Analysis of Multiple Classifiers Performance for Discretized Data in Authorship Attribution
In authorship attribution domain single classifiers are often employed in research as elements of decision system. On the other hand, there is intuitive prediction that the use of multiple classifier with fusion of their outcomes may improve the quality of the investigated system. Additionally, discretization can be applied for input data which can be beneficial for the classification accuracy. The paper presents performance analysis of some multiple classifiers basing on the majority voting rule. Ensembles were composed from eight single well known classifiers. Influence of different discretization methods on the quality of the analyzed systems was also investigated.
KeywordsMultiple classifier Ensemble classifier Majority voting Discretization Authorship attribution
The research described was performed at the Silesian University of Technology, Gliwice, Poland, in the framework of the project BK/RAu2/2017. All experiments were performed using WEKA workbench .
- 2.Baron, G.: Comparison of cross-validation and test sets approaches to evaluation of classifiers in authorship attribution domain. In: Czachórski, T., Gelenbe, E., Grochla, K., Lent, R. (eds.) Computer and Information Sciences: 31st International Symposium, ISCIS 2016, Kraków, Poland, October 27–28, 2016, Proceedings, pp. 81–89. Springer International Publishing, Cham (2016)CrossRefGoogle Scholar
- 4.Baron, G., Haężlak, K.: On approaches to discretization of datasets used for evaluation of decision systems. In: Czarnowski, I., Caballero, M.A., Howlett, J.R., Jain, C.L. (eds.) Intelligent Decision Technologies 2016: Proceedings of the 8th KES International Conference on Intelligent Decision Technologies (KES-IDT 2016) - Part II, pp. 149–159. Springer International Publishing, Cham (2016)CrossRefGoogle Scholar
- 5.Crippa, P., Curzi, A., Falaschetti, L., Turchetti, C.: Multi-class ECG beat classification based on a gaussian mixture model of Karhunen-Loéve transform. Int. J. Simul. Syst. Sci. Technol. 16(1), 2.1–2.10 (2015)Google Scholar
- 6.Dietterich, T.G.: Ensemble methods in machine learning. In: Proceedings of the 1st International Workshop on Multiple Classifier Systems, MCS 2000, pp. 1–15. Springer-Verlag, London (2000)Google Scholar
- 7.Fayyad, U.M., Irani, K.B.: Multi-interval discretization of continuousvalued attributes for classification learning. In: 13th International Joint Conference on Articial Intelligence, vol. 2, pp. 1022–1027. Morgan Kaufmann Publishers (1993)Google Scholar
- 11.Ho, T.K.: Multiple classifier combination: lessons and next steps. In: Kandel, A., Bunke, H. (eds.) Hybrid Methods in Pattern Recognition, pp. 171–198. World Scientific, Singapore (2011)Google Scholar
- 12.Jamak, A., Savatić, A., Can, M.: Principal component analysis for authorship attribution. Bus. Syst. Res. 3, 49–56 (2012). Proceedings of 11th International Conference Symposium on Operational Research in SloveniaGoogle Scholar
- 13.Kononenko, I.: On biases in estimating multi-valued attributes. In: 14th International Joint Conference on Articial Intelligence, pp. 1034–1040 (1995)Google Scholar
- 16.Stańczyk, U.: Feature evaluation by filter, wrapper, and embedded approaches. In: Stańczyk, U., Jain, L.C. (eds.) Feature Selection for Data and Pattern Recognition, pp. 29–44. Springer, Heidelberg (2015)Google Scholar
- 18.Stefanowski, J.: Multiple classifiers (2009). http://www.cs.put.poznan.pl/jstefanowski/aed/DMmultipleclassifiers.pdf. Accessed 27 Jan 2017