混沌理论和极限学习机的物流需求预测模型

Logistics demand prediction model based on chaos theory and extreme learning machine

为了提高物流需求的预测精度,为物流园区规划提供科学支撑,提出混沌理论和极限学习机的物流需求预测模型。物流需求受外界因素综合作用,具有混沌变化特点,通过互信息法和G-P法分析其混沌变化规律,根据混沌变化特点处理物流需求数据,并采用极限学习机进行回归与预测,最后与其他物流需求模型的性能进行对比与分析。结果表明,该模型获得了更高的物流需求预测精度,预测结果更加稳定、可信,预测结果有利于物流园区规划。

In order to improve the prediction accuracy of the logistics demand, and provide the scientific support for the lo- gistics park planning, a logistics demand prediction model based on chaos theory and extreme learning machine is proposed. Since the logistics demand affected by the external factors synthetically, and has the chaos variation characteristics, its chaos change law is analyzed with the mutual information method and G-P method. The logistics demand data is processed according to the chaos variation characteristics, and regressed and predicted with the extreme learning machine. The performance of the logis- tics demand prediction model is analyzed and compared with that of other models. The results show that the model can obtain the higher logistics demand prediction accuracy, has more stable and reliable prediction result, and the prediction result is bene- ficial to the logistics park planning.