Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data.
Zhuoning YuanXun ZhouTianbao YangPublished in: KDD (2018)
Keyphrases
- deep learning
- spatio temporal data
- traffic accidents
- spatio temporal
- unsupervised learning
- spatial data
- sensor data
- spatial databases
- databases
- traffic flow
- scientific data
- wireless sensor networks
- image features
- moving objects
- weakly supervised
- three dimensional
- mental models
- countermeasures
- computer vision
- machine learning