作者: S. Pouryazdian , A. Erfanian
DOI: 10.1007/978-3-642-03889-1_128
关键词:
摘要: This paper presents a new method for detection of steady-sate visual evoked potential (SSVEP) in 26-class brain-computer interface (BCI) using principal component analysis (PCA). PCA is used to decompose the multi-channel EEG signals into components which are orthogonal. After processing, (PCs) can be grouped related SSVEPs and brain activities. A major issue detect SSVEP selection proper components. In this work, we use high-order statistics automatically identify AR power spectra frequency SSVEP. The results experiments on three subjects each subject with 8 experiment sessions show that an average accuracy between 76.4% 91.8% achieved.