Neuro-fuzzy ellipsoid basis function multiple classifier for diagnosis of urinary tract infections

Authors:
E. Wadge;V. Kodogiannis;D. Tomtsis
Affiliations:
Mechatronics Group, Computer Science Dept., University of Westminster, London HA1 3TP, Uk;Mechatronics Group, Computer Science Dept., University of Westminster, London HA1 3TP, Uk;TEI of West Macedonia, Kozani, Greece
Venue:
ICCMSE '03 Proceedings of the international conference on Computational methods in sciences and engineering
Year:
2003

Citing 1
Cited 3

Radial basis function networks, regression weights, and the expectation-maximization algorithm

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Intelligent systems for the diagnosis of wireless-capsule endoscopic images

SSIP'05 Proceedings of the 5th WSEAS international conference on Signal, speech and image processing
Detecting abnormalities in capsule endoscopic images by textural description and neural networks

PCI'05 Proceedings of the 10th Panhellenic conference on Advances in Informatics
Decision support systems in Wireless Capsule Endoscopy: Revisited

Intelligent Decision Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, the use of smell in clinical diagnosis has been rediscovered due to major advances in odour sensing technology and artificial intelligence. Urinary tract infections are a serious health problem producing significant morbidity in a vast number of people each year. A newly developed "artificial nose" based on chemoresistive sensors has been employed to identify in vivo urine samples from 45 patients with suspected uncomplicated UTI who were scheduled for micro-biological analysis in a UK Health Laboratory environment. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on artificial based techniques has been developed. The implementation of an advanced hybrid neuro-fuzzy scheme and the concept of fusion of multiple classifiers dedicated to specific feature parameters has been also adopted in this study. The experimental results confirm the validity of the presented methods.