NFSDED: Neuro-Fuzzy System to Support the Diagnosis of Epileptic Diseases

Background: this research approaches the development of a neuro-fuzzy system to support the diagnosis of epileptic diseases (NFSDED). Neuro-fuzzy systems are the most common type of artificial intelligence in medicine. The neuro-fuzzy system contains medical knowledge represented by rules, gathering...

Full description

Bibliographic Details
Authors: Carvalho, Lucimar Fossatti de, Carvalho, Hugo José, Rech, Ciciliana Zílio
Format: article
Status:Published version
Publication Date:2009
Country:Brasil
Institution:Universidade Federal do Rio Grande do Sul (UFRGS)
Repository:Clinical and Biomedical Research
Language:Portuguese
OAI Identifier:oai:seer.ufrgs.br:article/5101
Online Access:https://seer.ufrgs.br/index.php/hcpa/article/view/5101
Access Level:Open access
Keyword:Epilepsia
redes neurais artificiais
lógica difusa
Neurologia
Description
Summary:Background: this research approaches the development of a neuro-fuzzy system to support the diagnosis of epileptic diseases (NFSDED). Neuro-fuzzy systems are the most common type of artificial intelligence in medicine. The neuro-fuzzy system contains medical knowledge represented by rules, gathering the strength of two paradigms: artificial neural networks and fuzzy logic. Objective: the main interest of the research is to examine the applicability of the t-norms and t-conorms fuzzy arithmetical operations, implemented by fuzzy neurons. Results: show that the arithmetical operations of Einstein's Sum/Product AND/OR implemented with the fuzzy neuron proposed by Kwan-Cai obtained the highest rates of system hits, when compared to the min/max arithmetical operations