基于两阶段优化算法的神经网络预测模型  

Neural network forecasting model using multi-stage optimization approach based on GMDH and genetic algorithm

作　　者：邹昊飞[1] 夏国平[1] 杨方廷 

机构地区：[1]北京航空航天大学经济管理学院,北京100083 [2]北京仿真中心,北京100854

出　　处：《管理科学学报》2006年第5期28-35,共8页Journal of Management Sciences in China

基　　金：国家自然科学基金资助项目(70371004);教育部博士点基金资助项目(20040006023)

摘　　要：采用基于两阶段优化算法(multi_stage optimization approach,MSOA)的GA人工神经网络,将训练集分为两部分,在前一训练集训练后获得的网络基础上使用后一训练集进行进一步的训练获得更为优化的网络结构.针对复杂系统建模输入节点难以确定的问题,提出将其与自组织数据挖掘算法相结合,利用GMDH算法获得神经网络的初始化节点,使用训练好的神经网络模型进行预测.将由此建立的预测模型应用于粮食价格的预测,并进一步探讨了MSOA算法的收敛性问题.结果表明基于GMDH和MSOA的神经网络组合预测模型能较大提高神经网络的全局收敛能力和收敛速度,提高预测精度.This paper introduces a multi-stage optimization approach （MSOA） used in genetic algorithm （GA） for training neural networks to forecast the Chinese food grain price. We divide the training sample of neural networks into two parts considering the truth that the recent observations should be more important than the older ones. Firstly, we use the first training sample to train the neural network and achieve the network structure; Secondly, we continue to use the second training sample to further optimize the structure of neural network based on the previous step. Aiming at the characteristics of neural network structure, a model using a hybrid GMDH and artificial neural network is established. It can make the selection of input-lay units easy and improve the ability of rate of studying and the adaptability of neural network. Empirical results show that the neural networks based on MSOA can improve greatly the global convergence ability and convergence speed of most networks. Furthermore the result indicates that the combined model can be an effective way to improve forecasting accuracy.

关 键 词：GMDH MSOA 遗传算法 人工神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]