A discretization algorithm based on Class-Attribute Contingency Coefficient
Information SciencesPublished 12 September 2007
Cheng‐Jung Tsai, Chien-I Lee, Wei‐Pang Yang
Citations205
SJR quartileQ1
SJR score1.80
SNIP1.98
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Empirical evaluation showed that the proposed algorithm could generate a better discretization scheme that improved the accuracy of classification and the execution time, number of generated rules, and the training time of C5.0.
Abstract
Discretization algorithms have played an important role in data mining and knowledge discovery. They not only produce a concise summarization of continuous attributes to help the experts understand the data more easily, but also make learning more accurate and faster. In this paper, we propose a static, global, incremental, supervised and top-down discretization algorithm based on Class-Attribute Contingency Coefficient. Empirical evaluation of seven discretization algorithms on 13 real datasets and four artificial datasets showed that the proposed algorithm could generate a better discretization scheme that improved the accuracy of classification. As to the execution time of discretization, the number of generated rules, and the training time of C5.0, our approach also achieved promising results.
Keywords
Computer Science
Choice Reviews OnlineData mining: concepts and techniques
28,877 Citations2012Jiawei Han, Micheline Kamber +1 more
Data mining is the search for new, valuable, and nontrivial information in large volumes of data, a cooperative effort of humans and computers that is possible to put data-mining activities into one of two categories: Predictive data mining, which produces the model of the system described by the given data set, or Descriptive data mining which produces new, nontrivials information based on the available data set.
Statistical Comparisons of Classifiers over Multiple Data Sets
11,198 Citations2006Janez Demšar
A set of simple, yet safe and robust non-parametric tests for statistical comparisons of classifiers is recommended: the Wilcoxon signed ranks test for comparison of two classifiers and the Friedman test with the corresponding post-hoc tests for comparisons of more classifiers over multiple data sets.
International Joint Conference on Artificial IntelligenceMulti-Interval Discretization of Continuous-Valued Attributes for Classification Learning
2,832 Citations1993Usama M. Fayyad, Keki B. Irani
This paper addresses the use of the entropy minimization heuristic for discretizing the range of a continuous-valued attribute into multiple intervals.
Machine LearningThe CN2 Induction Algorithm
2,015 Citations1989Peter Clark, Tim Niblett
A description and empirical evaluation of a new induction system, CN2, designed for the efficient induction of simple, comprehensible production rules in domains where problems of poor description language and/or noise may be present.
Elsevier eBooksSupervised and Unsupervised Discretization of Continuous Features
1,931 Citations1995James Dougherty, Ron Kohavi +1 more
Binning, an unsupervised discretization method, is compared to entropy-based and purity-based methods, which are supervised algorithms, and it is found that the performance of the Naive-Bayes algorithm significantly improved when features were discretized using an entropy- based method.
MIT Press eBooksKnowledge Discovery in Databases
1,758 Citations1991Gregory Piateski, William Frawley
Machine LearningThe CN2 induction algorithm
994 Citations1989Peter Clark, Tim Niblett
A description and empirical evaluation of a new induction system, designed for the efficient induction of simple, comprehensible production rules in domains where problems of poor description language and/or noise may be present, is presented.
Data Mining and Knowledge DiscoveryDiscretization: An Enabling Technique
979 Citations2002Huan Liu, Farhad Hussain +2 more
This paper aims at a systematic study of discretization methods with their history of development, effect on classification, and trade-off between speed and accuracy.
National Conference on Artificial IntelligenceThe multi-purpose incremental learning system AQ15 and its testing application to three medical domains
761 Citations1986Ryszard S. Michalski, Igor Mozetič +2 more
The demonstration that by applying the proposed method of cover truncation and analogical matching, called TRUNC, one may drastically decrease the complexity of the knowledge base without affecting its performance accuracy is demonstrated.
Machine LearningOn the Handling of Continuous-Valued Attributes in Decision Tree Generation
680 Citations1992Usama M. Fayyad, Keki B. Irani
The result serves to give a better understanding of the entropy measure, to point out that the behavior of the information entropy heuristic possesses desirable properties that justify its usage in a formal sense, and to improve the efficiency of evaluating continuous-valued attributes for cut value selection.
National Conference on Artificial IntelligenceChiMerge: discretization of numeric attributes
603 Citations1992Randy Kerber
ChiMerge is described, a general, robust algorithm that uses the χ2 statistic to discretize (quantize) numeric attributes.
IEEE Transactions on Knowledge and Data EngineeringCAIM discretization algorithm
446 Citations2004Lukasz Kurgan, Krzysztof J. Cios
The tests performed using CAIM and six other state-of-the-art discretization algorithms show that discrete attributes generated by the CAIM algorithm almost always have the lowest number of intervals and the highest class-attribute interdependency.
Machine LearningOn the handling of continuous-valued attributes in decision tree generation
360 Citations1992Usama M. Fayyad, Keki B. Irani
The result serves to give a better understanding of the entropy measure, to point out that the behavior of the information entropy heuristic possesses desirable properties that justify its usage in a formal sense, and to improve the efficiency of evaluating continuous-valued attributes for cut value selection.
IEEE Transactions on Knowledge and Data EngineeringFeature selection via discretization
325 Citations1997Huan Liu, Rudy Setiono
Chi2 is a simple and general algorithm that uses the /spl chi//sup 2/ statistic to discretize numeric attributes repeatedly until some inconsistencies are found in the data and achieves feature selection via discretization.
