Table 7 Comparison classification performance between the proposed and previous works
From: Classification of bruxism based on time-frequency and nonlinear features of single channel EEG
Authors | Signal | Method | Channel | Sleep stage | Accuracy (%) |
|---|---|---|---|---|---|
E. O’Hare et al. [9] | EMG | Linear discriminant analysis | EMG | Awake | 82.8% |
Bin Heyat et al. [16] | EEG | Decision tree | C4P4,C4A1 | REM | 81.25% |
Bin Heyat et al. [17] | EEG,EMG,ECG | Hybrid Machine Learning Classifier | ECG1,ECG2,C4P4,C4A1 | REM | 97% |
D. Lai et al. [10] | EEG,EMG,ECG | Decision tree | EEG,EMG,ECG1 | REM | 97.21% |
Present | EEG | Decision tree (Fine Tree classifier) | C4P4 | REM | 97.84% |