Retargeting PHM tools: from industrial to medical field

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 22, 2020
Abir Belaala Zeina Al Masry Labib Sadek Terrissa Noureddine Zerhouni

Abstract

Prognostics and Health Management (PHM) approach, and theoretical models have had great success for industrial systems. Therefore, this accomplishment motivates us to think about potential extension of the PHM approach in such area as the medicine. The aim of this paper is to apply an adaptation of a PHM model from fault diagnosis of aircraft engine to diagnosis human heart disease. For that adaptation, an algorithm for retargeting extreme learning machine (ID-RELM) is applied. The complete process from data pre-processing to classification is developed. Numerical results using heart disease benchmark dataset showed that the combination of random forest and ID-RELM provides the highest classification accuracy and outperforms other algorithms in classifying this chronic disease status.

How to Cite

Belaala, A., Al Masry, Z. ., Terrissa, L. S. ., & Zerhouni , N. . (2020). Retargeting PHM tools: from industrial to medical field. PHM Society European Conference, 5(1), 7. https://doi.org/10.36001/phme.2020.v5i1.1232
Abstract 1098 | PDF Downloads 281

##plugins.themes.bootstrap3.article.details##

Keywords

Prognostics and Health Management (PHM), Improved Dragging Regularized extreme learning machine (ID-RELM), Random Forest (RF), Heart disease, Computer Aided Diagnosis ( CAD)

Section
Technical Papers