论文部分内容阅读
物流需求受多种因素的作用,具有时变性和混沌性,针对当前支持向量机的参数优化难题,提出一种改进人工鱼群算浅优化支持向量机的物流需求预测模型.首先对原始物流需求数据进行混沌分析,挖掘出隐藏其中的物流需求变化规律,然后采用支持向量机对物流需求数据进行非线性建模,并采用人工鱼群算法搜索支持向量机的参数,最后利用某地区物流数据与当前经典模型进行性能对比测试.结果表明,模型预测精度.更高,更加客观地反映了物流需求变化特性.
Logistics demand is affected by many factors, which are time-varying and chaotic. In order to solve the problem of parameter optimization for current support vector machines, a logistics demand forecasting model based on shallow artificial optimization optimization (SVM) is proposed. Firstly, Data to chaos analysis, dig out the change of logistics demand, and then use support vector machine to logistics demand data for non-linear modeling and artificial fish swarm algorithm to search for support vector machine parameters, and finally the use of a regional logistics data and The performance comparison test of the current classic model shows that the prediction accuracy of the model is higher and more objectively reflects the changing characteristics of the logistics demand.