论文部分内容阅读
准确的旅游客流量预测对旅游风景区有着决定性的意义.受多种原因影响,旅游客流量预测不仅呈现复杂非线性特点,而且显示出典型的季节性趋势,尤其在旅游旺季.文章提出一种季节支持向量回归(seasonal support vector regression,SSVR)和粒子群算法(particle swarm optimization,PSO)结合模型,即SSVR-PSO,实现对旅游客流量的预测.来自国内著名5A级风景区黄山2008-2011年最新月客流量数据仿真结果显示,SSVR-PSO模型预测精度明显高于SVRPSO、SVR-GA、BPNN、ARIMA等方法,是进行旅游客流量预测的有效工具.
Accurate prediction of tourist flow has a decisive significance for the tourist scenic area.Due to a variety of reasons, the prediction of tourist flow not only shows the characteristics of complex non-linearity but also shows the typical seasonal trend, especially in the tourist peak season.This paper proposes a The combination of seasonal support vector regression (SSVR) and particle swarm optimization (PSO) model, ie, SSVR-PSO, can realize the prediction of the tourist traffic volume.From the well-known 5A scenic spot Huangshan 2008-2011 The simulation results of the latest monthly traffic data show that the prediction accuracy of SSVR-PSO model is significantly higher than that of SVRPSO, SVR-GA, BPNN and ARIMA, which is an effective tool to forecast the passenger flow.