In the automotive industry, it is important to evaluate different car setups in order to match a professional driver's preference or to match the most acceptable setup for most drivers. Therefore, it is of great significance to devise objective and automatic procedures to assess a driver's response to different car settings. In this work, we analyze different physiological signals in order to evaluate how a particular car setup can be more or less stressful than others. In detail, we record an endosomatic Electrodermal Activity (EDA) signal, called Skin Potential Response (SPR), the Electrocardiogram (ECG) signal, and eye tracking coordinates. We eliminate motion artifacts by processing two SPR signals, one from each hand of the driver. Tests are carried out in a company that designs driving simulators, where the tested individuals had to drive along a straight highway with several lane changes. Three different car setups have been tested (neutral, understeering, and oversteering). We apply a statistical test to the data extracted from the cleaned SPR signal, and we then compare the results with the ones obtained using a Machine Learning algorithm. We show that we are able to discriminate the drivers' response to each setup, and, in particular, that the base car setup generates the least intense emotional response when compared to the understeering and the oversteering car setups.
