Multi-model Hybrid Traffic Flow Forecast Algorithm Based on Multivariate Data

Traffic flow forecast is a fine-grained task in urban intelligent transportation systems. Accurate traffic flow forecast can effectively support the development of intelligent transportation systems, reduce congestion, and improve the quality of residents’ travel. The forecast of traffic flow is affected by many random factors such as weather, holidays and seasons. It has a certain degree of randomness and uncertainty, which makes the traditional single model prediction result extremely unstable, and the consideration of random factors is incomplete. As a result, the final forecast results are quite different from the actual situation. To address this problem, this paper proposes a multi-model hybrid traffic flow forecast algorithm based on multivariate data, which considers various random factors from multiple aspects, and captures different features through multiple models to improve the accuracy. The experiments on the dataset of KDD CUP 2017 demonstrate the effectiveness of our approach.

[1]  Yu Zheng,et al.  Effective and Efficient: Large-Scale Dynamic City Express , 2015, IEEE Transactions on Knowledge and Data Engineering.

[2]  Tharam S. Dillon,et al.  Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm , 2012, IEEE Transactions on Intelligent Transportation Systems.

[3]  Ji Liu,et al.  Short-term traffic flow forecast based on parallel long short-term memory neural network , 2017, 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS).

[4]  Yu Zheng,et al.  Methodologies for Cross-Domain Data Fusion: An Overview , 2015, IEEE Transactions on Big Data.

[5]  Zhao Zhi-hong,et al.  K-nearest neighbor model of short-term traffic flow forecast , 2012 .

[6]  Yu Zheng,et al.  T-share: A large-scale dynamic taxi ridesharing service , 2013, 2013 IEEE 29th International Conference on Data Engineering (ICDE).

[7]  Yu Zheng,et al.  Real-Time City-Scale Taxi Ridesharing , 2015, IEEE Transactions on Knowledge and Data Engineering.

[8]  PengCheng Yuan,et al.  How long will the traffic flow time series keep efficacious to forecast the future , 2017 .

[9]  Panos G Michalopoulos,et al.  IMPROVED ESTIMATION OF TRAFFIC FLOW FOR REAL-TIME CONTROL (DISCUSSION AND CLOSURE) , 1981 .

[10]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[11]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[12]  Juan Zhicai,et al.  The Application of Nonparametric Regressive Algorithm for Short-Term Traffic Flow Forecast , 2009, 2009 First International Workshop on Education Technology and Computer Science.

[13]  Haiyan Wang,et al.  Urban Road Traffic Condition Pattern Recognition Based on Support Vector Machine , 2013 .