Presentation 2009-07-13
Estimation of Driving State by Modeling Brake Pressure Signails
Hiroki MIMA, Kazushi IKEDA, Tomohiro SHIBATA, NAOKI Fukaya, Kentaro HITOMI, Takashi BANDO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is important for a driver-assist system to know how a driver is. The paper proposes two methods for estimating a driver's phase, applying machine learning techniques to the sequences of the M/C pressure of the brake. One models the set of the signals at each time with a mixture of Gaussians, where a Gaussian corresponds to a phase. The other classifies a segment of the brake sequence to one of the hidden Markov models, each of which represents a phase. These methods are consistent with each other for the collected data in an unconstrained drive.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Driver behavior / ITS / Hidden Marcov Model
Paper # NLP2009-23,NC2009-16
Date of Issue

Conference Information
Committee NLP
Conference Date 2009/7/6(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of Driving State by Modeling Brake Pressure Signails
Sub Title (in English)
Keyword(1) Driver behavior
Keyword(2) ITS
Keyword(3) Hidden Marcov Model
1st Author's Name Hiroki MIMA
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Kazushi IKEDA
2nd Author's Affiliation Nara Institute of Science and Technology
3rd Author's Name Tomohiro SHIBATA
3rd Author's Affiliation Nara Institute of Science and Technology
4th Author's Name NAOKI Fukaya
4th Author's Affiliation DENSO CORPORATION
5th Author's Name Kentaro HITOMI
5th Author's Affiliation DENSO CORPORATION
6th Author's Name Takashi BANDO
6th Author's Affiliation DENSO CORPORATION
Date 2009-07-13
Paper # NLP2009-23,NC2009-16
Volume (vol) vol.109
Number (no) 124
Page pp.pp.-
#Pages 5
Date of Issue