摘要
将输入空间划分为若干个相互重叠的模糊子空间 ,并在子空间内 ,利用线性模型对非线性系统进行局部建模 ,最后内插局部模型的输出 ,得到非线性系统的全局模糊建模 .基于 Sugeno模糊推理模型的模糊神经网络 (自适应网络模糊推理系统 ANFIS)正是上述模糊建模思想的神经网络实现的一种形式 .R/ S分析表明 ,上海股票市场的价格波动具有长期记忆性 ,因而可以预测 .基于此 ,利用 ANFIS对上证综合指数进行多步预测 。
Input space of nonlinear model is partitioned into several fuzzy subspaces. Within each subspace, a local linear model is used to model the nonlinear model. The global model output is obtained by interpolating the local model outputs. Adaptive network fuzzy inference system (ANFIS), based on Sugeno fuzzy inference model, is one way of neural network realization of the fuzzy modeling based on the ideal of local linear modeling above. The results of R/S analysis show that Shanghai stock market has long-term memory, thus possible to predict. This study combines ANFIS and FMH to implement multi-step prediction of Shanghai Stock Exchange index.
出处
《系统工程理论与实践》
EI
CSCD
北大核心
2003年第3期70-76,共7页
Systems Engineering-Theory & Practice
关键词
神经模糊建模
R/S分析
多步预测
neural fuzzy modeling
R/S analysis
multi-step prediction
