Long-term epileptic EEG classification via 2D mapping and textural features

E EG - Based Epileptic Seizures Detection with Adaptive Learning Capability

“…Seizure detection method should be able to automatically adapt it properties to tackle this condition. However most of the proposed methods rely on extensive pre-training process for their machine learning algorithm (e.g, using ANN [11,14,16] or SVM [10,12,[21][22]). Huge training data, both for normal EEG and EEG with seizures, are needed to obtain accurate seizure detector.…”

“…These methods could be further categorized into: timedomain (e.g, [10,11]), frequency-domain (e.g, using filter bank [12] and sign periodogram transform [13]), time-frequency domain (e.g, wavelet transform [14][15][16][17]), nonlinear methods (e.g, using various entropies [18][19]) or combination of them (e.g, [10,20]). Other methods include using spatial filter (e.g, common spatial filter [21]) and transforming EEG signal into 2D image (e.g, image texture analysis [22]). Different artificial intelligent and machine learning techniques are used also for EEG signal classification such as artificial neural network (ANN) [11,14,16], support vector machines (SVM) [10,12,[21][22] and k-nearest neighbor (KNN) [20].…”

“…Other methods include using spatial filter (e.g, common spatial filter [21]) and transforming EEG signal into 2D image (e.g, image texture analysis [22]). Different artificial intelligent and machine learning techniques are used also for EEG signal classification such as artificial neural network (ANN) [11,14,16], support vector machines (SVM) [10,12,[21][22] and k-nearest neighbor (KNN) [20].…”

“…The third issue related to the testing procedure. Many of the proposed methods, such in [17,[20][21][22], were tested only using selected EEG epochs (few minutes EEG segments), not continuous EEG recording. This testing scheme is less realistic and fails to provide some of the important detection performances such as false detection rate and latency.…”

“…Recently, several promising EEG signal processing and feature extraction methods for seizure detection are proposed [10][11][12][13][14][15][16][17][18][19][20][21][22][23]. These methods could be further categorized into: timedomain (e.g, [10,11]), frequency-domain (e.g, using filter bank [12] and sign periodogram transform [13]), time-frequency domain (e.g, wavelet transform [14][15][16][17]), nonlinear methods (e.g, using various entropies [18][19]) or combination of them (e.g, [10,20]).…”