作者: Luisa F. Velásquez-Martínez , A. M. Álvarez-Meza , C. G. Castellanos-Domínguez
DOI: 10.1007/978-3-642-38622-0_38
关键词:
摘要: Recently, there have been many efforts to develop Brain Computer Interface (BCI) systems, allowing identify and discriminate brain activity. In this work, a Motor Imagery (MI) discrimination framework is proposed, which employs Common Spatial Patterns (CSP) as preprocessing stage, feature relevance analysis approach based on an eigendecomposition method the main features that allow studied EEG signals. The CSP employed reveal dynamics of interest from signals, then we select set representing best possible process. signals modeling done by estimation three frequency-based one time-based. Besides, over channels performed, gives user idea about mainly contribute for MI discrimination. Our tested well known dataset. Attained results (95.21±4.21 [%] mean accuracy) show presented can be used tool support