title   
  

AR-PCA-HMM approach for sensorimotor task classification in EEG-based brain-computer interfaces

Argunşah, Ali Özgür and Çetin, Müjdat (2010) AR-PCA-HMM approach for sensorimotor task classification in EEG-based brain-computer interfaces. In: 20th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey

[img]
Preview
PDF (This is a RoMEO green publisher -- author can archive publisher's version/PDF) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
319Kb

Official URL: http://dx.doi.org/10.1109/ICPR.2010.36

Abstract

We propose an approach based on Hidden Markov models (HMMs) combined with principal component analysis (PCA) for classification of four-class single trial motor imagery EEG data for brain computer interfacing (BCI) purposes. We extract autoregressive (AR) parameters from EEG data and use PCA to decrease the number of features for better training of HMMs. We present experimental results demonstrating the improvements provided by our approach over an existing HMM-based EEG single trial classification approach as well as over state-of-the-art classification methods.

Item Type:Papers in Conference Proceedings
Uncontrolled Keywords:BCI , EEG , HMM
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:15658
Deposited By:Müjdat Çetin
Deposited On:03 Dec 2010 17:12
Last Modified:03 Dec 2010 17:12

Repository Staff Only: item control page