Presentation 2018-08-27
Development of tropical-cyclone detection method using machine learning
Takuro Kanasaki, Hironori Fudeyasu, Koki Kase, Daisuke Matsuoka, Ryuji Yoshida,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This study developed typhoon position detection models using machine learning and Himawari-8 cloud images and verified how their detection accuracy changed depending on learning setting and typhoon case. As a result, the detection accuracy of models using the LBP (Local Binary Pattern) feature amount setting is higher than that using the HAAR - LIKE feature amount setting. Note that the detection accuracy of models changed with the difference of typhoon characteristics.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) typhoon position / machine learning / Himawari-8
Paper # AI2018-15
Date of Issue 2018-08-20 (AI)

Conference Information
Committee AI
Conference Date 2018/8/27(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) Development of tropical-cyclone detection method using machine learning
Sub Title (in English)
Keyword(1) typhoon position
Keyword(2) machine learning
Keyword(3) Himawari-8
1st Author's Name Takuro Kanasaki
1st Author's Affiliation Yokohama National University(YNU)
2nd Author's Name Hironori Fudeyasu
2nd Author's Affiliation Yokohama National University(YNU)
3rd Author's Name Koki Kase
3rd Author's Affiliation Graduate School of education Yokohama National University(YNU)
4th Author's Name Daisuke Matsuoka
4th Author's Affiliation Japan Agency for Marine-Earth Science and Technology(JAMSTEC)
5th Author's Name Ryuji Yoshida
5th Author's Affiliation RIKEN(RIKEN)
Date 2018-08-27
Paper # AI2018-15
Volume (vol) vol.118
Number (no) AI-197
Page pp.pp.13-18(AI),
#Pages 6
Date of Issue 2018-08-20 (AI)