Human seizure detection using quadratic Rényi entropy

Author

Feltane, Amal ; Bartels, G. F. Boudreaux ; Gaitanis, John ; Boudria, Yacine ; Besio, Walter

Author_Institution

Dept. of Electr., Univ. of Rhode Island, Kingston, RI, USA

fYear

2013

fDate

6-8 Nov. 2013

Firstpage

815

Lastpage

818

Abstract

In this study, the quadratic Rényi entropy is applied for seizure detection from human electroencephalography (EEG) signals. Quadratic Rényi entropy was combined with two different methods; the empirical mode decomposition (EMD) and discrete wavelet transform (DWT). The use of these two methods is justified since EEGs are non-linear and non-stationary signals. First, the EEG signal is decomposed into sub-signals using the EMD method or the DWT. Then, the quadratic Rényi entropy is used as an input feature. The k-nearest neighbor (k-NN) classifier algorithm extracted the features with 99.5%-100% accuracy.

Keywords

decomposition; discrete wavelet transforms; electroencephalography; entropy; feature extraction; medical signal detection; medical signal processing; DWT; EEG signal; EMD method; discrete wavelet transform; empirical mode decomposition; feature extraction; human electroencephalography signals; human seizure detection; k-nearest neighbor classifier algorithm; nonlinear signals; nonstationary signals; quadratic Renyi entropy; Accuracy; Discrete wavelet transforms; Electroencephalography; Empirical mode decomposition; Entropy; Feature extraction; Time-frequency analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering (NER), 2013 6th International IEEE/EMBS Conference on

Conference_Location

San Diego, CA

ISSN

1948-3546

Type

conf

DOI

10.1109/NER.2013.6696059

Filename

6696059