Citation

Hosokawa T, Hashimoto H, Tagawa T, Yoshida S, Nitta S. Trans. Soc. Automot. Eng. Jpn. 2009; 40(2): 519-524.

Copyright

(Copyright © 2009, Society of Automotive Engineers of Japan)

DOI

10.11351/jsaeronbun.40.519

PMID

unavailable

Abstract

The purpose of the study is to classify elderly drivers in order to clarify their driving behavior. The classification approach will help us to understand the characteristics and will lead to develop driver assistance systems and education programs in order to prevent traffic accidents of aged drivers. We first applied cluster analysis to driver parameters acquired in driving simulator and questionnaire studies. The result classified subjects into several clusters. We then performed linear discriminant analysis. Depending on the results, we can classify aged drivers with high probability. Evaluation of the linear discriminant functions also revealed characteristics of each cluster.

Language: ja

Keywords

Aged Drivers; Cluster Analysis; Driver Behavior; Driver classification; Human-machine Interface; Linerar Discriminant Analysis; Preventive Safety; Traffic Accidents