Feature extraction and classification for multiple species of Gyrodactylus ectoparasite

Rozniza Ali, Amir Hussain, Mustafa Man


Active Shape Models (ASM) are applied to the attachment hooks of several species of Gyrodactylus, including the notifiable pathogen G. salaris, to assign each species to its truespecies type. Linear (i.e. LDA and K-NN) andnon-linear (i.e. MLP and SVM) models are used to classify Gyrodactylus species. Speciesof Gyrodactylus, ectoparasitic monogenetic flukes of fish, are difficult to discriminate andidentify according to morphology alone and their speciation currently requires taxonomicexpertise. The current exercise sets out to confidently classify species, which in this example includes a species which is a notifiable pathogen of Atlantic salmon, to their true classwith a high degree of accuracy. The findings from the current exercise demonstrates thatimport of ASM data into a MLP classifier, outperforms several other methods of classification (i.e. LDA, K-NN and SVM) that were assessed, with an average classification accuracyof 98.72%.

DOI: http://dx.doi.org/10.11591/telkomnika.v13i3.7096


machine learning, feature extraction

Full Text:



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License