基于NGACH和ANFIS的调谐模型构建  

Research on ANFIS-NGARCH tuning model

作　　者：王惠[1] 陈燕[1] 杨小佳[1] 

机构地区：[1]大连海事大学经济与管理学院,辽宁大连116026

出　　处：《大连海事大学学报》2006年第4期11-13,18,共4页Journal of Dalian Maritime University

基　　金：国家自然科学基金资助项目(70540005)

摘　　要：针对传统的自适应模糊推理系统无法解决波动聚类现象,通过分析自适应模糊推理系统和非线性广义自回归条件方差的特性,提出了融合自适应模糊推理系统和非线性广义自回归条件方差的调谐模型.调谐模型实质是指在对ANFIS和NGARCH进行独立运行的基础上,对运行结果进行动态调谐操作,从而提高系统的预测精度.最后,结合实际的项目数据,证明调谐模型提高了传统ANFIS对于波动聚类现象的应对能力,获得较好的运行效果.Volatility clustering degrades the accuracy of ANFIS. To overcome volatility clustering problems, an adaptive neuro-fuzzy inference system （ANFIS） is combined with a nonlinear generalized autoregressive conditional heteroscedasticity （NGARCH） model that is tuned by adaptive support vector regression （ASVR） so as to tackle the problem of time-varying conditional variance in residual errors. Adaptive support vector regression is given to make the model. The proposed method significantly reduces large residual errors in forecasts because volatility clustering effects are regulated to trivial levels. Results show that foreca sting performance of the new model is better than previous one.

关 键 词：自适应模糊推理系统 非线性广义自回归条件方差 自适应支持向量机 波动聚类 

分 类 号：TP393.01[自动化与计算机技术—计算机应用技术] N945.12[自动化与计算机技术—计算机科学与技术]