大会名称 |
---|
2023年 総合大会 |
大会コ-ド |
2023G |
開催年 |
2023 |
発行日 |
2023-02-28 |
セッション番号 |
D-20 |
セッション名 |
情報論的学習理論と機械学習 |
講演日 |
2023/3/8 |
講演場所(会議室等) |
2号館 2401教室 |
講演番号 |
D-20-11 |
タイトル |
Congestion Prediction using Multi-Resolution Recursive Spatio-Temporal Transformer |
著者名 |
○QUANG HUY UNG, HAO NIU, SHINYA WADA, |
キーワード |
Congestion Prediction, Mu2ReST, Spatio-Temporal Transformer |
抄録 |
Traveling and transporting are essential demands of human beings to do daily activities. Due to the increasing demands of traffic usage, and various factors (e.g., weather, public infrastructure, etc.), traffic congestion often happens in large cities. Early warnings of congestion could help traffic managers to adjust the traffic flow for congestion prevention. Congestion prediction could be considered as a time-series forecasting problem. Recently, Niu et al. [1] proposed an efficient method, namely Mu2ReST, outperforming previous studies for long-term time-series forecasting. In this paper, we apply Mu2ReST to the problem of congestion prediction and evaluate its performance for long-term prediction. |
本文pdf |
PDF download
|