Title :
Research on SSVEP feature extraction based on HHT
Author :
Zhao, Li ; Yuan, Pengxian ; Xiao, Longteng ; Meng, Qingguo ; Hu, Daofu ; Shen, Hui
Author_Institution :
Dept. of Autom. & Electr. Eng., Tianjin Univ. of Technol. & Educ., Tianjin, China
Abstract :
Considering of high transmission rate and short training time, Steady State Visual Evoked Potential (SSVEP) rapidly becomes a practical signal in Brain-Computer Interface(BCI) system. This paper study the extraction method of SSVEP based on the Hilbert-Huang Transformation. The SSVEP was processed by a time-frequency processing system. after empirical mode decomposition and Hilbert-Huang Transform(HHT), an eigenvector detected from the result of HHT was viewed as the characteristics of the SSVEP signal that contains different frequency component. Then the eigenvector is classified in a Fisher classifier. Compared with the (Fast Fourier Transform)FFT, the classification accuracy of a one-minute data can reach more than 85 percent.
Keywords :
Hilbert transforms; brain-computer interfaces; eigenvalues and eigenfunctions; visual evoked potentials; Fisher classifier; Hilbert-Huang transformation; SSVEP feature extraction; brain-computer interface system; eigenvector; empirical mode decomposition; extraction method; fast Fourier transform; steady state visual evoked potential; time-frequency processing system; Accuracy; Electric potential; Electroencephalography; Feature extraction; Time frequency analysis; Transforms; Visualization; BCI; Fisher classifier; Hilbert-Huang Transform; SSVEP;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2010 Seventh International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5931-5
DOI :
10.1109/FSKD.2010.5569537
