摘要
对平稳的数据和非平稳数据两种数据序列建立的GM(1,1)模型,分别用加速遗传算法(AGA)和最小二乘法(LSM)对模型参数求解。结果表明:对平稳变化数据序列,两种方法建立的预测模型的拟合优度和预测精度无显著差异;对变化幅度较大的非平稳数据序列,基于AGA的GM(1,1)模型的拟合优度和预测精度高于基于LSM的GM(1,1)模型的拟合优度和预测精度。
The accelerated genetic algorithm (AGA) and the least square method(LSM) are used to solve the parameters of the gray GM(1,1) models of both stable and unstable data sequences. It is shown that there is little difference of the precision of the fit and forecast between the AGA and the LSM for the stable data sequence. But for the unstable data sequence the precision based on the AGA is much higher than that based on the LSM.
出处
《成都信息工程学院学报》
2002年第4期265-268,共4页
Journal of Chengdu University of Information Technology
基金
九.五国家重点科技攻关计划(96 911 08 03 05)