ADAPTIVE CLASSIFICATION ALGORITHMS FOR PREDICTING THE SYMPTOMS OF IMPENDING HEART, KIDNEY AND LIVER FAILURES BASED ON MEASURABLE BLOOD- RELATED PARAMETERS

Vincent, A. AKPAN and Oluwatosin, T. OMOTEHINWA and Agbogun, J. B. (2019) ADAPTIVE CLASSIFICATION ALGORITHMS FOR PREDICTING THE SYMPTOMS OF IMPENDING HEART, KIDNEY AND LIVER FAILURES BASED ON MEASURABLE BLOOD- RELATED PARAMETERS. In: Ibadan Conference on Biomedical Engineering ICBME 2019.

[img] Text
Adaptive Algos for HKL Symptoms Prediction (1).pdf

Download (644kB)

Abstract

The major causes of death across the world have been closely link to heart, kidney and liver related diseases. An early prediction and classification of the symptoms of such disease could facilitate the treatment of such disease. Thus, an hybrid adaptive neural-fuzzy algorithm based on adaptive resonant theory (HANFA-ART) with adaptive clustering for classification has been proposed in this paper. The proposed HANFA-ART classification algorithm has been applied to investigate the symptoms of impending heart, kidney and liver failures based on measurable blood-related parameters obtained from hospitals in Akure, Ondo State - Nigeria. A total of 5888 data set with 16 attributes each for 368 patients collected from 4 hospitals have been used for this investigation. Comparison of the proposed HANFA-ART algorithm with neural-fuzzy classifier trained with the modified error back-propagation with momentum (M-EBPM) algorithm shows the efficiency and superior performance of the proposed HANFA-ART algorithm for correct classification and prediction of the symptoms of impending heart, kidney and liver failure.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QM Human anatomy
Divisions: Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User: mrs chioma hannah
Date Deposited: 03 Jan 2023 09:17
Last Modified: 03 Jan 2023 09:17
URI: http://eprints.gouni.edu.ng/id/eprint/3946

Actions (login required)

View Item View Item