Use of Genetic Algorithms and Clustering in the Identification of Noise

• Grant number: 09/00234-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): April 01, 2009
• Effective date (End): January 31, 2010
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: André Carlos Ponce de Leon Ferreira de Carvalho
• Grantee: Andre Luiz Billia de Miranda
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The data in Bioinformatics are known to have a lot of noise. These noises are generated for various reasons, such as the lack of data collection techniques. When used in the induction of classifiers by techniques of Machine Learning, these noisy data increases the complexity of the case obtained, as well as his time of induction, and they could worsen your performance. In this study, two techniques for elimination of noise are investigated to lessen the interference of noisy data. The purpose of this study is to compare two techniques for elimination of noise, one grouping based on data and another in genetic algorithms.