Sequential Fish Catch Forecasting Using Bayesian State Space Models

Yuya Kokaki, Naohiro Tawara, Tetsunori Kobayashi, Kazuo Hashimoto, Tetsuji Ogawa

研究成果: Conference contribution

抄録

A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

元の言語English
ホスト出版物のタイトル2018 24th International Conference on Pattern Recognition, ICPR 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ776-781
ページ数6
2018-August
ISBN(電子版)9781538637883
DOI
出版物ステータスPublished - 2018 11 26
イベント24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
継続期間: 2018 8 202018 8 24

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
China
Beijing
期間18/8/2018/8/24

Fingerprint

Fish
Fisheries
Hamiltonians
Decision trees
Parameter estimation
Monte Carlo methods
Decision making

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

これを引用

Kokaki, Y., Tawara, N., Kobayashi, T., Hashimoto, K., & Ogawa, T. (2018). Sequential Fish Catch Forecasting Using Bayesian State Space Models. : 2018 24th International Conference on Pattern Recognition, ICPR 2018 (巻 2018-August, pp. 776-781). [8546069] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8546069

Sequential Fish Catch Forecasting Using Bayesian State Space Models. / Kokaki, Yuya; Tawara, Naohiro; Kobayashi, Tetsunori; Hashimoto, Kazuo; Ogawa, Tetsuji.

2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 776-781 8546069.

研究成果: Conference contribution

Kokaki, Y, Tawara, N, Kobayashi, T, Hashimoto, K & Ogawa, T 2018, Sequential Fish Catch Forecasting Using Bayesian State Space Models. : 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻. 2018-August, 8546069, Institute of Electrical and Electronics Engineers Inc., pp. 776-781, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 18/8/20. https://doi.org/10.1109/ICPR.2018.8546069
Kokaki Y, Tawara N, Kobayashi T, Hashimoto K, Ogawa T. Sequential Fish Catch Forecasting Using Bayesian State Space Models. : 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 776-781. 8546069 https://doi.org/10.1109/ICPR.2018.8546069
Kokaki, Yuya ; Tawara, Naohiro ; Kobayashi, Tetsunori ; Hashimoto, Kazuo ; Ogawa, Tetsuji. / Sequential Fish Catch Forecasting Using Bayesian State Space Models. 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 776-781
@inproceedings{6e61f3e1905d4ebb95f05d0242a393cf,
title = "Sequential Fish Catch Forecasting Using Bayesian State Space Models",
abstract = "A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.",
author = "Yuya Kokaki and Naohiro Tawara and Tetsunori Kobayashi and Kazuo Hashimoto and Tetsuji Ogawa",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8546069",
language = "English",
volume = "2018-August",
pages = "776--781",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Sequential Fish Catch Forecasting Using Bayesian State Space Models

AU - Kokaki, Yuya

AU - Tawara, Naohiro

AU - Kobayashi, Tetsunori

AU - Hashimoto, Kazuo

AU - Ogawa, Tetsuji

PY - 2018/11/26

Y1 - 2018/11/26

N2 - A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

AB - A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

UR - http://www.scopus.com/inward/record.url?scp=85059747873&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059747873&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8546069

DO - 10.1109/ICPR.2018.8546069

M3 - Conference contribution

AN - SCOPUS:85059747873

VL - 2018-August

SP - 776

EP - 781

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -