Spatiotemporal Traffic Flow Prediction with KNN and LSTM

• Published in: Journal of advanced transportation Vol. 2019; no. 2019; pp. 1 - 10
• Main Authors: Zhang, Shengrui, Yang, Yu, Li, Danyang, Luo, Xianglong
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2019; Hindawi; John Wiley & Sons, Inc; Wiley
• Subjects: Accuracy; Analysis; Autoregressive models; Belief networks; Data centers; Deep learning; Intelligent transportation systems; Long short-term memory; Neural networks; Nonparametric statistics; Performance evaluation; Prediction models; Rankings; Regression analysis; Sensors; Stations; Statistical analysis; Support vector machines; Time series; Traffic congestion; Traffic control; Traffic flow; Traffic management; Transportation; Transportation networks; Weighting methods; Trinidad and Tobago; China
• ISSN: 0197-6729; 2042-3195
• DOI: 10.1155/2019/4145353

The traffic flow prediction is becoming increasingly crucial in Intelligent Transportation Systems. Accurate prediction result is the precondition of traffic guidance, management, and control. To improve the prediction accuracy, a spatiotemporal traffic flow prediction method is proposed combined with k-nearest neighbor (KNN) and long short-term memory network (LSTM), which is called KNN-LSTM model in this paper. KNN is used to select mostly related neighboring stations with the test station and capture spatial features of traffic flow. LSTM is utilized to mine temporal variability of traffic flow, and a two-layer LSTM network is applied to predict traffic flow respectively in selected stations. The final prediction results are obtained by result-level fusion with rank-exponent weighting method. The prediction performance is evaluated with real-time traffic flow data provided by the Transportation Research Data Lab (TDRL) at the University of Minnesota Duluth (UMD) Data Center. Experimental results indicate that the proposed model can achieve a better performance compared with well-known prediction models including autoregressive integrated moving average (ARIMA), support vector regression (SVR), wavelet neural network (WNN), deep belief networks combined with support vector regression (DBN-SVR), and LSTM models, and the proposed model can achieve on average 12.59% accuracy improvement.