利用LS—SVM模块化决策系统求解EEG源参数

给定头皮脑电位的分布推算脑内电活动的源是脑电研究的一个重要的方面.研究涉及到信息科学、电磁场计算及生物医学工程等多个学科领域,其研究成果在神经疾病诊断、探索人的感觉和认知过程等方面具有蕈要意义.基于最小二乘支持向最机(LS-SVM)算法建立模块化决策系统,首先对脑电数据进行分类,然后依据分类结果提取数据样本,并建立回归模型,最后求解多种偶极子源参数.从而建立起头皮电压和脑电源参数之间的内在联系,为脑电动态分析提出一种实时的研究思路.计算机仿真计算结果证明了此方法的有效性.

Solving EEG Source Parameters with Modular Decision-Making System Based on LS-SVM

It is an important topic in electroencephalography(EEG)research to estimate the electric current sources within the brain from EEG recordings.This research involves many subjects such as informatics,calculation of electromagnetic field and biomedicine engineering etc.The research is of great significance to the neuropathy diagnosis,exploring of human's feeling and cognition course etc.This paper establishes a modular system for decision-making based on the Least-Squares Support Vector Machines(LS-SVM) algor...