Table 10.

Comparison of the accuracy (%) of the proposed model with previous works, for the four quadrants classification. Values are from the original papers and using the DEAP dataset.

Year	Method	Accuracy
2020	Nonlinear higher order statistics and deep learning algorithm [20]	82.01
2019	Wavelet energy and entropy; Extreme Learning Machine with kernel [45]	80.83
2019	Time-frequency analysis using multivariate synchrosqueezing transform; Gaussian SVM [62]	76.30
2018	Wavelet energy; SVM classifier [21]	81.97
2018	Flexible analytic wavelet transform + information potential to extract features; Random Forest [23]	71.43
2017	Hybrid deep learning neural network (CNN + LSTM) [38]	75.21
2016	Discriminative Graph regularized Extreme Learning Machine with differential entropy features [32]	69.67
2021	Proposed model	84.40
	$\alpha ,\beta ,\gamma (All-SE)+{\alpha }_{DA}(All-H3)$; KNN, K = 1