Traffic Forecasting via Dilated Temporal Convolution With Peak-Sensitive Loss

被引:41
作者
Guo, Ge [1 ]
Yuan, Wei [2 ]
Liu, Jinyuan [2 ]
Lv, Yisheng [3 ]
Liu, Wei [4 ,5 ]
机构
[1] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Peoples R China
[2] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China
[3] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
[4] Northeastern Univ, Res Acad, Shenyang, Peoples R China
[5] Neusoft Corp, Intelligent Vis Lab, Shenyang 110819, Peoples R China
基金
中国国家自然科学基金;
关键词
Correlation; Spatiotemporal phenomena; Forecasting; Data models; Deep learning; Convolution; Predictive models; FLOW;
D O I
10.1109/MITS.2021.3119869
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Deep learning-based traffic forecasting methods can capture intricate spatiotemporal features in traffic data and environmental factors. However, they have unsatisfactory performance around the minority peaks and are inefficient for modeling wide-range spatial correlations. This article gives a peak-aware deep learning architecture for traffic forecasting by involving a cost-sensitive loss function called peak-sensitive loss. This method can improve the performance since different costs are employed on the prevalent metrics such as mean-square loss and square of mean absolute percentage loss. A spatiotemporal convolutional architecture based on a dilated convolutional network (DCN) and a temporal convolutional network (TCN) is constructed that models the spatial features (both wide and short range) by the DCN and learns the time characteristics by the TCN. The effectiveness of the model is demonstrated with real-world data sets. © 2009-2012 IEEE.
引用
收藏
页码:48 / 57
页数:10
相关论文
共 24 条
[1]   Traffic Flow Prediction for Road Transportation Networks With Limited Traffic Data [J].
Abadi, Afshin ;
Rajabioun, Tooraj ;
Ioannou, Petros A. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, 16 (02) :653-662
[2]  
Ahmed M., TRANSP RES REC, V773, P1
[3]  
[Anonymous], 2016, TAXI L C T T R DATA
[4]   Dynamic near-term traffic flow prediction: system-oriented approach based on past experiences [J].
Chang, H. ;
Lee, Y. ;
Yoon, B. ;
Baek, S. .
IET INTELLIGENT TRANSPORT SYSTEMS, 2012, 6 (03) :292-305
[5]   Short-term inter-urban traffic forecasts using neural networks [J].
Dougherty, MS ;
Cobbett, MR .
INTERNATIONAL JOURNAL OF FORECASTING, 1997, 13 (01) :21-31
[6]  
Duan PB, 2016, 2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), P1610, DOI 10.1109/ITSC.2016.7795773
[7]  
Geng X, 2019, AAAI CONF ARTIF INTE, P3656
[8]   Vehicle Rebalancing With Charging Scheduling in One-Way Car-Sharing Systems [J].
Guo, Ge ;
Xu, Tao .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (05) :4342-4351
[9]   A residual spatio-temporal architecture for travel demand forecasting [J].
Guo, Ge ;
Zhang, Tianqi .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2020, 115
[10]   Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm [J].
Hong, Wei-Chiang .
NEUROCOMPUTING, 2011, 74 (12-13) :2096-2107