EEG signal classification for Epilepsy Seizure Detection using Improved Approximate Entropy

The detection of epileptic seizure signals based on fuzzy entropy

“…The results are satisfactory: using the FuzzyEn and the SampEn as features, the average accuracies of the CHB-MIT are 98.31% and 97.16%, respectively. Akareddy et al (2013) used the same data and used ApEn as a feature; his accuracy was only 90%, a result that is not better than ours. In this author's study, the specific indexes, such as accuracy, sensitivity and specificity, were not calculated.…”

“…On the basis of PE, Nicolaou and Georgiou (2012) were the first to perform an epilepsy classification using support vector machines (SVM), and their obtained classification accuracy was 94.38%. Using ANN, Akareddy et al (2013) studied the EEG signals of epileptics based on ApEn, with a classification accuracy of 90%. With the calculated SampEn adopted as the index, Shen et al (2013) also conducted classifications of epilepsy, and their calculated accuracy was as high as 91.18%.…”

A novel method of EEG data acquisition, feature extraction and feature space creation for early detection of epileptic seizures

“…Since EEG signals are transient, and highly dynamic, feature vectors are formed for each time epoch. The Multi-level Wavelet Decomposition is a popular technique used in previous studies [3,10,11,12,13,[15][16][17][18] for feature vector extraction. This technique decomposes an EEG signal into a number of sub-band signals each depicting a different waveform morphology within a particular frequency range.…”

Performance evaluation of contemporary classifiers for automatic detection of epileptic EEG

“…The idea for LDA was proposed by [5] and developed by [6]. Here, the method is to fmd a weight vector wso that NI and N2 ,which are the training feature vectors described bythe sets {XI, X2 , ... , XNI } and {XI, X2 , ... , XN2} respectively can be projected on w.They should be separated by linear hyper planes so that very small variance inside the clusters CI, C2, is obtained.…”