Welcome to the InfoSci Platform
Neuro-Immune Model Based on Bio-Inspired Methods for Medical Diagnosis

Neuro-Immune Model Based on Bio-Inspired Methods for Medical Diagnosis

Fatiha Djahafi, Abdelkader Gafour
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 18
ISSN: 1941-6237|EISSN: 1941-6245|EISBN13: 9781683180647|DOI: 10.4018/IJACI.293176
Cite Article Cite Article

MLA

Djahafi, Fatiha, and Abdelkader Gafour. "Neuro-Immune Model Based on Bio-Inspired Methods for Medical Diagnosis." IJACI vol.13, no.1 2022: pp.1-18. http://doi.org/10.4018/IJACI.293176

APA

Djahafi, F. & Gafour, A. (2022). Neuro-Immune Model Based on Bio-Inspired Methods for Medical Diagnosis. International Journal of Ambient Computing and Intelligence (IJACI), 13(1), 1-18. http://doi.org/10.4018/IJACI.293176

Chicago

Djahafi, Fatiha, and Abdelkader Gafour. "Neuro-Immune Model Based on Bio-Inspired Methods for Medical Diagnosis," International Journal of Ambient Computing and Intelligence (IJACI) 13, no.1: 1-18. http://doi.org/10.4018/IJACI.293176

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this article, a hybrid bio-inspired algorithm called neuro-immune is proposed based on Multi-Layer Perceptron Neural Network (MLPNN) and the Clonal Selection Classification (CSC) principle of the Artificial Immune System (AIS) for the classifying and diagnosing of medical disease. The proposed approach consists in the first phase to code the weights and biases of MLPNN concatenation vector of the input samples into an antigen vector and to decompose it into new weights to generate population memory cells which will be applied by the processes of the CSC algorithm clone and mutate in the second phase, to optimize the accuracy class of data and updating the MLPNN weights to minimize the mean squared error. Experimental results show that the proposed hybrid neuro-immune model allows obtaining a high diagnosis performance on a set of medical data problems from the UCI repository with an improved classification accuracy compared to existing works in the literature.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.