Developing a multi sensors system to detect sleepiness to drivers from transport systems

The increasing number of accidents in transportation (rail, road) recorded in the past few years have become a serious concern for the society. The accidents caused by driving under fatigue, drowsiness and disruptive (stress) factors have a high mortality rate due to decreasing of the abilities of perception, recognition and control which are necessary for the conductors in the field of road and railway. The paper proposes a multi-sensor system for predicting fatigue and drowsiness based on the analysis of the power spectrum density (PSD) of the electroencephalogram (EEG) and correlation with the cardiac cycle (ECG) or with the respiratory cycle. EEG data collecting uses a sensorial system, headset type (physical contact) or capacitive (no physical contact), and for ECG data collecting a new system of sensor is proposed, that does not involve physical contact against the capacitive system currently used. Our results demonstrated that it is possible to estimate with quantitative accuracy the driving performance in a 3D driving simulator, using the multi-sensor system proposed.