摘要：Data mining played vital role in comprehending, analyzing, understanding and interpreting microarray technology expression data. That includes search for genes that had similar or correlated patterns of expression. For that, the feature selection was one of the frequently used important techniques for data preprocessing. Many feature selection algorithms had been developed. Yet the persisting problem was in selecting optimal subset of features from the colon tumor dataset. The use of feature selection reduced the number of features, removed irrelevant, redundant or noise data thereby improving the accuracy, efficiency, applicability and understandability of the learning process. Dimensionality reduction and feature subset selection were important components of classification techniques. In this study, the authors presented a comparative study of existing six feature selection methods and the proposed two algorithms of their own.
