Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape
The assignment of individual fish to its stock of origin is important for reliable stock assessment and fisheries management. Otolith shape is commonly used as the marker of distinct stocks in discrimination studies. Our literature review showed that the application and comparison of alternative sta...
Published in: | Canadian Journal of Fisheries and Aquatic Sciences |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/11250/2636101 https://doi.org/10.1139/cjfas-2019-0251 |
id |
ftimr:oai:imr.brage.unit.no:11250/2636101 |
---|---|
record_format |
openpolar |
spelling |
ftimr:oai:imr.brage.unit.no:11250/2636101 2023-05-15T15:27:34+02:00 Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape Smoliński, Szymon Schade, Franziska M. Berg, Florian 2019 application/pdf http://hdl.handle.net/11250/2636101 https://doi.org/10.1139/cjfas-2019-0251 eng eng urn:issn:0706-652X http://hdl.handle.net/11250/2636101 https://doi.org/10.1139/cjfas-2019-0251 cristin:1739420 Canadian Journal of Fisheries and Aquatic Sciences Journal article Peer reviewed 2019 ftimr https://doi.org/10.1139/cjfas-2019-0251 2021-09-23T20:15:18Z The assignment of individual fish to its stock of origin is important for reliable stock assessment and fisheries management. Otolith shape is commonly used as the marker of distinct stocks in discrimination studies. Our literature review showed that the application and comparison of alternative statistical classifiers to discriminate fish stocks based on otolith shape is limited. Therefore, we compared the performance of two traditional and four machine learning classifiers based on Fourier analysis of otolith shape using selected stocks of Atlantic cod (Gadus morhua) in the southern Baltic and Atlantic herring (Clupea harengus) in the western Norwegian Sea, Skagerrak and the southern Baltic Sea. Our results showed that the stocks can be successfully discriminated based on their otolith shapes. We observed significant differences in the accuracy obtained by the tested classifiers. For both species, support vector machines (SVM) resulted in the highest classification accuracy. These findings suggest that modern machine learning algorithms, like SVM, can help to improve the accuracy of fish stock discrimination systems based on the otolith shape. Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape submittedVersion Article in Journal/Newspaper atlantic cod Gadus morhua Norwegian Sea Institute for Marine Research: Brage IMR Norwegian Sea Canadian Journal of Fisheries and Aquatic Sciences 77 4 674 683 |
institution |
Open Polar |
collection |
Institute for Marine Research: Brage IMR |
op_collection_id |
ftimr |
language |
English |
description |
The assignment of individual fish to its stock of origin is important for reliable stock assessment and fisheries management. Otolith shape is commonly used as the marker of distinct stocks in discrimination studies. Our literature review showed that the application and comparison of alternative statistical classifiers to discriminate fish stocks based on otolith shape is limited. Therefore, we compared the performance of two traditional and four machine learning classifiers based on Fourier analysis of otolith shape using selected stocks of Atlantic cod (Gadus morhua) in the southern Baltic and Atlantic herring (Clupea harengus) in the western Norwegian Sea, Skagerrak and the southern Baltic Sea. Our results showed that the stocks can be successfully discriminated based on their otolith shapes. We observed significant differences in the accuracy obtained by the tested classifiers. For both species, support vector machines (SVM) resulted in the highest classification accuracy. These findings suggest that modern machine learning algorithms, like SVM, can help to improve the accuracy of fish stock discrimination systems based on the otolith shape. Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape submittedVersion |
format |
Article in Journal/Newspaper |
author |
Smoliński, Szymon Schade, Franziska M. Berg, Florian |
spellingShingle |
Smoliński, Szymon Schade, Franziska M. Berg, Florian Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
author_facet |
Smoliński, Szymon Schade, Franziska M. Berg, Florian |
author_sort |
Smoliński, Szymon |
title |
Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
title_short |
Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
title_full |
Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
title_fullStr |
Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
title_full_unstemmed |
Assessing the performance of statistical classifiers to discriminate fish stocks using Fourier analysis of otolith shape |
title_sort |
assessing the performance of statistical classifiers to discriminate fish stocks using fourier analysis of otolith shape |
publishDate |
2019 |
url |
http://hdl.handle.net/11250/2636101 https://doi.org/10.1139/cjfas-2019-0251 |
geographic |
Norwegian Sea |
geographic_facet |
Norwegian Sea |
genre |
atlantic cod Gadus morhua Norwegian Sea |
genre_facet |
atlantic cod Gadus morhua Norwegian Sea |
op_source |
Canadian Journal of Fisheries and Aquatic Sciences |
op_relation |
urn:issn:0706-652X http://hdl.handle.net/11250/2636101 https://doi.org/10.1139/cjfas-2019-0251 cristin:1739420 |
op_doi |
https://doi.org/10.1139/cjfas-2019-0251 |
container_title |
Canadian Journal of Fisheries and Aquatic Sciences |
container_volume |
77 |
container_issue |
4 |
container_start_page |
674 |
op_container_end_page |
683 |
_version_ |
1766357984000081920 |