Feature selection techniques for prediction of warning level in aircraft accidents

This paper focuses on different feature selection techniques applied on the huge number of datasets of an airline databases to understand and clean the dataset. CFS Subset Evaluator, Consistency Subset Evaluator, Gain Ratio feature evaluator, Information Gain Attribute Evaluator, OneR feature evaluator, Principal Components Attribute Transformer (PCA), ReliefF Attribute Evaluator and Symmetrical Uncertainty Attribute Evaluator are used in this analysis in order to reduce the dataset. Also the Decision Tree classifier techniques of data mining are used to predict the warning level of the component as the class attribute in aircraft accidents for Risk and Safety. For this intention Weka software tools are used. This study also proved that the Principal Components Attribute Transformer would performance better than other attribute evaluators on airline data. This work may be useful for Aviation Company to make better prediction.