An efficient realization of deep learning for traffic data imputation
详细信息 查看全文
- 作者：Yanjie Duan duanyanjie2012@ia.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Yisheng Lv ; yisheng.lv@ia.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Yu-Liang Liu liuyuliangxp@126.com" class="auth_mail" title="E-mail the corresponding author ; Fei-Yue Wang feiyue@ieee.org" class="auth_mail" title="E-mail the corresponding author
- 关键词：Traffic data imputation ; Deep learning ; Missing data
- 刊名：Transportation Research Part C: Emerging Technologies
- 出版年：2016
- 出版时间：November 2016
- 年：2016
- 卷：72
- 期：Complete
- 页码：168-181
- 全文大小：824 K
文摘
- •
The model denoising stacked autoencoders for traffic data imputation is proposed.
- •
The model performance changes with temporal and spatial factors.
- •
An efficient model realization with hierarchically training algorithm is developed.