Development of driver-state estimation algorithm based on Hybrid Bayesian Network

Author

Dong Woon Ryu ; Hyeon Bin Jeong ; Sang Hun Lee ; Woon-Sung Lee ; Ji Hyun Yang

Author_Institution

Grad. Sch. of Automotive Eng., Kookmin Univ., Seoul, South Korea

fYear

2015

fDate

June 28 2015-July 1 2015

Firstpage

1282

Lastpage

1286

Abstract

In this study, we develop and evaluate an estimation algorithm of abnormal driving states (drowsiness, distraction, and workload) based on a Hybrid Bayesian Network (HBN) using multimodal information. The HBN algorithm is expected to increase transportation safety by combining merits of both the Bayesian Network and clustering algorithm. In addition, multimodal data efficacy analysis through human-in-the-loop experiments is used to enhance the performance of the driver-state estimation algorithm. Performance results obtained the lowest false alarm rate and fastest calculation speed. The false alarm rate decreased from 18.2 to 15.5%, whereas the calculation speed decreased by 4.35%.

Keywords

belief networks; data analysis; pattern clustering; road accidents; road safety; road traffic; state estimation; HBN algorithm; abnormal driver-state estimation algorithm; clustering algorithm; hybrid Bayesian network; multimodal data efficacy analysis; transportation safety; Acceleration; Algorithm design and analysis; Bayes methods; Clustering algorithms; Estimation; Sensors; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium (IV), 2015 IEEE

Conference_Location

Seoul

Type

conf

DOI

10.1109/IVS.2015.7225873

Filename

7225873