This paper investigates the contributing factors of the driving risk of naturalistic driving using k-means clustering and ordered logit regression. A naturalistic driving experiment is conducted in order to collect driving data on Chinese roads especially on the roads of the City of Wuhan. K-means clustering method is adopted to a group near crash events according to their driving risk. In addition, order logit regression is employed to examine the contributing factors which influence the driving risk of near-crash events. The results of this study show that five factors related to environment and driver are considered as significant ones including congested road condition, time of day, weekend, age and driving years. The findings proved insights and suggestions to transportation regulations in order to reduce crashes and make roads safer.
Examining contributing factors on driving risk of naturalistic driving using K-means clustering and ordered logit regression
2017-08-01
288890 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Driving Style Clustering using Naturalistic Driving Data
Transportation Research Record | 2019
|Transportation Research Record | 2022
|