Short-Term Traffic Flow Prediction Model Based On K-Nearest Neighbors and Deep Learning Method
Author(s):
Ali Mustafa Ali Alshaykha, Abdullah Ibrahim Shaban
Affiliation(s):
Shirqat Engineering College, Tikrit University, Tikrit, Iraq
College of science, Tikrit University, Tikrit, Iraq
Corresponding Author Email:
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Aiming at the problem of deep learning prediction model calculations, on the basis of fully mining the spatio-temporal correlation of traffic big data. In this paper short-term traffic flow prediction model based on a combined k-nearest neighbors and Broad Learning System (KNN-BLS) is proposed. The KNN algorithm is used to monitor the K road sections with high temporal and spatial correlation. The traffic flow data of California Department of Transportation database the selected road section is used as the target and testing of the KNN-BLS model to predict respectively. The simulation results show that the proposed model reduces the average root mean square error by 39.72% compared with the ARIMA, LSTM, and KNN-LSTM models, and the root mean square error (RMSE) is the minimum value of K as the final predicted value. In addition, the computational efficiency is significantly improved by 17.4%.