Sayed, R., Eskandarian, A., and Oskard, M. (2001) "Monitoring Drowsy Drivers with Artificial Neural Network", Miami Beach, FL: Intelligent Transportation Society of America 2001.

Abstract: This research is conducted for the purpose of detecting drowsiness/sleepiness of drivers for preventing traffic accidents on our highways. In this study we proposed a system which measures signals from the vehicle and then analyze those signals to detect drowsiness of driver. This method is based on an Artificial Neural Network (ANN). An ANN, with a hybrid architecture using an unsupervised clustering algorithm and a classifier, was trained and tested. Data used for training and testing was obtained from twelve drivers, each driving a simulator under different levels of sleep deprivation. We present a drowsiness detection method, which rely on signals from the vehicle only and thus present no obstruction to the driver.