TY  - JOUR
PY  - 2017//
TI  - Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction
JO  - Sensors (Basel)
A1  - Ma, Xiaolei
A1  - Dai, Zhuang
A1  - He, Zhengbing
A1  - Ma, Jihui
A1  - Wang, Yong
A1  - Wang, Yunpeng
SP  - s17040818
EP  - s17040818
VL  - 17
IS  - 4
N2  - This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.<p />  <p>Language: en</p>
LA  - en
SN  - 1424-8220
UR  - http://dx.doi.org/10.3390/s17040818
ID  - ref1
ER  -