Introducing Fluctuation into Increasing Order of Symmetric Uncertainty for Consistency-Based Feature Selection
In order to select correlated and relevant features in a feature selection, several filter methods adopt a symmetric uncertainty as one of the feature ranking measures. In this paper, we introduce a fluctuation into the increasing order of the symmetric uncertainty for the consistency-based feature selection algorithms. Here, the fluctuation is an operation of transforming the sorted sequence of features to a new sequence of features. Then, we compare the selected features by the algorithms with a fluctuation with those without fluctuations.
KeywordsFluctuation Symmetric uncertainty Consistency-based feature selection algorithm Feature selection
- 5.Hall, M.A.: Correlation-based feature selection for machine learning, Ph.D thesis, Waikato University (1998)Google Scholar
- 6.Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1, 81–106 (1986)Google Scholar
- 11.Shin, K., Fernanndes, D., Miyazaki, S.: Consistency measures for feature selection: a formal definition, relative sensitivity comparison, and a fast algorithm. In: Proceedings IJCAI 2011, pp. 1491–1497. AAAI/IJCAI Press (2011)Google Scholar
- 12.Shin, K., Kuboyama, T., Hashimoto, T., Shepard, D.: Super-CWC and super-LCC: Super fast feature selection algorithms. In: Proceedings BigData 2015, pp. 1–7. IEEE (2015)Google Scholar
- 16.Zhao, Z., Liu, H.: Searching for interacting features. In: Proceedings IJCAI 2007, pp. 1156–1161. AAAI/IJCAI Press (2007)Google Scholar