A hybrid Local Binary Pattern and wavelets based approach for EEG classification for diagnosing epilepsy

作者：

Highlights：

• Proposes hybrid Local Binary Pattern-Wavelet based approach to classify EEG in epileptic patients.

• A combination of univariate and a bivariate feature forms the feature set for seizure detection.

• A novel LBP based spatio-temporal analysis of the continuous EEG signal for epilepsy detection is carried out.

• Better performance isobtained as compared to existing works on same database.

摘要

•Proposes hybrid Local Binary Pattern-Wavelet based approach to classify EEG in epileptic patients.•A combination of univariate and a bivariate feature forms the feature set for seizure detection.•A novel LBP based spatio-temporal analysis of the continuous EEG signal for epilepsy detection is carried out.•Better performance isobtained as compared to existing works on same database.

论文关键词：Epilepsy,Electroencephalogram (EEG),Discrete Wavelet Transform (DWT),Linear Discriminant Classifier (LDA),Local Binary Pattern (LBP)

论文评审过程：Received 13 January 2019, Revised 20 August 2019, Accepted 20 August 2019, Available online 22 August 2019, Version of Record 30 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112895