Thursday 25th of April 2024
 

Diagnosis of Fish Diseases Using Artificial Neural Networks


J.N.S. Lopes, A.N.A. Gonçalves, R.Y. Fujimoto and J.C.C. Carvalho

Artificial neural networks (ANNs) are computational intelligence techniques, which are used in many applications, such as disease diagnosis. The objective of this study was to evaluate two artificial neural networks created for the diagnosis of diseases in fish caused by protozoa and bacteria. As a classification system, ANNs are an important tool for decision-making in disease diagnosis. A back-propagation feed-forward was selected, with two layers, sigmoid and linear activation functions, and the Levenberg -Marquardat algorithm, for the training of the ANNs. The results of the application of these neural networks for the diagnosis of fish diseases based on test cases indicated a 97% success rate for the classification of both bacterial and protozoan diseases.

Keywords: Artificial Neural Networks, Fish Disease Diagnosis, Feed-forward back-propagation network, Artificial Intelligence, and Decision Support Systems

Download Full-Text


ABOUT THE AUTHORS

J.N.S. Lopes
Programa de Pós-graduação em Biologia Ambiental, Universidade Federal do Pará - Bragança, Pará, Brazil

A.N.A. Gonçalves
Programa de Pós-graduação em Genética e Biologia Molecular – com Ênfase em Bioinformática, Universidade Federal do Pará - Belém, Pará, Brazil

R.Y. Fujimoto
Programa de Pós-graduação em Biologia Ambiental e Docente da Faculdade de Engenharia de Pesca, Universidade Federal do Pará Bragança, Pará, Brazil

J.C.C. Carvalho
Docente da Faculdade de Engenharia de Pesca, Universidade Federal do Pará - Bragança, Pará, Brazil


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »