Feature selection is very important as data is created constantly and at an ever increasing rate, it helps to reduce the high dimensionality of some problems. Feature selection as a preprocessing step to machine learning, is effective in reducing redundancy, removing irrelevant data, increasing learning accuracy, and improving result comprehensibility. This work offers comprehensive approach to feature selection in the scope of classification problems, explaining the foundations, real application problems etc in the context of high dimensional data. First, we focus on the basis of feature selection provides an analysis on history and basic concepts. The different types of feature selection methods are discussed and finally analyze the findings.
展开▼
