Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea)
This thesis presents an investigation into Gyrodactylus species recognition, making use of machine learning classification and feature selection techniques, and explores image feature extraction to demonstrate proof of concept for an envisaged rapid, consistent and secure initial identification of p...
Main Author: | |
---|---|
Other Authors: | , , , |
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
University of Stirling
2014
|
Subjects: | |
Online Access: | http://hdl.handle.net/1893/21734 http://dspace.stir.ac.uk/bitstream/1893/21734/3/thesis_hardbound.pdf |
id |
ftunivstirling:oai:dspace.stir.ac.uk:1893/21734 |
---|---|
record_format |
openpolar |
spelling |
ftunivstirling:oai:dspace.stir.ac.uk:1893/21734 2023-05-15T15:32:55+02:00 Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) Ali, Rozniza Hussain, Amir Bron, James Shinn, Andrew Ministry of Malaysia Education, Malaysia 2014-05-28 application/pdf http://hdl.handle.net/1893/21734 http://dspace.stir.ac.uk/bitstream/1893/21734/3/thesis_hardbound.pdf en eng University of Stirling http://hdl.handle.net/1893/21734 http://dspace.stir.ac.uk/bitstream/1893/21734/3/thesis_hardbound.pdf Gyrodactylus machine learning feature selection Active Shape Model ensemble classification Complex Network Fishes Parasites Thesis or Dissertation Doctoral Doctor of Philosophy 2014 ftunivstirling 2022-06-13T18:43:39Z This thesis presents an investigation into Gyrodactylus species recognition, making use of machine learning classification and feature selection techniques, and explores image feature extraction to demonstrate proof of concept for an envisaged rapid, consistent and secure initial identification of pathogens by field workers and non-expert users. The design of the proposed cognitively inspired framework is able to provide confident discrimination recognition from its non-pathogenic congeners, which is sought in order to assist diagnostics during periods of a suspected outbreak. Accurate identification of pathogens is a key to their control in an aquaculture context and the monogenean worm genus Gyrodactylus provides an ideal test-bed for the selected techniques. In the proposed algorithm, the concept of classification using a single model is extended to include more than one model. In classifying multiple species of Gyrodactylus, experiments using 557 specimens of nine different species, two classifiers and three feature sets were performed. To combine these models, an ensemble based majority voting approach has been adopted. Experimental results with a database of Gyrodactylus species show the superior performance of the ensemble system. Comparison with single classification approaches indicates that the proposed framework produces a marked improvement in classification performance. The second contribution of this thesis is the exploration of image processing techniques. Active Shape Model (ASM) and Complex Network methods are applied to images of the attachment hooks of several species of Gyrodactylus to classify each species according to their true species type. ASM is used to provide landmark points to segment the contour of the image, while the Complex Network model is used to extract the information from the contour of an image. The current system aims to confidently classify species, which is notifiable pathogen of Atlantic salmon, to their true class with high degree of accuracy. Finally, some concluding ... Doctoral or Postdoctoral Thesis Atlantic salmon University of Stirling: Stirling Digital Research Repository |
institution |
Open Polar |
collection |
University of Stirling: Stirling Digital Research Repository |
op_collection_id |
ftunivstirling |
language |
English |
topic |
Gyrodactylus machine learning feature selection Active Shape Model ensemble classification Complex Network Fishes Parasites |
spellingShingle |
Gyrodactylus machine learning feature selection Active Shape Model ensemble classification Complex Network Fishes Parasites Ali, Rozniza Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
topic_facet |
Gyrodactylus machine learning feature selection Active Shape Model ensemble classification Complex Network Fishes Parasites |
description |
This thesis presents an investigation into Gyrodactylus species recognition, making use of machine learning classification and feature selection techniques, and explores image feature extraction to demonstrate proof of concept for an envisaged rapid, consistent and secure initial identification of pathogens by field workers and non-expert users. The design of the proposed cognitively inspired framework is able to provide confident discrimination recognition from its non-pathogenic congeners, which is sought in order to assist diagnostics during periods of a suspected outbreak. Accurate identification of pathogens is a key to their control in an aquaculture context and the monogenean worm genus Gyrodactylus provides an ideal test-bed for the selected techniques. In the proposed algorithm, the concept of classification using a single model is extended to include more than one model. In classifying multiple species of Gyrodactylus, experiments using 557 specimens of nine different species, two classifiers and three feature sets were performed. To combine these models, an ensemble based majority voting approach has been adopted. Experimental results with a database of Gyrodactylus species show the superior performance of the ensemble system. Comparison with single classification approaches indicates that the proposed framework produces a marked improvement in classification performance. The second contribution of this thesis is the exploration of image processing techniques. Active Shape Model (ASM) and Complex Network methods are applied to images of the attachment hooks of several species of Gyrodactylus to classify each species according to their true species type. ASM is used to provide landmark points to segment the contour of the image, while the Complex Network model is used to extract the information from the contour of an image. The current system aims to confidently classify species, which is notifiable pathogen of Atlantic salmon, to their true class with high degree of accuracy. Finally, some concluding ... |
author2 |
Hussain, Amir Bron, James Shinn, Andrew Ministry of Malaysia Education, Malaysia |
format |
Doctoral or Postdoctoral Thesis |
author |
Ali, Rozniza |
author_facet |
Ali, Rozniza |
author_sort |
Ali, Rozniza |
title |
Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
title_short |
Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
title_full |
Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
title_fullStr |
Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
title_full_unstemmed |
Ensemble classification and signal image processing for genus Gyrodactylus (Monogenea) |
title_sort |
ensemble classification and signal image processing for genus gyrodactylus (monogenea) |
publisher |
University of Stirling |
publishDate |
2014 |
url |
http://hdl.handle.net/1893/21734 http://dspace.stir.ac.uk/bitstream/1893/21734/3/thesis_hardbound.pdf |
genre |
Atlantic salmon |
genre_facet |
Atlantic salmon |
op_relation |
http://hdl.handle.net/1893/21734 http://dspace.stir.ac.uk/bitstream/1893/21734/3/thesis_hardbound.pdf |
_version_ |
1766363395428188160 |