Automated Recognition of Epileptic EEG States Using a Combination of Symlet Wavelet Processing, Gradient Boosting Machine, and Grid Search Optimizer

• DOI: 10.3390/s19020219
• Publication Date: 2019-01-10T08:22:31Z
• Authors: Xiashuang Wang; Guanghong Gong; Ni Li
• Keywords: Boosting; Gradient boosting

Automatic recognition methods for non-stationary electroencephalogram (EEG) data collected from EEG sensors play an essential role in neurological detection. The integrated approaches proposed this study consist of Symlet wavelet processing, a gradient boosting machine, and grid search optimizer three-class classification scheme normal subjects, intermittent epilepsy, continuous epilepsy. Fourth-order wavelets are adopted to decompose the into five frequencies sub-bands, such as gamma, beta, alpha, theta, delta, whose statistical features were computed used features. is automatically find optimal parameters training classifier. accuracy machine was compared with that conventional support vector random forest classifier constructed according previous descriptions. Multiple performance indices evaluate scheme, which provided better detection effectiveness than has been recently reported other studies on data.