Open Access

ARTICLE

A Combined Approach of Principal Component Analysis and Support Vector Machine for Early Development Phase Modeling of Ohrid Trout (Salmo Letnica)

by Sunil Kr. Jha^1,*, Ivan Uzunov², Xiaorui Zhang¹

1 School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2 Faculty of Computer Science and Engineering, University of Information Science and Technology, Ohrid, 6000, Republic of Macedonia

* Corresponding Author: Sunil Kr. Jha. Email:

Computer Modeling in Engineering & Sciences 2021, 126(3), 991-1009. https://doi.org/10.32604/cmes.2021.011821

Received 30 May 2020; Accepted 04 December 2020; Issue published 19 February 2021

Abstract

Ohrid trout (Salamo letnica) is an endemic species of fish found in Lake Ohrid in the Former Yugoslav Republic of Macedonia (FYROM). The growth of Ohrid trout was examined in a controlled environment for a certain period, thereafter released into the lake to grow their natural population. The external features of the fish were measured regularly during the cultivation period in the laboratory to monitor their growth. The data mining methods-based computational model can be used for fast, accurate, reliable, automatic, and improved growth monitoring procedures and classification of Ohrid trout. With this motivation, a combined approach of principal component analysis (PCA) and support vector machine (SVM) has been implemented for the visual discrimination and quantitative classification of Ohrid trout of the experimental and natural breeding and their growth stages. The PCA results in better discrimination of breeding categories of Ohrid trout at different development phases while the maximum classification accuracy of 98.33% was achieved using the combination of PCA and SVM. The classification performance of the combination of PCA and SVM has been compared to combinations of PCA and other classification methods (multilayer perceptron, naïve Bayes, random committee, decision stump, random forest, and random tree). Besides, the classification accuracy of multilayer perceptron using the original features has been studied.

---

Keywords

---