Presentation 2018-07-02
An investigation of prediction accuracy of bus delay time influenced by the amount of training data and the variation of outlier detection
Tsubasa Yamaguchi, Mansur AS, Tsunenori Mine,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Prediction of bus delay is one of crucial research tasks in the intelligent transport systems (ITS) field, and is important not only for a bus operation company, but also passengers, who want to know how many minutes a bus will be concretely delayed to get at a bus stop. In this paper, we propose methods to predict bus delay using bus probe data collected from Nov. 21st to Dec. 20th, 2013 and provided by Nishitetsu Bus company. We used several machine learning methods to build the prediction models. Wediscuss experimental results from the points that how much extents the difference of the amount of training data and the variation of outlier detection methods affect prediction accuracy of predicting bus delay.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) scheduled bus / delay time prediction / probe data / machine learning
Paper # AI2018-4
Date of Issue 2018-06-25 (AI)

Conference Information
Committee AI
Conference Date 2018/7/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An investigation of prediction accuracy of bus delay time influenced by the amount of training data and the variation of outlier detection
Sub Title (in English)
Keyword(1) scheduled bus
Keyword(2) delay time prediction
Keyword(3) probe data
Keyword(4) machine learning
1st Author's Name Tsubasa Yamaguchi
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Mansur AS
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
3rd Author's Name Tsunenori Mine
3rd Author's Affiliation Kyushu University(Kyushu Univ.)
Date 2018-07-02
Paper # AI2018-4
Volume (vol) vol.118
Number (no) AI-116
Page pp.pp.15-21(AI),
#Pages 7
Date of Issue 2018-06-25 (AI)