Name
Abstract | ||
|---|---|---|
The Internet of Things (IoT) enables us to collect traffic data from multiple sources, which makes it possible to predict traffic speed in time with big traffic data. This article presents a novel spatio-temporal deep learning framework that aims to provide accurate and timely traffic speed forecasting. To extract the spatial and temporal features of traffic data simultaneously, this framework combines two different deep learning models, namely convolutional long short-term memory (ConvLSTM) and the graph convolutional network (GCN). Specifically, the ConvLSTM model is used to learn the temporal dynamics of traffic data to extract temporal features. On the other hand, the GCN model is used to learn the spatial complexity of traffic data to extract spatial features. Experiments show that the prediction performance of our framework at different time horizons outperforms three baseline approaches. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/IOTM.0001.2000031 | IEEE Internet of Things Magazine |
Keywords | DocType | Volume |
temporal features,temporal dynamics,IoT,big traffic data,spatio-temporal deep learning framework,traffic speed forecasting,graph convolutional network,convolutional long short-term memory,ConvLSTM,GCN | Journal | 3 |
Issue | ISSN | Citations |
4 | 2576-3180 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fei Dai | 1 | 0 | 4.39 |
| Penggui Huang | 2 | 0 | 1.01 |
| Xu Xiaolong | 3 | 424 | 64.23 |
| Lianyong Qi | 4 | 0 | 0.34 |
| Mohammad R. Khosravi | 5 | 26 | 7.55 |