Chen Fei
5 Papers
2 Citations
Chen Fei is an academic researcher. The author has contributed to research in topics: Graph (abstract data type) & Warning system. The author has an hindex of 2, co-authored 5 publications.
Chat about Author
Papers
Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction
Chen Ken,Chen Fei,Baisheng Lai,Zhongming Jin,Yong Liu,Li Kai,Long Wei,Pengfei Wang,Tang Yandong,Jianqiang Huang,Xian-Sheng Hua +10 more
TL;DR: DST-GCNN is a two stream network that learns expressive features to represent spatio-temporal structures and predicts future traffic flows from surveillance video data and achieves competitive performances compared with the other state-of-the-art methods.
54
•Posted Content
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
Chen Ken,Chen Fei,Baisheng Lai,Zhongming Jin,Yong Liu,Li Kai,Long Wei,Pengfei Wang,Tang Yandong,Jianqiang Huang,Xian-Sheng Hua +10 more
TL;DR: This paper presents dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio,temporal structures and predict future traffic flows from surveillance video data using a two stream network.
An Early Warning Method for Highway Traffic Accidents Based on Bayesian Networks
Chen Ken,Chen Fei,Li Kai,Liu Juexiong,Fengli Zhang,Lin Mei,Jiayi Zhai +6 more
- 12 Jul 2019
TL;DR: The experimental results show that the proposed early warning method for highway traffic accident based on Bayesian network has higher accuracy in early warning of accidents and the temporal distribution of prediction results is consistent with the peak season.
4
An Algorithm-optimized Car-following Model Based on Chengdu Ring Expressway Traffic Flow Characteristics
TL;DR: An algorithm-optimized car-following model is presented to describe the overall effect on the Chengdu ring expressway in China from May to October, 2019, based on dynamic data observed from the intelligent transportation system.
Patent
Monitoring and early warning method for safety risk of highways
TL;DR: In this article, a monitoring and early warning method for safety risk of highways is proposed, which comprises the following steps: S1: dividing a mountain into a plurality of monitoring layers based on stratification of rock/soil layers, pre-embedding a number of monitoring units in each of the monitoring layers along a direction of stratification for measuring a pressure variable of monitoring layer; S2: fixing a pluralityof GNSS earth surface displacement monitors to the same monitoring layer.