Traffic flow prediction using LSSVM optimized by the bat algorithm

This study makes use of the daily vessel traffic flow in the waters near the Three Gorges Dam as its object of study and uses the bat algorithm to optimize the regularization parameter C and the kernel parameter σ of the least-squares support vector machine (LSSVM). Subsequently, a hybrid BA-LSSVM model proposed in this work is utilized to forecast the flow of vessel traffic. The algorithm was validated by real data, selecting 70% of the data as training set and 30% of the data as test set, and compared with the least squares support vector machine (LSSVM) prediction method. The results show that the model has good RMSE index, correct method and high prediction accuracy. Meanwhile, the engineering value and practical significance of the model provide a feasible method for traffic flow prediction.