DocumentCode
181644
Title
Analysis of temporal vehicle behaviors using bag of dynamical systems
Author
Sannomiya, Chihiro ; Kurihara, Keiichirou ; Tanaka, Yuichi ; Kashiwakura, Toshiki ; Nawa, Kazunari
Author_Institution
Tech. Res. Div., Toyota InfoTechnology Center Co., Ltd., Tokyo, Japan
fYear
2014
fDate
8-11 June 2014
Firstpage
1396
Lastpage
1401
Abstract
In this report, we have proposed a new data mining method to analyze vehicles´ temporal behaviors. The Bag-of-Systems (BoS) representation was adopted to analyze the temporal behavior signals. The BoS representation was originally used for analyzing motion data from video image. We have extended the model of dynamical systems to analyze vehicles´ temporal behaviors of both travel direction and rotational direction. By using this method, a symbol sequence was obtained for each trip. Therefore we could apply various data mining method to the obtained sequences. As for the first trial, a clustering method was applied to the sequences and characteristic segments to know the events happened on the vehicles were successfully found.
Keywords
data mining; mechanical engineering computing; pattern clustering; road vehicles; traffic engineering computing; vehicle dynamics; BoS representation; bag of dynamical systems; bag-of-systems representation; clustering method; data mining; rotational direction; symbol sequence; temporal behavior signals; travel direction; vehicle temporal behaviors; Acceleration; Image segmentation; Roads; Vectors; Vehicle dynamics; Vehicles;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Vehicles Symposium Proceedings, 2014 IEEE
Conference_Location
Dearborn, MI
Type
conf
DOI
10.1109/IVS.2014.6856441
Filename
6856441
Link To Document