Real time driver drowsiness detection using a logistic-regression-based machine learning algorithm

Detection and Evaluation of Driver Distraction Using Machine Learning and Fuzzy Logic

“…The suggested methodology has a certain advantage over other DD detection methods described in Section II. Particularly, as compared to the methods, where the behavioral and psychological attributes are applied [6][7][8][9][10][11][12][13][14][15][16][17][18], the proposed approach does not require additional devices, such as cameras and neuroscan systems. Those devices increase the system cost [8], what in its turn is a potential resistance for system application in a commercial passenger vehicle.…”

“…In [17], the same signal analyses were applied for the DD detection by different machine learning methods: decision tree, random forest, k-NN, SVM, and Naïve Bayes. The driver drowsiness detection using heart rate electrocardiogram signals with LR and BN was described in [18]. Very popular is the usage or performance-based attributes in the DD detection as an estimate of the vehicle dynamics.…”

Fatigue driving detection model based on multi‐feature fusion and semi‐supervised active learning

“…Park et al [13] proposed a deep drowsiness detection network for learning effective features and detecting drowsiness with recorded RGB videos of driving behaviours. Babaeian et al [27] proposed a method to detect driver fatigue by using a ML algorithm based on a priori logistic regression. Zhao et al [28] proposed a framework for recognising driver fatigue expressions based on facial dynamic fusion information and a deep belief network (DBN), this method is validated on a driver drowsiness dataset, which includes different genders, ages, head poses and illuminations.…”

A Method for Detection and Evaluation of Driver Distraction Induced by In-Vehicle Information Systems

“…electrocardio-and electroencephalographical signals). In [8], decision tree, random forest, k-NN, SVM, and Naïve Bayes algorithms were compared, while in [9] the Bayesian network and logic regression were used. The reliance on additional devices, such as cameras and neuroscan system, is the methods' main drawback, because it rises the system price and complexity [10].…”