Presentation 2005/9/10
Modeling of Individual Characteristics in Driving Signals
Koji OZAWA, Toshihiro WAKITA, Chiyomi MIYAJIMA, Katsunobu ITOU, Kazuya TAKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Driving behavior modeling using such driving signals as velocity, following distance, and gas or brake pedal operations, has been investigated. Driving behaviors are different among drivers, and research on driver modeling has also been carried out from several points of view in cognitive and engineering approaches. In this paper, assuming that driving behavior can be modeled using a source-filter model, we model driver's characteristics in driving behaviors with a Gaussian mixture model (GMM) using cepstral features obtained through spectral analysis of gas pedal operation signals. The GMM driver model based on cepstral features is evaluated in driver identification experiments and compared with a conventional GMM driver model that uses raw driving signals without spectral analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Driver's behavioral signal / Driving simulator / Person identification / Gaussian mixture model (GMM) / Cepstral analysis
Paper # SIP2005-95,SIS2005-44,SP2005-77
Date of Issue

Conference Information
Committee SIS
Conference Date 2005/9/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Modeling of Individual Characteristics in Driving Signals
Sub Title (in English)
Keyword(1) Driver's behavioral signal
Keyword(2) Driving simulator
Keyword(3) Person identification
Keyword(4) Gaussian mixture model (GMM)
Keyword(5) Cepstral analysis
1st Author's Name Koji OZAWA
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Toshihiro WAKITA
2nd Author's Affiliation Graduate School of Information Science, Nagoya University:Toyota Central R&D Labs.
3rd Author's Name Chiyomi MIYAJIMA
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
4th Author's Name Katsunobu ITOU
4th Author's Affiliation Graduate School of Information Science, Nagoya University
5th Author's Name Kazuya TAKEDA
5th Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2005/9/10
Paper # SIP2005-95,SIS2005-44,SP2005-77
Volume (vol) vol.105
Number (no) 295
Page pp.pp.-
#Pages 6
Date of Issue