DETECTION AND PREDICTION OF DRIVER DROWSINESS USING ARTIFICIAL NEURAL NETWORK MODELS

Abstract

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 110 min 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 of4.18 min. 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.

Existing System

Karolinska Sleepiness Scale (KSS), Video-oculo-graphy

Proposed System

The goal of this study is to develop and evaluate a model with an artificial neural network (ANN), so as to predict when a given impaired state will be reached in addition to detecting this impaired state. It deliberately chose unobtrusive recording techniques easily applicable in a car. Different datasets using different sources of information were tested, to determine which kind of information yields the most powerful model. It put forward two hypotheses. First, it hypothesized that it is possible to predict when the impaired state will arise by using the sensorimotor, physiological and performance indicators used to detect drowsiness. Second, it hypothesized that adding information such as driving time and participant information will improve the accuracy of the model.

Architecture

BLOCK DIAGRAM