Ultra-fast Epileptic seizure detection using EMD based on multichannel electroencephalogram

Author

Wei Chen ; Yan-Yu Lam ; Chia-Ping Shen ; Hsiao-Ya Sung ; Jeng-Wei Lin ; Ming-Jang Chiu ; Feipei Lai

Author_Institution

Grad. Inst. of Biomed. Electron. & Bioinf., Nat. Taiwan Univ., Taipei, Taiwan

fYear

2013

fDate

10-13 Nov. 2013

Firstpage

1

Lastpage

4

Abstract

We present a system to detect seizure and spike in Epilepsy Electroencephalogram (EEG) analysis and characterize different epilepsy EEG types. After extracting features from three EEG types, Normal, Seizure and Spike, with Empirical Mode Decomposition (EMD), we do Analysis of variance (ANOVA) to classify conspicuous features and low-resolution features, and build Gaussian distributions of conspicuous features for probability density function (PDF) to do classification. Using EMD, the recognition rate improved from 70% to 90%. With ANOVA, the recognition rate can reach 99%. The linear model accelerates the system from 2 hours to 90 seconds compare to the previous approach.

Keywords

Gaussian distribution; electroencephalography; medical signal detection; ANOVA; Empirical Mode Decomposition; Epilepsy Electroencephalogram analysis; Gaussian distribution; feature extraction; multichannel electroencephalogram; probability density function; spike detection; ultrafast epileptic seizure detection; Analysis of variance; Correlation coefficient; Electroencephalography; Epilepsy; Feature extraction; Probability density function; Standards;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on

Conference_Location

Chania

Type

conf

DOI

10.1109/BIBE.2013.6701576

Filename

6701576