Transactions on Mass-Data Analysis of Images and Signals (ISSN:1868-6451)
Volume 1 - Number 1 - September 2009 - Pages 76-88
Analysis of Massive Data in Biology using Hyperplane-based Genetic Algorithms
C. To and T. D. Pham
ADFA School of Information Technology and Electrical Engineering, The University of New South Wales, Canberra ACT 2600, Australia
Abstract
Single class problem is a novel detection method in pattern recognition. In this paper, we present an algorithm based on genetic algorithms for disease classification using bio-mass data. The single class problem is modeled by nonlinear programming. In order to solve the nonlinear programming problem, genetic algorithms have been used for global searching of an optimal solution. We applied the proposed method to four real datasets that include proteomics, transcriptomics, and two breast cancer diseases. Obtained results are found superior in comparison with six other well-known methods.