Table 7 Comparison of the proposed method with the recent studies for the DEAP dataset.
From: Detecting emotions through EEG signals based on modified convolutional fuzzy neural network
Study | Feature extraction | Classifier | Dataset | Results | |
|---|---|---|---|---|---|
Valence | Arousal | ||||
PSD, Asymmetry features | DNN | DEAP | 82.00 | 82.00 | |
– | LSTM | DEAP | 85.45 | 85.65 | |
Signal framing, Frequency band power, Pearson correlation | SAE + LSTM | DEAP | 81.10 | 74.38 | |
Differential entropy | CNN + LSTM | DEAP-SEED | 65 (DEAP) | ||
PSD | CNN | DEAP-SEED | 85.23 | 86.50 | |
PSD | LSTM | DEAP-SEED | 87.68 | 87.98 | |
– | 1DCNN + LSTM | DEAP | 92.29 | 90.33 | |
– | CNN | DEAP | 90.01 | 90.65 | |
– | LSTM-Attention | DEAP | 90.10 | 83.30 | |
Proposed | FFT | CFNN | DEAP | 98.21 | 98.08 |
