The aim of this Diploma Thesis is to examine and model the impact of mobile phone use on driver behaviour through the exploitation of data from smartphone sensors. To achieve this objective, data collected from 100 drivers who participated at a naturalistic driving experiment for four months are analyzed. The analysis was carried out with the use of statistical methods of mixed-effects linear and binary logistic regression. Through the linear regression models it was examined whether driving characteristics recorded by smartphone sensors affect and can therefore predict harsh driving events, whereas the logistic regression models were used to predict the use or no use of mobile phone while driving through the recording of driving related measures. The application of the models revealed that the factors affecting the harsh events are five, with the average driving speed being the main one, while the factors affecting the possibility of using the mobile phone while driving are six, with the average angular speed being the main one.
ID | ad64 |
Presentation | |
Full Text | |
Tags | big data, driver behaviour, driver distraction, driving simulator, naturalistic driving, statistical modelling |