A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system

作者：Ai, Yi; Li, Zongping; Gan, Mi^*; Zhang, Yunpeng; Yu, Daben; Chen, Wei; Ju, Yanni

来源：Neural Computing & Applications, 2019, 31(5): 1665-1677.

DOI：10.1007/s00521-018-3470-9

• Dockless bike-sharing system
• Short-term spatiotemporal distribution forecasting
• Deep learning
• Convolutional long short-term memory network (conv-LSTM)

Dockless bike-sharing is becoming popular all over the world, and short-term spatiotemporal distribution forecasting on system state has been further enlarged due to its dynamic spatiotemporal characteristics. We employ a deep learning approach, named the convolutional long short-term memory network (conv-LSTM), to address the spatial dependences and temporal dependences. The spatiotemporal variables including number of bicycles in area, distribution uniformity, usage distribution, and time of day as a spatiotemporal sequence in which both the input and the prediction target are spatiotemporal 3D tensors within one end-to-end learning architecture. Experiments show that conv-LSTM outperforms LSTM on capturing spatiotemporal correlations.

• 出版日期2019-5
• 单位西南交通大学