关键词: 公共交通, 短期预测, 灰狼优化, 最小二乘支持向量机

Abstract: In order to improve the accuracy of short-term passenger flow forecasting for large-scale public transport, an optimization algorithm of Least Squares Support Vector Machine（EEMD-GWO-LSSVM） based on Grey Wolf Optimization algorithm is proposed under the condition of decomposing the original data with integrated empirical mode. The algorithm is used to realize short-term passenger flow forecasting for large-scale public transport. The model uses EEMD to decompose the original data, and uses LSSVM to predict the decomposed IMF components. The prediction parameters of LSSVM are optimized by grey wolf algorithm. By training and forecasting the number of people entering and leaving the North Passenger Station of Xi’an Metro Line 2 in a month, the forecasting results and Support Vector Machine（SVM）, Autoregressive Integrated Moving Average Model（ARIMA） are predicted, and the Least Squares Support Vector Machine（GWO-LSSVM） algorithm based on Grey Wolf Optimization parameters and cross-checking are used only. The Least Squares Support Vector Machines（LS-SVMs） with row parameter optimization are compared and the results show that the proposed algorithm has more accurate prediction results.

Key words: public transportation, short term prediction, grey wolf optimization, least square support vector machine