Particle swarm optimization of feedforward neural networks for the detection of drowsy driving

The work presented in this paper concerns the detection of drowsy driving based on time series measurements of driving behavior. Artificial neural networks, trained using particle swarm optimization, have been used to combine several indicators of drowsy driving based on a data set originating from a large study carried out in the driving simulator at the Swedish National Road and Transportation Institute. The neural networks obtained outperform the best individual indicators by a few percentage points, the best network reaching a performance (average of sensitivity and specificity) of around 75% on previously unseen test data.