Table 4.
The summary of reviewed driver drowsiness detection papers. The meanings of the abbreviations are: TD—time-domain, FD—frequency-domain, N—nonlinear, EN—entropies, CN—complex networks, SIG—signal-based labeling, Li’s—Li’s subjective fatigue scale, SD—sleep deprivation, NREM1—labels based on the sleep stages, BE3—first and last three minutes as two labels, BE5—first and last five minutes as two labels, BIH—behavior-based labeling, WIE—Wierwille scale, RT—reaction time based labeling, EXP—expert labeling, LSTM—long-short term memory, KNN—k nearest neighbor, SVM—support vector machine, RF—random forest, ELM—extreme learning machine, GBDT—gradient boosting decision tree, NN—neural network, FLDA—Fisher linear discriminant analysis, SDBN—sparse deep belif network, HMM—hidden Markov model, and Thres.—thresholding-based algorithm.
| Author | Features | Target | Algorithm | No. Classes | Acc. |
|---|---|---|---|---|---|
| Chaabene et al. [174] | Raw | SIG | CNN | 2 | 90.14 |
| Balam et al. [173] | Raw | NREM1 | CNN | 2 | 94.00 |
| Yingying et al. [175] | FD | SIG | LSTM | 2 | 98.14 |
| Zou et al. [176] | EN | Li’s | KNN | 88.74 | |
| Chaudhuri and Routray [177] | EN | SD | SVM | 2 | 86.00 |
| Budak et al. [178] | TD, FD, EN and special | NREM1 | LSTM | 2 | 94.31 |
| Chen et al. [179] | CN | BE3 | SVM | 2 | 94.40 |
| Mehreen et al. [180] | FD | KSS | SVM | 2 | 92.00 |
| Martensson et al. [181] | FD, N and EN | KSS | RF | 2 | 93.50 |
| Barua et al. [182] | TD, FD and EN | KSS | SVM | 2 and 3 | 93.00 and 79.00 |
| Ogino and Mitsukura [183] | FD and EN | KSS | SVM | 2 | 67.00 |
| Chen et al. [184] | CN | KSS | |||
| Chen et al. [185] | CN | KSS | KNN | 2 | 98.60 |
| Chen et al. [186] | CN | BE3 | ELM | 2 | 95.00 |
| Hu and Min [187] | EN | BE5 | GBDT | 2 | 94.00 |
| Dimitrakopoulos et al. [188] | CN | BE5 | SVM | 2 | 92.10 |
| Hong et al. [189] | FD, N and EN | EBE | SVM | 5 | 99.50 |
| Li and Chung [190] | FD | WIE | SVM | 5 | 93.87 |
| Min et al. [191] | FD and EN | BE5 | NN | 2 | 98.30 |
| Awais et al. [192] | TD, FD and EN | BIH | SVM | 2 | 80.00 |
| Nguyen et al. [193] | FD | SIG | FLDA | 2 | 79.20 |
| Hu [194] | EN | BE5 | AdaBoost | 2 | 97.50 |
| Chai et al. [195] | FD | BE5 | SDBN | 2 | 90.60 |
| Chai et al. [196] | FD | BE5 | NN | 2 | 88.20 |
| Mu et al. [197] | EN | Li’s | SVM | 2 | 97.00 |
| Fu et al. [198] | FD | KSS | HMM | 3 | AUC 0.841 |
| Ahn et al. [199] | FD | SD | FLDA | 2 | 75.90 |
| Huang et al. [200] | FD | RT | |||
| Li et al. [201] | FD | BIH | SVM | 2 | 93.16 |
| Chen et al. [202] | FD, N and EN | SIG | ELM | 2 | 95.60 |
| Sauvet et al. [203] | FD | EXP | Threshold | 2 | 98.30 |
| Lee et al. [204] | TD and FD | NREM1 | SVM | 4 | 98.50 |
| Garces Correa et al. [205] | TD and FD | NREM1 | NN | 2 | 87.40 |
| Zhang et al. [110] | N and EN | SIG | NN | 4 | 96.50 |
| Hu et al. [206] | FD | KSS | SVM | 2 | 75.00 |
| Picot et al. [207] | FD | SIG | Threshold | 5 | 80.60 |
| Zhao et al. [208] | FD | Li’s | SVM | 3 | 81.60 |
| Khushaba et al. [20] | FD | WIE | LDA | 5 | 95.00 |
| Liu et al. [209] | EN | KSS and Li’s | HMM | 2 | 84.00 |