TY - JOUR
T1 - A temporal-aware LSTM enhanced by loss-switch mechanism for traffic flow forecasting
AU - Lu, Huakang
AU - Ge, Zuhao
AU - Song, Youyi
AU - Jiang, Dazhi
AU - Zhou, Teng
AU - Qin, Jing
N1 - Funding Information:
This work was supported by the NSFC (No. 61902232), the Natural Science Foundation of Guangdong Province (No. 2018A030313291), the Education Science Planning Project of Guangdong Province (2018GXJK048), the Guangdong Special Cultivation Funds for College Students’ Scientific and Technological Innovation (No. pdjh2020b0222), the grant from the Hong Kong Polytechnic University (No. 1ZE8J), the STU Scientific Research Foundation for Talents (NTF18006), and the 2020 Li Ka Shing Foundation Cross-Disciplinary Research Grant (No. 2020LKSFG05D, 2020LKSFG04D).
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2021/2/28
Y1 - 2021/2/28
N2 - Short-term traffic flow forecasting at isolated points is a fundamental yet challenging task in many intelligent transportation systems. We present a novel long short-term memory (LSTM) network enhanced by temporal-aware convolutional context (TCC) blocks and a new loss-switch mechanism (LSM) to carry out this task. Compared with conventional recurrent neural networks (RNN) or LSTM networks, the proposed network can capture much more distinguishable temporal features and effectively counteracting noise and outliers for more accurate prediction. The proposed TCC blocks, leveraging dilated convolution, produce an enlarged receptive field in temporal contexts, and formulate a temporal-aware attention mechanism to learn the complicated and subtle temporal features from the traffic flows. We further cascade multiple TCC blocks in the network to learn more temporal features at different scales. To deal with the noise and outliers, we propose a novel loss-switch mechanism (LSM) by combining the traditional mean square error loss and the generalized correntropy induced metric (GCIM), which is capable of effectively counteracting non-Gaussian disturbances. The whole network is trained in an end-to-end manner guided by the loss-switch mechanism. Extensive experiments are conducted on two typical benchmark datasets and the experimental results corroborate the superiority of the proposed model over state-of-the-art methods.
AB - Short-term traffic flow forecasting at isolated points is a fundamental yet challenging task in many intelligent transportation systems. We present a novel long short-term memory (LSTM) network enhanced by temporal-aware convolutional context (TCC) blocks and a new loss-switch mechanism (LSM) to carry out this task. Compared with conventional recurrent neural networks (RNN) or LSTM networks, the proposed network can capture much more distinguishable temporal features and effectively counteracting noise and outliers for more accurate prediction. The proposed TCC blocks, leveraging dilated convolution, produce an enlarged receptive field in temporal contexts, and formulate a temporal-aware attention mechanism to learn the complicated and subtle temporal features from the traffic flows. We further cascade multiple TCC blocks in the network to learn more temporal features at different scales. To deal with the noise and outliers, we propose a novel loss-switch mechanism (LSM) by combining the traditional mean square error loss and the generalized correntropy induced metric (GCIM), which is capable of effectively counteracting non-Gaussian disturbances. The whole network is trained in an end-to-end manner guided by the loss-switch mechanism. Extensive experiments are conducted on two typical benchmark datasets and the experimental results corroborate the superiority of the proposed model over state-of-the-art methods.
KW - Deep learning
KW - Intelligent transportation system
KW - Noise-immune learning
KW - Time series analysis
KW - Traffic flow modeling
UR - http://www.scopus.com/inward/record.url?scp=85098464792&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2020.11.026
DO - 10.1016/j.neucom.2020.11.026
M3 - Journal article
AN - SCOPUS:85098464792
SN - 0925-2312
VL - 427
SP - 169
EP - 178
JO - Neurocomputing
JF - Neurocomputing
ER -