| 基于深度学习的城市流量预测 |
| |
| 引用本文： | 王梦园,翟希,王斌.基于深度学习的城市流量预测[J].上海师范大学学报(自然科学版),2021,50(1):122-127. |
| |
| 作者姓名： | 王梦园 翟希 王斌 |
| |
| 作者单位： | 上海师范大学 信息与机电工程学院, 上海 200234,上海市城乡建设和交通发展研究院 上海交通信息中心, 上海 200003,上海师范大学 信息与机电工程学院, 上海 200234 |
| |
| 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 |
| 收稿时间： | 2020/12/17 0:00:00 |
City traffic forecast based on deep learning |
| |
| WANG Mengyuan,ZHAI Xi and WANG Bin.City traffic forecast based on deep learning[J].Journal of Shanghai Normal University(Natural Sciences),2021,50(1):122-127. |
| |
| Authors: | WANG Mengyuan ZHAI Xi and WANG Bin |
| |
| Institution: | College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, China,Shanghai Traffic Information Center, Shanghai Urban and Rural Construction and Traffic Development Research Institute, Shanghai 200003, China and College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, 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. |
| |
| Keywords: | traffic management Didi travel spatiotemporal data neural network traffic forecast |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《上海师范大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《上海师范大学学报(自然科学版)》下载免费的PDF全文 |
|
