Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy based features of EEG signals.

摘要: Abstract Background and objective Epilepsy is a prevalent disorder that affects the central nervous system, causing seizures. In current study, novel algorithm developed using electroencephalographic (EEG) signals for automatic seizure detection from continuous EEG monitoring data. Methods proposed methods, discrete wavelet transform (DWT) orthogonal matching pursuit (OMP) techniques are used to extract different coefficients signals. Then, some non-linear features, such as fuzzy/approximate/sample/alphabet correct conditional entropy, along with statistical features calculated DWT OMP coefficients. Three widely-used datasets were utilized assess performance of techniques. Results The OMP-based technique support vector machine classifier yielded an average specificity 96.58%, accuracy 97%, sensitivity 97.08% types classification tasks. Moreover, DWT-based provided 99.39%, 99.63%, 99.72%. Conclusions: experimental findings indicated algorithms outperformed other existing Therefore, these can be implemented in relevant hardware help neurologists detection.