An evolutionary approach to feature function generation in application to biomedical image patterns

Authors:
Pei Fang Guo;Prabir Bhattacharya
Affiliations:
Concordia University, Montreal, PQ, Canada;Concordia University, Montreal, PQ, Canada
Venue:
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Year:
2009

Citing 3
Cited 2

Classification algorithms

Classification algorithms
Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Machine Learning

Machine Learning

The unconstrained automated generation of cell image features for medical diagnosis

Proceedings of the 14th annual conference on Genetic and evolutionary computation
Detection of protein conformation defects from fluorescence microscopy images

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A mechanism involving evolutionary genetic programming (GP) and the expectation maximization algorithm (EM) is proposed to generate feature functions, based on the primitive features, for an image pattern recognition system on the diagnosis of the disease OPMD. Experiments show that the propose algorithm achieves an average performance of 90.20% recognition rate on diagnosis, while reducing the number of feature dimensions from 11 primitive features to the space of a single generated feature.