Table 2 Comparison of state-of-the-art emotion databases using physiological signals.
From: Insights from EEG analysis of evoked memory recalls using deep learning for emotion charting
Dataset | AMIGOS25 | DEAP26 | DECAF27 | DREAMER28 | MAHNOB-HCI29 | Imagined Emotions30 | MEMO |
|---|---|---|---|---|---|---|---|
Participants | 40 (27M, 13F) | 32 (16M, 16F) | 30 (16M, 14F) | 23 (14M, 9F) | 30 (13M, 17F) | 32 (13M, 19F) | 69 (36M, 33F) |
Modalities | EEG, ECG, GSR and audio-visual | EEG, GSR and peripheral signals | ECG and peripheral signals | EEG, ECG | EEG, ECG, GSR and peripheral signals | EEG, ECG, EMG | EEG |
Self-assessment annotations | Dimensional: valence, arousal, dominance, liking, familiarity. Categorical: Six basic emotions. | Dimensional: arousal, valence, liking, dominance and familiarity. | Dimensional: valence, arousal and dominance. | Dimensional: Valence, arousal and dominance. | Dimensional: valence, dominance. | Categorical: Love, joy, anger, fear etc. | Dimensional: valence, arousal. |
Dimensional scale | 1 to 9 | Continuous scale 1 to 9 | 0 to 5 and − 2 to + 2 | 1 to 5 | 1 to 9 | Non metric multi-dimensional scale | − 4 to 4 |
Acquisition | 14 Channel EEG, Wireless ECG and GSR | 32 Channel EEG and wired GSR | 3 channel ECG | 14 Channel EEG, Wireless ECG | 32 Channel EEG and wired ECG, GSR | 256-Channel Biosemi wired | 64-channel Wireless sports cap (ANT Neuro)31 |
Age (years) | 21–40 (\(\mu\) = 28.3) | 19–37 (\(\mu\) = 26.9) | (\(\mu\) = 27.3, \(\sigma\)= 4.3) | 22–33 (\(\mu\)= 26.6, \(\sigma\) = 2.7) | 19–40 (\(\mu\) = 26.06, \(\sigma\) = 4.93) | 18–38 (\(\mu\)= 25.5, \(\sigma\)= 5) | 20–56 (\(\mu\)= 36.95, \(\sigma\)= 9.67) |
Stimuli | 20 Videos | 40 Videos | 32 Videos | 18 Videos | 20 Videos | 15 Sounds | 16 words Memory recall |
