Presentation 2020-10-20
System operation for estimation of road condition using tire vibration data
Satoru Kawamata, Tomoko Matsui, Mitsuhiro Nishida, Takeshi Masago,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In a system that estimates the road surface condition from tire sensor data and supports safe driving, it is crucial to deal with three problems, (1) robust, high-speed and lightweight calculation of feature quantities from tire sensor data, (2) data selection, and (3) continuous update of the road surface condition classifier to respond to changes in tires over time. In this paper, we apply a feature extraction method that is robust against changes in speed and road surface unevenness, a data selection method by kernel herding, and a semi-supervised learning method. In the experiments with two types of road surface conditions, dry and wet, the effectiveness of these methods is examined.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Intelligent tire / road surface condition / kernel herding / semi-supervised learning
Paper # IBISML2020-10
Date of Issue 2020-10-13 (IBISML)

Conference Information
Committee IBISML
Conference Date 2020/10/20(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Organized Sessions on Frontiers of Machine Learning and General Sessions
Chair Ichiro Takeuchi(Nagoya Inst. of Tech.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(AIST) / Koji Tsuda(NTT)
Assistant Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) System operation for estimation of road condition using tire vibration data
Sub Title (in English)
Keyword(1) Intelligent tire
Keyword(2) road surface condition
Keyword(3) kernel herding
Keyword(4) semi-supervised learning
1st Author's Name Satoru Kawamata
1st Author's Affiliation Bridgestone(Bridgestone)
2nd Author's Name Tomoko Matsui
2nd Author's Affiliation Institute of Statistical Mathematics(ISM)
3rd Author's Name Mitsuhiro Nishida
3rd Author's Affiliation Bridgestone(Bridgestone)
4th Author's Name Takeshi Masago
4th Author's Affiliation Bridgestone(Bridgestone)
Date 2020-10-20
Paper # IBISML2020-10
Volume (vol) vol.120
Number (no) IBISML-195
Page pp.pp.14-19(IBISML),
#Pages 6
Date of Issue 2020-10-13 (IBISML)