MeLiF+: Optimization of Filter Ensemble Algorithm with Parallel Computing
Search of algorithms ensemble – that is, best algorithms combination is common used approach in machine learning. MeLiF algorithm uses this technique for filter feature selection. In our research we proposed parallel version of this algorithm and showed that it is not only improves algorithm performance significantly, but also improves feature selection quality.
KeywordsFeature selection Variable selection Attribute selection Ensemble learning Feature filters Metrics aggregation MeLiF Parallel computing
Authors would like to thank Julia Ugarkina and Andrey Filchenkov for useful comments and proofreading. This work was financially supported by the Government of Russian Federation, Grant 074-U01.
- 2.Auffarth, B., López, M., Cerquides, J.: Comparison of redundancy and relevance measures for feature selection in tissue classification of CT images. In: Perner, P. (ed.) ICDM 2010. LNCS, vol. 6171, pp. 248–262. Springer, Heidelberg (2010)Google Scholar
- 9.Filchenkov, A., Dolganov, V., Smetannikov, I.: Pca-based algorithm for constructing ensembles of feature ranking filters. In: Proceedings of ESANN Conference, pp. 201–206 (2015)Google Scholar
- 13.Smetannikov, I., Filchenkov, A.: MeLiF: filter ensemble learning algorithm for gene selection. In: Advanced Science Letters. American Scientific Publisher (2016, to appear)Google Scholar
- 14.Waikato, T.U.: Weka 3: Data Mining Software in Java (2016). http://www.cs.waikato.ac.nz/ml/weka/. Accessed 7 May 2016