Awesome

Codes-for-RiskSeq-TKDE

Thank you for your interests in our work!

The dataset we ultilized for training and testing for NYC is reposited in BaiduYun.

Address: https://pan.baidu.com/s/1_lMpaY7bfkkAIPbmJyRCsw Extraction Codes: 67tu.

For the contract of SIP dataset, we apologize for its temporal unavailability due to the contract.

You can download this notebook as well as the well-organized dataset for training and testing. The toy example for visualization is in AAAI2020-RiskOracle Respository. If you find this work interesting and helpful to your work, please find the citation of these two papers (AAAI and TKDE) as below. Thank you very much. Any question you can email to zzy0929@mail.ustc.edu.cn

@article{zhou2020foresee, title={Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective}, author={Zhou, Zhengyang and Wang, Yang and Xie, Xike and Chen, Lianliang and Zhu, Chaochao}, journal={IEEE Transactions on Knowledge and Data Engineering}, year={2020}, publisher={IEEE} }

@inproceedings{zhou2020riskoracle, title={RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework}, author={Zhou, Zhengyang and Wang, Yang and Xie, Xike and Chen, Lianliang and Liu, Hengchang}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={34}, number={01}, pages={1258--1265}, year={2020} }