Skip to main content

Table 8 Comparison of methodologies presented in the literature for the three-class (ZO-NF-S) problem

From: Spectral information of EEG signals with respect to epilepsy classification

Authors

Feature extraction

Classification

Validation

Classification accuracy

Tzallas et al. [17] (2009)

TFD (SPWVD)/fractional energy

ANN

Monte Carlo cross-validation (50% split – 10 repeats)

97.72%

Acharya et al. [26] (2009)

10 parameters from Recurrence Quantification Analysis

SVM

3-fold cross-validation

95.60%

Orhan et al. [27] (2011)

DWT and K-means clustering

MLP

50% train, 50% validation and test

95.60%

Acharya et al. [28] (2012)

ApEn, SampEn, Phase Entropy 1 and 2

Fuzzy Sugeno Classifier

Threefold cross-validation

98.10%

Peker et al. [29] (2016)

Dual tree complex wavelet transform

Complex valued neural networks

10-fold cross-validation

98.28%

Tiwari et al. [30] (2016)

Key-point-based local binary patterns

SVM

10-fold cross-validation

98.80%

Bhattacharyya et al. [31] (2017)

Tunable-Q WT and K-NN entropies

SVM

10-fold cross-validation

98.60%

This study

Frequency sub-bands/energy, total energy, fractional energy, entropy

Random forests

10-fold cross-validation

98.80%