| 摘要: |
| 就所述的长短期记忆（LSTM）模型和DeepST-ResNet模型进行了研究分析，并基于西安滴滴出行的真实数据对相关模型进行对比实验，分析了各个模型的优劣，提出了建立更优模型的思路与展望. |
| 关键词: 交通管理 滴滴出行 时空数据 神经网络 流量预测 |
| DOI：10.3969/J.ISSN.1000-5137.2021.01.017 |
| 分类号:TP399 |
| 基金项目: |
|
| City traffic forecast based on deep learning |
|
WANG Mengyuan1, ZHAI Xi2, WANG Bin1
|
|
1.College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, China;2.Shanghai Traffic Information Center, Shanghai Urban and Rural Construction and Traffic Development Research Institute, Shanghai 200003, China
|
| Abstract: |
| In this paper the long-term and short-term memory(LSTM)model and the DeepST-ResNet model were both studied and analyzed. Based on the real data of Xi' an Didi travel, the above models were compared and tested to analyze the advantages and disadvantages of each model according to which a better model was proposed and the preliminary work and preparation was conducted. |
| Key words: traffic management Didi travel spatiotemporal data neural network traffic forecast |
Editorial Board