Premium
EEG signal compression based on classified signature and envelope vector sets
Author(s) -
Gürkan Hakan,
Guz Umit,
Yarman B. Siddik
Publication year - 2009
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.548
Subject(s) - pattern recognition (psychology) , signal (programming language) , signal compression , computer science , frame (networking) , cluster analysis , envelope (radar) , electroencephalography , artificial intelligence , signature (topology) , speech recognition , mean squared error , algorithm , mathematics , statistics , image (mathematics) , image processing , psychology , telecommunications , radar , geometry , psychiatry , programming language
In this paper, a novel method to compress electroencephalogram (EEG) signal is proposed. The proposed method is based on the generation process of the classified signature and envelope vector sets (CSEVS), which employs an effective k ‐means clustering algorithm. It is assumed that both the transmitter and the receiver units have the same CSEVS. In this work, on a frame basis, EEG signals are modeled by multiplying only three factors called as classified signature vector, classified envelope vector, and gain coefficient (GC), respectively. In other words, every frame of an EEG signal is represented by two indices R and K of CSEVS and the GC. EEG signals are reconstructed frame by frame using these numbers in the receiver unit by employing the CSEVS. The proposed method is evaluated by using some evaluation metrics that are commonly used in this area such as root‐mean‐square error, percentage root‐mean‐square difference, and measuring with visual inspection. The performance of the proposed method is also compared with the other methods. It is observed that the proposed method achieves high compression ratios with low‐level reconstruction error while preserving diagnostic information in the reconstructed EEG signal. Copyright © 2008 John Wiley & Sons, Ltd.