| Nomenclature | |
| NHTSA | National highway traffic safety administration |
| DDD | Driver drowsiness detection |
| IoT | Internet of things |
| KSS | Karolinska sleepiness scale |
| ML | Machine learning |
| TP | True positive |
| TN | True negative |
| FP | False positive |
| FN | False negative |
| NTHUDDD | National Tsuing Hua university drowsy driver detection |
| PERCLOS | Percentage of eyelid closure |
| EAR | Eye aspect ratio |
| SVM | Support vector machine |
| KNN | K-nearest neighbor |
| SHRP2 | Strategic highway research program results |
| RF | Random forest |
| ANN | Artificial neural networks |
| CNN | Convolutional neural network |
| FD-NN | Fully designed neural network |
| TL-VGG16 | Transfer learning in VGG16—VG16 is a 16-layers deep CNN architecture, named after the Visual Geometry Group from Oxford |
| TL-VGG19 | Transfer learning in VGG19—VG19 is a 19-layers deep CNN architecture |
| LSTM | Long short-term memory |
| RNN | Recursive neural network |
| ROI | Region of interest |
| EM-CNN | Eye and mouth CNN |
| EMD | Empirical mode decomposition |
| IMF | Intrinsic mode functions |
| EEG | Electroencephalography |
| ECG | Electrocardiography |
| PPG | Photoplethysmography |
| HRV | Heart rate variability |
| EOG | Electrooculography |
| EMG | Electromyography |
| ELM | Extreme learning machine |
| SVDD | Simulated virtual driving driver |
| AVMD | Adaptive variational mode decomposition |
| RPs | Recurrence plots |
| RRIs | R–R intervals |
| Bin-RP | Binary recurrence plot |
| Cont-RP | Continuous recurrence plot |
| ReLU-RP | Thresholded recurrence plot |
| ReLU | Rectified linear unit |
| HF | High frequency |
| LF | Low frequency |
| LF/HF | Low to high frequency |
| MeanNN | Mean of RRI |
| SDNN | Standard deviation of RRI |
| RMSSD | Root means square of the difference of adjacent RRI |
| TP | Total power which is the variance of RRI |
| NN50 | Number of pairs of adjacent RRI spaced by 50 ms or more |
| RRV | Respiratory rate variability. |
| H1 | Sum of the logarithmic amplitudes of the bispectrum |
| H2 | Sum of the logarithmic amplitudes of the diagonal elements in the bispectrum |
| H3 | First-order spectral moment of the amplitudes of diagonal elements in the bispectrum |
| SWA | Steering wheel angle |
| ANFIS | Adaptive neuro-fuzzy inference systems |
| MOL | Multilevel ordered logit |
| BPNN | Back propagation neural network |
| NIRS | Near-infrared spectroscopy |
| MEC | Multi-access edge computing |