Ranking Based Feature Selectors for Effective Data Classification
B. Amarnath, S. Balamurugan, Alias Balamurugan · 2015
Ranking is the attribute selection technique used in the pre-processing phase to emphasize the most relevant attributes which allow models of classification simpler and easy to understand. In recent years, there has been growing interest in learning to rank. It is a very important and a central task for information retrieval, such as web search engines, recommendation systems and advertisement systems. In this work we presented a comparison between several feature ranking methods used in and we considered eight ranking methods and adopted ten different learning algorithms, namely, NaiveBayes, J48, SMO, JRIP, Decision table, RandomForest, Multilayerperceptron and Kstar to test the accuracy. We also compare the results induced by several ranking methods with these algorithms. In our experiments, ranking methods with different supervised learning algorithms give quite different results for balanced accuracy. This study shows that the selection of ranking methods could be important for classification accuracy and the proposed method are able to reduce disaster impact through correctly identifying the potential risk features for disaster management.