Table 5 Comparison results of some epileptic seizure detection methods
From: Automated epileptic seizures detection using multi-features and multilayer perceptron neural network
Author | Features | Classifier | Results | Database |
|---|---|---|---|---|
Kiymik et al. | Autoregressive features | Back-propagation neural network | Accuracy 95% | Neurology department of the Medical Faculty Hospital of Dicle University |
Orhan et al. | DWT-based features | MLPNN | Accuracy 99.6 | University of Bonn |
Kamath 2013 | Teager energy | Radial basis function neural network | Accuracy 97.8% | University of Bonn |
Gurwinder et al. 2015 | Wavelet transformation and spike-based features | MLPNN | Accuracy 98.6 | University of Bonn |
Ahammad et al. | Energy, entropy, standard deviation, maximum, minimum, and mean | MLPNN | Accuracy 84.2 | University of Bonn |
Wang et al. 2011 | Wavelet packet entropy | K-NN | Accuracy 100% | University of Bonn |
Abbasi et al. 2017 | DWT-based features | MLPNN | 98.33% | University of Bonn |
Srinivasan et al. 2007 | ApEn | Recurrent Elman neural network | Accuracy 100% | University of Bonn |
Proposed method | PSD, entropy, and Teager energy | MLPNN | Sensitivity 97.8% Specificity 96.4% FDR 1 h−1 | Ramaiah Memorial College and Hospital, Bengaluru |