A novel robust diagnostic model to detect seizures in electroencephalography

作者：

Highlights：

• A robust method is proposed for efficient detection of seizures in EEG.

• Dual tree-complex wavelet transform is used for feature extraction.

• General regression neural network is employed to classify extracted features.

• The proposed technique is giving ceiling level performance.

• The model can be used for fast and accurate diagnosis of epilepsy.

摘要

•A robust method is proposed for efficient detection of seizures in EEG.•Dual tree-complex wavelet transform is used for feature extraction.•General regression neural network is employed to classify extracted features.•The proposed technique is giving ceiling level performance.•The model can be used for fast and accurate diagnosis of epilepsy.

论文关键词：Electroencephalography (EEG),Seizure,Dual-tree complex wavelet transform (DTCWT),General regression neural network (GRNN),EEG,electroencephalography,DWT,discrete wavelet transform,DTCWT,dual-tree complex wavelet transform,GRNN,general regression neural network,TTTR,train-to-test ratio,ERD,energy,RMS,root-mean-square,STD,standard deviation,ENT,entropy,MXP,maximum peak,CA,classification accuracy,SE,standard error,SN,sensitivity,SP,specificity,CT,computation time

论文评审过程：Received 22 May 2015, Revised 22 February 2016, Accepted 23 February 2016, Available online 2 March 2016, Version of Record 24 March 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.02.040