and Zhou, Tieli, additional

Published
2022
Full Text
View/download PDF

19. A deep learning framework for modelling left-turning vehicle behaviour considering diagonal-crossing motorcycle conflicts at mixed-flow intersections

Author

Chen Yihao, Zhaoshui He, Yao Ruoyu, and Zeng Weiliang

Subjects
Computer science, business.industry, Deep learning, Pooling, Transportation, Management Science and Operations Research, computer.software_genre, Motion (physics), Probabilistic method, Automotive Engineering, Trajectory, Feature (machine learning), Graph (abstract data type), Data mining, Motion planning, Artificial intelligence, business, computer, Civil and Structural Engineering
Abstract

With heterogeneous traffic agents moving at unprotected phase, severe crossing conflicts are witnessed at mixed-flow intersections, especially when left-turning vehicles are confronted with motorcycles. However, for modelling vehicle turning behaviour, potential conflicts involving diagonal-crossing motorcycles are seldom investigated in existing studies. To explore these scenes, we present a novel interaction-aware deep-learning framework. Firstly, a Long Short-Term Memory (LSTM) based network is employed to encode vehicle historical motion features. Secondly, each vehicle’s potential target lanes are identified with a probabilistic method, followed by a pooling module that extracts and summarizes intention features. Thirdly, Graph Attention Network (GAT) and a synthesized network are introduced to model vehicle-vehicle interaction and vehicle-motorcycle interaction respectively. Finally, multiple kinds of obtained features are sent to a LSTM based decoder module, where both future displacement and body orientation of vehicles are predicted. In short-time simulation experiments, average displacement error is reduced by 47.7% and 20.0% compared to baseline and state-of-the-art methods, with ablation studies conducted to quantify the efficacy of each kind of feature. Moreover, regarding recursive simulation, our model shows availability of reproducing lane-selecting and motorcycle-evasive behaviours. Distributions of post-encroachment time further indicate that the proposed framework can serve as a promising method to realize reliable motion planning for autonomous vehicles.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results