Presentation | 2020-03-09 Improvement of generalization performance in fish species discrimination and catch prediction using echo sounder images Yuto Mori, Keiji Suzuki, Masaaki Wada, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A Set-Net fishery has various problems. One of the problems is that it is difficult to cope with fishing restrictions for specific fish species. This is because we do not know the type of fish and the amount of catch until the net is lifted from the sea. In the current fishery, the images of the fish are grasped by the fish finder. A system to estimate the fish species and catch is not established. It has become clear that previous studies cannot perform learning to improve generalization performance. In this study, the problems were clarified in the learning of fish species discrimination up to now by the experiment using a training data division method and artificial echo images. In addition, the possibility of catch prediction is examined by performing multi-class classification using the created clusters. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Fish finder / Set net fishery / Clustering / Deep learning / Fish species discrimination / Fish catch prediction |
Paper # | AI2019-63 |
Date of Issue | 2020-03-01 (AI) |
Conference Information | |
Committee | AI / IPSJ-ICS / JSAI-SAI / JSAI-DOCMAS / JSAI-KBS |
---|---|
Conference Date | 2020/3/8(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Workshop of Social System and Information Technology (WSSIT20) |
Chair | Naoki Fukuta(Shizuoka Univ.) |
Vice Chair | Yuichi Sei(Univ. of Electro-Comm.) / Yuko Sakurai(AIST) |
Secretary | Yuichi Sei(Osaka Univ.) / Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) |
Assistant |
Paper Information | |
Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing / Special Interest Group on Intelligence and Complex Systems / Special Interest Group on Society and Artificial Intelligence / Special Interest Group on Data Oriented Constructive Mining and Simulation / Special Interest Group on Knowledge-Based Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Improvement of generalization performance in fish species discrimination and catch prediction using echo sounder images |
Sub Title (in English) | |
Keyword(1) | Fish finder |
Keyword(2) | Set net fishery |
Keyword(3) | Clustering |
Keyword(4) | Deep learning |
Keyword(5) | Fish species discrimination |
Keyword(6) | Fish catch prediction |
1st Author's Name | Yuto Mori |
1st Author's Affiliation | Future University Hakodate(FUN) |
2nd Author's Name | Keiji Suzuki |
2nd Author's Affiliation | Future University Hakodate(FUN) |
3rd Author's Name | Masaaki Wada |
3rd Author's Affiliation | Future University Hakodate(FUN) |
Date | 2020-03-09 |
Paper # | AI2019-63 |
Volume (vol) | vol.119 |
Number (no) | AI-469 |
Page | pp.pp.55-60(AI), |
#Pages | 6 |
Date of Issue | 2020-03-01 (AI) |