Presentation 2012-11-07
Parameter Estimation and Active Learning in the ZRP Based on Traffic Spatiotemporal Data
Koichi KOBAYASHI, Keisuke YAMAZAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are many analyses on traffic flow models in order to elucidate the principals of traffic jams and to ease them. However, in spite of significance in application, there are few studies on estimation of the model parameter from observed traffic flow data. In the present paper, we focus on the zero range process (ZRP), the behavior of which is mathematically analysed, and we formulate its parameter estimation based on traffic spatiotemporal data. Moreover, an active learning method to minimize the estimation error by optimization of vehicle density on a road is proposed. We confirm the efficiency of the proposed algorithm by numerical simulations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) regression analysis / traffic flow models / active learning
Paper # IBISML2012-47
Date of Issue

Conference Information
Committee IBISML
Conference Date 2012/10/31(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Parameter Estimation and Active Learning in the ZRP Based on Traffic Spatiotemporal Data
Sub Title (in English)
Keyword(1) regression analysis
Keyword(2) traffic flow models
Keyword(3) active learning
1st Author's Name Koichi KOBAYASHI
1st Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Tech.()
2nd Author's Name Keisuke YAMAZAKI
2nd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Tech.
Date 2012-11-07
Paper # IBISML2012-47
Volume (vol) vol.112
Number (no) 279
Page pp.pp.-
#Pages 5
Date of Issue