基于支持向量机回归算法的旅游短时客流量数据预测模型  

Forecast Model of Tourism Short-term Passenger Flow Data Based on Support Vector Machine Regression Algorithm

作　　者：顾芳芳 江可申[1] GU Fang-fang;JIANG Ke-shen(College of Economics and Management,Nanjing University of Aeronautics and Astronautics,Nanjing 211106 China)

机构地区：[1]南京航空航天大学经济与管理学院,江苏南京211106

出　　处：《自动化技术与应用》2023年第2期14-16,55,共4页Techniques of Automation and Applications

摘　　要：传统的客流量数据预测模型获取的数据维数较高,难以消除冗余数据,导致预测结果误差较大。为此本文提出了基于支持向量机回归算法的旅游短时客流量数据预测模型。首先利用局部线性嵌入算法对旅游短时客流量数据样本点进行局部重构,减小重构误差,降低数据维数,并消除客流量数据中存在的噪声数据和冗余数据。然后利用支持向量机回归算法构建旅游短时客流量数据预测模型。实验结果表明:该模型预测结果的最大百分比误差、平均百分比误差和均方误差均较低,证明该模型实现了设计预期。The traditional passenger flow data prediction model obtains the data dimension is high, it is difficult to eliminate the redundant data, resulting in the prediction result error is large. To do this. In this paper, a forecasting model of short-term tourist flow data based on support vector machine regression algorithm is proposed. Firstly, the local linear embedding algorithm is used to reconstruct the sample points of tourist short-term passenger flow data locally to reduce the reconstruction error, reduce the data dimension, and eliminate the noise data and redundant data in the passenger flow data. Then the support vector machine regression algorithm is used to build the tourism short-term passenger flow data prediction model. The experimental results show that the maximum percentage error, average percentage error and mean square error of the prediction results of the model are lower, which proves that the model achieves the design expectations.

关 键 词：支持向量机回归算法 短时客流量预测 局部线性嵌入算法 预测模型 数据降维 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]