| | Researchers | Objectives of study | Algorithms used | Accuracy (%) |
| | [6] | They proposed a fatigue detection system based on monitoring high-speed train drivers by wireless EEG. | SVM | 90.70 | | [12] | Classification for positive and negative emotions used in the EEG signals. | MLPNN
KNN | 77.14
72.92 | | [13] | Classifying the resting states of the human brain using linear and nonlinear EEG features | SVM with non-linear features
SVM with linear features. | 92.1
87.5 | | [33] | Improving the three-class motor imagery (MI) with BCI classification accuracy | LDA
SFFS | 86.06
93 | | [34] | Imposing to increase the mental workload (mw) | Average accuracies of KNN, SVM, and DT | 94, 88, 89 | | [35] | Effectiveness of the discrete wavelet transform (DWT) in load recognitions signatures | KNN, SVM
DT, RF
Adaboost, GBoosting
GaussianNB, LDA
QDA | 98.93, 64.93
100, 95.33
61.20, 100
66.53, 69.06
19.06 | | Present work | Identifying the resting-state status of brain using short-length EEG epochs | Extracted features by FFT: KNN, LR, DT,
LD, GNB, SVM
Extracted features by SE: KNN, LR, DT
LD, GNB, SVM | 93, 97, 92,
95, 86, 97
86, 89, 86
90, 89, 92 |
|
|
