Detection and prediction of driver drowsiness using artificial neural network models.

Not just detecting but also predicting impairment of a car driver's operational state is a challenge. This study aims to determine whether the standard sources of information used to detect drowsiness can also be used to predict when a given drowsiness level will be reached. Moreover, we explore whether adding data such as driving time and participant information improves the accuracy of detection and prediction of drowsiness. Twenty-one participants drove a car simulator for 110min under conditions optimized to induce drowsiness. We measured physiological and behavioral indicators such as heart rate and variability, respiration rate, head and eyelid movements (blink duration, frequency and PERCLOS) and recorded driving behavior such as time-to-lane-crossing, speed, steering wheel angle, position on the lane. Different combinations of this information were tested against the real state of the driver, namely the ground truth, as defined from video recordings via the Trained Observer Rating. Two models using artificial neural networks were developed, one to detect the degree of drowsiness every minute, and the other to predict every minute the time required to reach a particular drowsiness level (moderately drowsy). The best performance in both detection and prediction is obtained with behavioral indicators and additional information. The model can detect the drowsiness level with a mean square error of 0.22 and can predict when a given drowsiness level will be reached with a mean square error of 4.18min. This study shows that, on a controlled and very monotonous environment conducive to drowsiness in a driving simulator, the dynamics of driver impairment can be predicted.

Adapting artificial neural networks to a specific driver enhances detection and prediction of drowsiness.

Monitoring car drivers for drowsiness is crucial but challenging. The high inter-individual variability observed in measurements raises questions about the accuracy of the drowsiness detection process. In this study, we sought to enhance the performance of machine learning models (Artificial Neural Networks: ANNs) by training a model with a group of drivers and then adapting it to a new individual. Twenty-one participants drove a car simulator for 110 min in a monotonous environment. We measured physiological and behavioral indicators and recorded driving behavior. These measurements, in addition to driving time and personal information, served as the ANN inputs. Two ANN-based models were used, one to detect the level of drowsiness every minute, and the other to predict, every minute, how long it would take the driver to reach a specific drowsiness level (moderately drowsy). The ANNs were trained with 20 participants and subsequently adapted using the earliest part of the data recorded from a 21st participant. Then the adapted ANNs were tested with the remaining data from this 21st participant. The same procedure was run for all 21 participants. Varying amounts of data were used to adapt the ANNs, from 1 to 30 min, Model performance was enhanced for each participant. The overall drowsiness monitoring performance of the models was enhanced by roughly 40% for prediction and 80% for detection.