Genetic Algorithm Based Pre-Processing Strategy for High Dimensional Micro-Array Gene Classification

Discretization is one of the popular pre-processing techniques that helps a learner overcome the difficulty in handling the wide range of continuous-valued attributes. The objective of this chapter is to explore the possibilities of performance improvement in large dimensional biomedical data with the alliance of machine learning and evolutionary algorithms to design effective healthcare systems. To accomplish the goal, the model targets the preprocessing phase and developed framework based on a Fisher Markov feature selection and evolutionary based binary discretization (EBD) for a microarray gene expression classification. Several experiments were conducted on publicly available microarray gene expression datasets, including colon tumors, and lung and prostate cancer. The performance is evaluated for accuracy and standard deviations, and is also compared with the other state-of-the-art techniques. The experimental results show that the EBD algorithm performs better when compared to other contemporary discretization techniques.