A Fuzzy Hybrid Intelligent System for Human Semen Analysis

Authors:
Esmeralda Ramos;Haydemar Núñez;Roberto Casañas
Affiliations:
Laboratorio de Inteligencia Artificial, Centro de Ingeniería de Software y Sistemas Escuela de Computación, Facultad de Ciencias, Universidad Central de Venezuela,;Laboratorio de Inteligencia Artificial, Centro de Ingeniería de Software y Sistemas Escuela de Computación, Facultad de Ciencias, Universidad Central de Venezuela,;Cátedra de Física y Análisis Instrumental, Escuela de Bioanálisis, Facultad de Medicina Universidad Central de Venezuela,
Venue:
IBERAMIA '08 Proceedings of the 11th Ibero-American conference on AI: Advances in Artificial Intelligence
Year:
2008

Citing 7
Cited 0

Case-based reasoning: foundational issues, methodological variations, and system approaches

AI Communications
Instance Pruning Techniques

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Integrating Hybrid Rule-Based with Case-Based Reasoning

ECCBR '02 Proceedings of the 6th European Conference on Advances in Case-Based Reasoning
Discovering Knowledge in Data: An Introduction to Data Mining

Discovering Knowledge in Data: An Introduction to Data Mining
Integrations with case-based reasoning

The Knowledge Engineering Review
Integrating data mining with case-based reasoning for chronic diseases prognosis and diagnosis

Expert Systems with Applications: An International Journal
Case-based reasoning for antibiotics therapy advice: an investigation of retrieval algorithms and prototypes

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a fuzzy hybrid system to support the human semen analysis, that integrates the case and rule based reasoning. The module of case based reasoning uses a recovery scheme in two phases: first, recovery rules are used to generate a spermatic classification; second, the k-nearest neighbor technique (KNN) with a fuzzy similarity measure, is used to determine the degrees of severity to each alteration. In order to complete the solution of the new case, a module of rule based reasoning gives suggestions and observations from variables that do no affect this classification. Experimental results obtained show that the system provides a good percentage of successes; therefore it could be used as an instrument to support the decision-making process that carries out the professionals of this domain.