The aim of this research is to identify the critical driving parameters that affect speeding using data from smartphones. To achieve this objective, data collected from sixty-eight (68) drivers who participated in a naturalistic driving experiment for fifteen (15) months, are analyzed. Through linear regression models, it was examined whether driving characteristics recorded by smartphone affect and can therefore predict the percentage of speeding time during driving. Four statistical linear regression models forecasting the percentage of speeding time during driving were developed: one overall model and three models for each road type (urban, rural, highway). The results revealed that six parameters namely, distance, high intensity harsh acceleration and braking events as well as cornering events, average deceleration and mobile usage, were found to be statistically significant in the regression models.
ID | pc353 |
Presentation | |
Full Text | |
Tags | big data, driver behaviour, naturalistic driving, speed, statistical modelling, telematics |