publications

2022

1. Efficient Spatio-Temporal Randomly Wired Neural Networks for Traffic Forecasting

   Li Song, Kainan Bao, Songyu Ke, Chunyang Li, Junbo Zhang, and Yu Zheng

   In 2022 IEEE International Conference on Data Mining Workshops (ICDMW), 2022

   DOI Bib PDF

   @inproceedings{10031245,
     author = {Song, Li and Bao, Kainan and Ke, Songyu and Li, Chunyang and Zhang, Junbo and Zheng, Yu},
     booktitle = {2022 IEEE International Conference on Data Mining Workshops (ICDMW)},
     title = {Efficient Spatio-Temporal Randomly Wired Neural Networks for Traffic Forecasting},
     year = {2022},
     volume = {},
     number = {},
     pages = {1-8},
     keywords = {Costs;Fuses;Conferences;Neural networks;Computer architecture;Generators;Computational efficiency;Spatio-temporal forecasting;urban computing;neural architecture search},
     doi = {10.1109/ICDMW58026.2022.00140}
   }

2020

1. Learning to Generate Maps from Trajectories

   Sijie Ruan, Cheng Long, Jie Bao, Chunyang Li, Zisheng Yu, Ruiyuan Li, Yuxuan Liang, Tianfu He, and Yu Zheng

   Proceedings of the AAAI Conference on Artificial Intelligence, Apr 2020

   DOI Bib PDF

   @article{Ruan_Long_Bao_Li_Yu_Li_Liang_He_Zheng_2020,
     title = {Learning to Generate Maps from Trajectories},
     volume = {34},
     url = {https://ojs.aaai.org/index.php/AAAI/article/view/5435},
     doi = {10.1609/aaai.v34i01.5435},
     abstractnote = {<p>Accurate and updated road network data is vital in many urban applications, such as car-sharing, and logistics. The traditional approach to identifying the road network, i.e., field survey, requires a significant amount of time and effort. With the wide usage of GPS embedded devices, a huge amount of trajectory data has been generated by different types of mobile objects, which provides a new opportunity to extract the underlying road network. However, the existing trajectory-based map recovery approaches require many empirical parameters and do not utilize the prior knowledge in existing maps, which over-simplifies or over-complicates the reconstructed road network. To this end, we propose a deep learning-based map generation framework, i.e., DeepMG, which learns the structure of the existing road network to overcome the noisy GPS positions. More specifically, DeepMG extracts features from trajectories in both spatial view and transition view and uses a convolutional deep neural network T2RNet to infer road centerlines. After that, a trajectory-based post-processing algorithm is proposed to refine the topological connectivity of the recovered map. Extensive experiments on two real-world trajectory datasets confirm that DeepMG significantly outperforms the state-of-the-art methods.</p>},
     number = {01},
     journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
     author = {Ruan, Sijie and Long, Cheng and Bao, Jie and Li, Chunyang and Yu, Zisheng and Li, Ruiyuan and Liang, Yuxuan and He, Tianfu and Zheng, Yu},
     year = {2020},
     month = apr,
     pages = {890-897}
   }