8 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 8 / 8
Yayın Parallel univariate decision trees(Elsevier B.V., 2007-05-01) Yıldız, Olcay Taner; Dikmen, OnurUnivariate decision tree algorithms are widely used in data mining because (i) they are easy to learn (ii) when trained they can be expressed in rule based manner. In several applications mainly including data mining, the dataset to be learned is very large. In those cases it is highly desirable to construct univariate decision trees in reasonable time. This may be accomplished by parallelizing univariate decision tree algorithms. In this paper, we first present two different univariate decision tree algorithms C4.5 and univariate linear discriminant tree. We show how to parallelize these algorithms in three ways: (i) feature based; (ii) node based; (iii) data based manners. Experimental results show that performance of the parallelizations highly depend on the dataset and the node based parallelization demonstrate good speedups.Yayın VC-dimension of univariate decision trees(IEEE-INST Electrical Electronics Engineers Inc, 2015-02-25) Yıldız, Olcay TanerIn this paper, we give and prove the lower bounds of the Vapnik-Chervonenkis (VC)-dimension of the univariate decision tree hypothesis class. The VC-dimension of the univariate decision tree depends on the VC-dimension values of its subtrees and the number of inputs. Via a search algorithm that calculates the VC-dimension of univariate decision trees exhaustively, we show that our VC-dimension bounds are tight for simple trees. To verify that the VC-dimension bounds are useful, we also use them to get VC-generalization bounds for complexity control using structural risk minimization in decision trees, i.e., pruning. Our simulation results show that structural risk minimization pruning using the VC-dimension bounds finds trees that are more accurate as those pruned using cross validation.Yayın On the feature extraction in discrete space(Elsevier Sci Ltd, 2014-05) Yıldız, Olcay TanerIn many pattern recognition applications, feature space expansion is a key step for improving the performance of the classifier. In this paper, we (i) expand the discrete feature space by generating all orderings of values of k discrete attributes exhaustively, (ii) modify the well-known decision tree and rule induction classifiers (ID3, Quilan, 1986 [1] and Ripper, Cohen, 1995 [2]) using these orderings as the new attributes. Our simulation results on 15 datasets from UCI repository [3] show that the novel classifiers perform better than the proper ones in terms of error rate and complexity.Yayın Tree Ensembles on the induced discrete space(Institute of Electrical and Electronics Engineers Inc., 2016-05) Yıldız, Olcay TanerDecision trees are widely used predictive models in machine learning. Recently, K-tree is proposed, where the original discrete feature space is expanded by generating all orderings of values of k discrete attributes and these orderings are used as the new attributes in decision tree induction. Although K-tree performs significantly better than the proper one, their exponential time complexity can prohibit their use. In this brief, we propose K-forest, an extension of random forest, where a subset of features is selected randomly from the induced discrete space. Simulation results on 17 data sets show that the novel ensemble classifier has significantly lower error rate compared with the random forest based on the original feature space.Yayın Univariate decision tree induction using maximum margin classification(Oxford Univ Press, 2012-03) Yıldız, Olcay TanerIn many pattern recognition applications, first decision trees are used due to their simplicity and easily interpretable nature. In this paper, we propose a new decision tree learning algorithm called univariate margin tree where, for each continuous attribute, the best split is found using convex optimization. Our simulation results on 47 data sets show that the novel margin tree classifier performs at least as good as C4.5 and linear discriminant tree (LDT) with a similar time complexity. For two-class data sets, it generates significantly smaller trees than C4.5 and LDT without sacrificing from accuracy, and generates significantly more accurate trees than C4.5 and LDT for multiclass data sets with one-vs-rest methodology.Yayın Mapping classifiers and datasets(Pergamon-Elsevier Science Ltd, 2011-04) Yıldız, Olcay TanerGiven the posterior probability estimates of 14 classifiers on 38 datasets, we plot two-dimensional maps of classifiers and datasets using principal component analysis (PCA) and Isomap. The similarity between classifiers indicate correlation (or diversity) between them and can be used in deciding whether to include both in an ensemble. Similarly, datasets which are too similar need not both be used in a general comparison experiment. The results show that (i) most of the datasets (approximately two third) we used are similar to each other, (ii) multilayer perceptrons and k-nearest neighbor variants are more similar to each other than support vector machine and decision tree variants. (iii) the number of classes and the sample size has an effect on similarity.Yayın Re-mining item associations: Methodology and a case study in apparel retailing(Elsevier Science BV, 2011-12) Demiriz, Ayhan; Ertek, Gürdal; Atan, Sabri Tankut; Kula, UfukAssociation mining is the conventional data mining technique for analyzing market basket data and it reveals the positive and negative associations between items. While being an integral part of transaction data, pricing and time information have not been integrated into market basket analysis in earlier studies. This paper proposes a new approach to mine price, time and domain related attributes through re-mining of association mining results. The underlying factors behind positive and negative relationships can be characterized and described through this second data mining stage. The applicability of the methodology is demonstrated through the analysis of data coming from a large apparel retail chain, and its algorithmic complexity is analyzed in comparison to the existing techniques.Yayın Omnivariate rule induction using a novel pairwise statistical test(IEEE Computer Soc, 2013-09) Yıldız, Olcay TanerRule learning algorithms, for example, RIPPER, induces univariate rules, that is, a propositional condition in a rule uses only one feature. In this paper, we propose an omnivariate induction of rules where under each condition, both a univariate and a multivariate condition are trained, and the best is chosen according to a novel statistical test. This paper has three main contributions: First, we propose a novel statistical test, the combined 5 x 2 cv t test, to compare two classifiers, which is a variant of the 5 x 2 cv t test and give the connections to other tests as 5 x 2 cv F test and k-fold paired t test. Second, we propose a multivariate version of RIPPER, where support vector machine with linear kernel is used to find multivariate linear conditions. Third, we propose an omnivariate version of RIPPER, where the model selection is done via the combined 5 x 2 cv t test. Our results indicate that 1) the combined 5 x 2 cv t test has higher power (lower type II error), lower type I error, and higher replicability compared to the 5 x 2 cv t test, 2) omnivariate rules are better in that they choose whichever condition is more accurate, selecting the right model automatically and separately for each condition in a rule.
