Table 4 Classification accuracy and details of the proposed method and deep neural network approaches which used raw EEG signals11,12,17,21,23,25,26 for the DEAP dataset.
Subject-dependent/independent | Methods | Used signals | Accuracy (%) |
|---|---|---|---|
Subject-dependent | Jin et al.26 (2020) | Raw EEG | 97.91 |
Zhong et al.25 (2020) | Raw EEG | 92.05 | |
Khare et al.23 (2020) | Raw EEG | 90.88 | |
Wang et al.21 (2020) | Raw EEG | 89.19 | |
Song et al.17 (2018) | Raw EEG | 83.20 | |
Chen et al.12 (2020) | Raw EEG | 79.81 | |
Padilla et al.11 (2016) | Raw EEG | 58.36 | |
Proposed method | EEG source signal | 98.96 | |
Subject-independent | Jin et al.26 (2020) | Raw EEG | 97.52 |
Zhong et al.25 (2020) | Raw EEG | 87.24 | |
Khare et al.23 (2020) | Raw EEG | 80.72 | |
Wang et al.21 (2020) | Raw EEG | 72.39 | |
Song et al.17 (2018) | Raw EEG | 71.48 | |
Chen et al.12 (2020) | 69.66 | ||
Padilla et al.11 (2016) | 57.94 | ||
Proposed method | EEG source signal | 98.31 |
