论文部分内容阅读
针对旅游景点游客数量的预测研究,传统的优化算法在建模速度和准确度方面已难以满足。基于此,本文提出基于参数优化的LS-SVM算法,该算法可以明显地提高预测的寻优精度和收敛速度。首先,采用SPSS对旅游入境人数和影响因素进行相关性分析,从而有效地提取出最佳影响因素,提高非必要因素的干扰,提高模型预测的精度。其次,由于预测模型应对不良数据造成误差增大的问题,研究选取径向基核(RBF核)为LS-SVM的核函数,在此基础上采用改进粒子群优化算法进行LS-SVM参数选择。最后,结合实例验证了该方法的实效性。以安徽省入境旅游为例,通过对LS-SVM与传统的神经网络预测结果进行对比,仿真结果表明该模型预测旅游景点旅客数量有较高的精度。
According to the prediction of the number of tourists in tourist attractions, the traditional optimization algorithms have been difficult to meet in terms of modeling speed and accuracy. Based on this, this paper proposes an LS-SVM algorithm based on parameter optimization, which can significantly improve the accuracy and convergence speed of the prediction. First of all, using SPSS to analyze the correlation between the number of inbound travelers and the influencing factors, so as to effectively extract the best influencing factors, increase the interference of non-essential factors, and improve the accuracy of model predictions. Secondly, due to the problem that the prediction model should increase the error caused by bad data, the kernel function of Radial Basis Function (RBF) is chosen as LS-SVM, and the improved Particle Swarm Optimization (PSO) algorithm is used to select LS-SVM parameters. Finally, an example is given to verify the effectiveness of this method. Taking the inbound tourism in Anhui Province as an example, the LS-SVM is compared with the traditional neural network forecasting results. The simulation results show that the model predicts the high precision of tourist attractions.