Presentation 2019-05-30
Daily Fish Catch Forecasting For Fixed Shore Net Fishing Using State Space Model Describing Probabilistic Behavior of Fish Inside Net
Yuya Kokaki, Naohiro Tawara, Tetsunori Kobayashi, Kazuo Hashimoto, Masayoshi Hukushima, Akira Idoue, Ogawa Tetsuji,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A state space model that incorporates knowledge on fixed shore net fishing was developed and suc- cessfully applied to daily fish catch forecasting. Accurate daily fish catch prediction can support fishery workers with their decision-making and efficient operation. The present study attempts to develop a fish catch forecasting method using a state space model that describes probabilistic behaviors of fish inside the net. In this method, the parameter estimation and forecasting are sequentially carried out using Hamiltonian Monte Carlo method. The experimental comparisons conducted using actual fish catch data and public meteorological data demonstrated that the developed forecasting system suitable for fixed shore net fishing reduced significant prediction errors over the systems using legacy state space models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hamiltonian Monte Carlo / State space model / Fixed shore net fishing / Fish catch forecasting
Paper # PRMU2019-3
Date of Issue 2019-05-23 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2019/5/30(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII)
Vice Chair Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.)
Secretary Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.)
Assistant Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Daily Fish Catch Forecasting For Fixed Shore Net Fishing Using State Space Model Describing Probabilistic Behavior of Fish Inside Net
Sub Title (in English)
Keyword(1) Hamiltonian Monte Carlo
Keyword(2) State space model
Keyword(3) Fixed shore net fishing
Keyword(4) Fish catch forecasting
1st Author's Name Yuya Kokaki
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Naohiro Tawara
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Tetsunori Kobayashi
3rd Author's Affiliation Waseda University(Waseda Univ.)
4th Author's Name Kazuo Hashimoto
4th Author's Affiliation Waseda University(Waseda Univ.)
5th Author's Name Masayoshi Hukushima
5th Author's Affiliation KDDI Research, Inc.(KDDI Research)
6th Author's Name Akira Idoue
6th Author's Affiliation KDDI Research, Inc.(KDDI Research)
7th Author's Name Ogawa Tetsuji
7th Author's Affiliation Waseda University(Waseda Univ.)
Date 2019-05-30
Paper # PRMU2019-3
Volume (vol) vol.119
Number (no) PRMU-64
Page pp.pp.13-18(PRMU),
#Pages 6
Date of Issue 2019-05-23 (PRMU)