Summary
Smart Info-Media Systems in Asia
2019
Session Number:SS2
Session:
Number:SS2-1
Traffic Flow State Prediction Based on Deep Learning - Taking Hohhot as an Example
Jiaqi Zhang, Hongye Yang, Shuchen Gao, Zituo Li,
pp.24-28
Publication Date:2019/9/4
Online ISSN:2188-5079
DOI:10.34385/proc.57.SS2-1
PDF download (1.1MB)
Summary:
Traffic flow prediction is an important part of a smart city. With the continuous development of machine learning and artificial intelligence, it has been widely used in the field of traffic engineering. This paper chooses the Gated Recurrent Unit model as the research object based on the bus GPS data of Hohhot. Through the comparative analysis with LSTM model, the results show that GRU model has better prediction performance than LSTM model in traffic state prediction.