A forecasting tool for prediction of epileptic seizures using a machine learning approach. (21st December 2018)

• Record Type: Journal Article
• Authors: Asharindavida, Fayas; Shamim Hossain, M.; Thacham, Azeemsha; Khammari, Hedi; Ahmed, Irfan; Alraddady, Fahad; Masud, Mehedi
• Other Names: Sangaiah Arun Kumar guestEditor.; Pham Hoang guestEditor.; Qiu Tie guestEditor.; Muhammad Khan guestEditor.; Awan Irfan guestEditor.; Younas Muhammad guestEditor.; Hussain Farookh guestEditor.
• Is Part Of: Concurrency and computation. Volume 32:Number 1(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-12-21
• Subjects: Electrocardiogram (ECG) -- Electroensephalogram (EEG) -- Empirical Mode Decomposition (EMD) -- epileptic seizure -- machine learning; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.5111
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: ECG and EEG signals are very helpful in the early diagnosis of epileptic seizures. The research focuses on analysis of ECG and EEG signals applying a deep learning technique to study early prediction of epileptic seizure. Signal processing methods like Empirical Mode Decomposition, spectral analysis, and statistical methods were used. The algorithms were implemented in MATLAB, and the EEG and ECG data were collected from Physiobank and EPILEPSIAE databases. In the window‐based analysis of low‐frequency spectral area of EEG signals, 78.5% of the cases displayed a significant change as the windows progressed and the onset of seizure was approached. The spectral area of IMF components indicated a possible seizure prediction in 68.9% of the analyzed cases. Considering signals from individual EEG electrodes, the least percentage of seizure prediction was indicated by signals from T4 and F4 electrodes (52.3% and 40.7%, respectively, for spectral peaks and 23.8% and 29.6%, respectively, for spectral area). The results of regression analysis show that prediction of seizures can be possible around 20‐30 minutes prior to the actual occurrence of seizures.