论文信息 - Credal Decision Trees to Classify Noisy Data Sets

Credal Decision Trees to Classify Noisy Data Sets

Credal Decision Trees (CDTs) are algorithms to design classifiers based on imprecise probabilities and uncertainty measures. C4.5 and CDT procedures are combined in this paper. The new algorithm builds trees for solving classification problems assuming that the training set is not fully reliable. This algorithm is especially suitable to classify noisy data sets. This is shown in the experiments.

Joaquín Abellán | Carlos Javier Mantas | J. Abellán | C. J. Mantas

[1] Ian H. Witten,et al. Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[2] Joaquín Abellán,et al. Analysis and extension of decision trees based on imprecise probabilities: Application on noisy data , 2014, Expert Syst. Appl..

[3] Janez Demsar,et al. Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[4] Alberto Maria Segre,et al. Programs for Machine Learning , 1994 .

[5] C. E. SHANNON,et al. A mathematical theory of communication , 1948, MOCO.

[6] Joaquín Abellán,et al. Uncertainty measures on probability intervals from the imprecise Dirichlet model , 2006, Int. J. Gen. Syst..

[7] P. Walley. Inferences from Multinomial Data: Learning About a Bag of Marbles , 1996 .

[8] G. Klir. Uncertainty and Information: Foundations of Generalized Information Theory , 2005 .

[9] Serafín Moral,et al. Building classification trees using the total uncertainty criterion , 2003, Int. J. Intell. Syst..

[10] Andrés R. Masegosa,et al. Bagging schemes on the presence of class noise in classification , 2012, Expert Syst. Appl..

[11] Ian Witten,et al. Data Mining , 2000 .