Traffic Flow Prediction Based on BRNN
- Resource Type
- Conference
- Authors
- Bohan, Huang; Yun, Bai
- Source
- 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC) Electronics Information and Emergency Communication (ICEIEC0, 2019 IEEE 9th International Conference on. :320-323 Jul, 2019
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Engineering Profession
Robotics and Control Systems
Predictive models
Logic gates
Recurrent neural networks
Data models
Global Positioning System
Deep learning
traffic flow prediction
BRNN
deep learning
GPS data
- Language
- ISSN
- 2377-844X
Accurate and real-time traffic flow prediction plays an important role in building intelligent transportation systems and traffic control and induction. As traffic flow data is mostly time series data, selecting a bidirectional recurrent neural network (BRNN) model in a recurrent neural network (RNN) that is good at processing time series data for speed prediction, comparing with long short term memory (LSTM) model and gated recurrent unit (GRU) model. The results show that BRNN has better prediction performance than the other two models.