Cooperative speed harmonization for efficient road utilization

Author: 
Englund, C., Chen, L., Voronov, A.
Type of publication: 
Conference item
Abstract: 

This paper presents a novel approach to modelling visual distraction of bicyclists. A unique bicycle simulator equipped with sensors capable of capturing the behaviour of the bicyclist is presented. Statistics of the measured speed, head movements, steering angle and road position along with questionnaire data are used to model the self-assessed distraction level of the bicyclist. Data mining techniques based on Random forests, Support vector machines and Neural networks are used for the modelling task. The variable selection procedure based on Random forests is able to both improve the modelling performance and name the most distinguish- ing variables. By combining the Random forest-based variable selection and Support vector machine-based modelling technique the best overall performance i achieved.

Year: 
2014
Published in: 
Nets4Cars