Fishing Spot Estimation by Clustering of Sea Temperature Pattern

Masaaki IIYAMA  Kei ZHAO  Atsushi HASHIMOTO  Hidekazu KASAHARA  Michihiko MINOH  

D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)   Vol.J101-D   No.8   pp.1070-1078
Publication Date: 2018/08/01
Online ISSN: 1881-0225
Type of Manuscript: Special Section PAPER (Special Section on Meeting on Image Recognition and Understanding 2017)
spectral clustering,  climate data,  fishery application,  

Full Text(in Japanese): PDF(1.9MB)
>>Buy this Article

This paper presents a new applications of pattern recognition – Fishery application –, and proposes a clustering-based method for estimating good fishing spots from sea temperature map. The proposed method does not estimate the fish amount but estimates probability distribution of fish amount. We apply spectral clustering to the sea temperature pattern and calculate the probability distribution for each cluster. Experimental results with flying squid fishery data show that the proposed method outperforms the state-of-the-art method.