Automatic detection of epileptic EEG using THFB and auroregressive modeling

Author

Khatavkar, S.S. ; Gawande, J.P.

Author_Institution

Dept. of Instrum. & Control, Cummins Coll. of Eng. for Women, Pune, India

fYear

2014

fDate

11-13 Dec. 2014

Firstpage

1

Lastpage

6

Abstract

In this work, the EEG signal is decomposed into its five subbands viz. delta (0.8-4Hz), theta (4-8Hz), alpha (8-15Hz), beta (15-30Hz), gamma (above 30Hz) using Triplet Half-band Filter Bank (THFB). Then, the autoregressive (AR) model is computed for each subband. Next, power spectral density (PSD) of the AR coefficients of each subbands is estimated for classfication of normal and epileptic EEG. It is observed that classification performed using THFB-AR modeling method gives better classification accuracy than existing method (approximate entropy).

Keywords

autoregressive processes; channel bank filters; electroencephalography; medical signal detection; AR coefficients; THFB-AR modeling method; automatic detection; autoregressive modeling; epileptic EEG signal; power spectral density; triplet half-band filter bank; Accuracy; Brain models; Computational modeling; Electroencephalography; Mathematical model; Wavelet transforms; Autoregressive model; Electroencephalogram; Power Spectral Density (PSD); Seizure detection; Wavelet filter bank;

fLanguage

English

Publisher

ieee

Conference_Titel

India Conference (INDICON), 2014 Annual IEEE

Conference_Location

Pune

Print_ISBN

978-1-4799-5362-2

Type

conf

DOI

10.1109/INDICON.2014.7030585

Filename

7030585