Table 5 Comparison of proposed methodology with state-of-the-art techniques with memory-induced emotion recognition dataset using EEG signals.
From: Insights from EEG analysis of evoked memory recalls using deep learning for emotion charting
Technique | Temporal and frequency domain features with Linear discriminant analysis (LDA) classifier22 | Wavelet transform feature extraction, Principal component analysis for feature selection, and SVM for classification23 | Differential entropy features, and SVM for classification24 | 1D-CRNN-ELM (Proposed) |
|---|---|---|---|---|
First random split (%) | 52.60 | 60.58 | 60.04 | 65.64 |
Second random split (%) | 53.83 | 61.12 | 59.43 | 66.03 |
Third random split (%) | 54.22 | 60.97 | 59.35 | 65.26 |
Mean accuracy (%) | 53.54 | 60.89 | 59.61 | 65.64 |
Standard deviation (%) | 0.69 | 0.23 | 0.31 | 0.31 |
