Algorithm of Imagined Left-Right Hand Movement Classification Based on Wavelet Transform and AR Parameter Model

• Published in: 2007 1st International Conference on Bioinformatics and Biomedical Engineering Vol. 1; pp. 539 - 542
• Main Authors: Xu, Baoguo, Song, Aiguo, Wu, Juan
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 2007
• Subjects: Brain computer interfaces; Brain modeling; Communication system control; Electroencephalography; Feature extraction; Linear discriminant analysis; Muscles; Testing; Wavelet coefficients; Wavelet transforms
• ISBN: 9781424411207; 1424411203
• ISSN: 2151-7614
• DOI: 10.1109/ICBBE.2007.141

Brain-computer interface (BCI) provides new communication and control channels that do not depend on the brain's normal output of peripheral nerves and muscles. In this paper, we report on results of developing a single trial online motor imagery feature extraction method for BCI. The wavelet coefficients and autoregressive parameter model was used to extraction the features from the motor imagery EEG and the linear discriminant analysis based on mahalanobis distance was utilized to classify the pattern of left and right hand movement imagery. The performance was tested by the Graz dataset for BCI competition 2003 and satisfactory results are obtained with an error rate as low as 10.0%.