IEEE Transactions on Pattern Analysis and Machine IntelligenceClass-dependent discretization for inductive learning from continuous and mixed-mode data
241 Citations1995J.Y. Ching, Andrew K. C. Wong +1 more
A new information theoretic discretization method optimized for supervised learning is proposed and described that seeks to maximize the mutual dependence as measured by the interdependence redundancy between the discrete intervals and the class labels, and can automatically determine the most preferred number of intervals for an inductive learning application.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSynthesizing Statistical Knowledge from Incomplete Mixed-Mode Data
190 Citations1987Andrew K. C. Wong, David Chiu
The proposed method adopts an event-covering approach which covers a subset of statistically relevant outcomes in the outcome space of variable-pairs and can acquire statistical knowledge from incomplete mixed-mode data.
IEEE Transactions on Knowledge and Data EngineeringAn extended Chi2 algorithm for discretization of real value attributes
155 Citations2005Chao‐Ton Su, Jyh-Hwa Hsu
A new algorithm, named the extended Chi2 algorithm, is proposed, which possesses a better performance than the original and modified Chi2 algorithms and ignores the effect of variance in the two merged intervals.
IEEE Transactions on Knowledge and Data EngineeringA modified Chi2 algorithm for discretization
155 Citations2002Francis E. H. Tay, Lixiang Shen
The Chi2 algorithm, a modification to the ChiMerge method, automates the discretization process by introducing an inconsistency rate as the stopping criterion and it automatically selects the significance value and becomes a completely automatic discretized method.
Information SciencesAn extension of the naive Bayesian classifier
128 Citations2005Ronald R. Yager
The objective here is to provide an extension of the naive Bayesian classifier in a manner that gives us more parameters for matching data and introduces a new class of OWA operators which are based on a combining the OWA Operators with t-norm's operators.
PUBLIC: A Decision Tree Classifier that Integrates Building and Pruning
110 Citations1998Rajeev Rastogi, Kyuseok Shim
Machine LearningKhiops: A Statistical Discretization Method of Continuous Attributes
108 Citations2004Marc Boullé
This method optimizes the chi-square criterion in a global manner on the whole discretization domain and does not require any stopping criterion, in contrast with related methods ChiMerge and ChiSplit.
Information SciencesA self-adaptive migration model genetic algorithm for data mining applications
104 Citations2007K. G. Srinivasa, K R Venugopal +1 more
This paper gives a mathematical schema analysis of the method stating and showing that the algorithm exploits previously discovered knowledge for a more focused and concentrated search of heuristically high yielding regions while simultaneously performing a highly explorative search on the other regions of the search space.
Elsevier eBooksCompression-Based Discretization of Continuous Attributes
91 Citations1995Bernhard Pfahringer
A global evaluation measure for discretizations based on the so-called Minimum Description Length (MDL) principle from information theory is defined and the efficient algorithmic usage of this measure in the MDL-Disc algorithm is described.
Information SciencesDecision-tree instance-space decomposition with grouped gain-ratio
68 Citations2007Shahar Cohen, Lior Rokach +1 more
The study indicates that using the novel splitting-rule, previously presented implementations of the framework, can be improved in terms of accuracy and computation time.
Information SciencesA coloring fuzzy graph approach for image classification
59 Citations2006Darío Gómez, Javier Montero +1 more
In this article, the image is conceived as a fuzzy graph defined on the set of pixels where fuzzy edges represent the distance between pixels to obtain a more flexible hierarchical structure of colors, which in turn should give useful hints about those classes with unclear boundaries.
Information SciencesBuilding multi-way decision trees with numerical attributes
58 Citations2003Fernando Berzal, Juan-Carlos Cubero +2 more
This paper proposes the use of multi-way splits for continuous attributes for decision trees in order to reduce the tree complexity without decreasing classification accuracy.
Information SciencesComputing with words for text processing: An approach to the text categorization
56 Citations2005Sławomir Zadrożny, Janusz Kacprzyk
The use of the computing with words paradigm for the automatic text documents categorization problem is discussed and results related to fuzzy (linguistic) queries in IR are employed, notably various interpretations of the weights of query terms.
Information SciencesCLIP4: Hybrid inductive machine learning algorithm that generates inequality rules
52 Citations2003Krzysztof J. Cios, Lukasz Kurgan
The paper describes a hybrid inductive machine learning algorithm called CLIP4 that first partitions data into subsets using a tree structure and then generates production rules only from subsets stored at the leaf nodes, which is a unique feature of the algorithm.
Lecture notes in computer scienceLearning from inconsistent and noisy data: The AQ18 approach
51 Citations1999Kenneth A. Kaufman, Ryszard S. Michalski
This paper presents an approach in which a learner seeks rules optimizing a description quality criterion that combines completeness and consistency gain, a measure based on consistency that reflects the rule’s benefit.
Studies in fuzziness and soft computingHybrid Inductive Machine Learning: An Overview of CLIP Algorithms
42 Citations2002Krzysztof J. Cios, Lukasz Kurgan
The chapter describes inductive machine learning methods for generating hypotheses about given training data by focusing on hybrid algorithms that generate hypotheses in the form of production ifthenrules, which constitute the model of the data.
Information SciencesNewspaper demand prediction and replacement model based on fuzzy clustering and rules
37 Citations2007Guilherme Ramos Cardoso, Fernando Gomide
A prediction method that uses fuzzy clustering for data base exploration and fuzzy rules together with performance scores of selling points for prediction is suggested that is effective when compared with the current methodology, neural network-based predictors, and autoregressive forecasters.
New Learning Paradigms in Soft Computing
29 Citations2001Lakhmi C. Jain, Janusz Kacprzyk
The purpose of this volume is to present some new learning paradigms that have been triggered, or at least strongly influenced by soft computing tools and techniques, mainly related to neural networks, fuzzy logic, rough sets, and evolutionary computations.
Information SciencesClassification methods in the detection of new malicious emails
28 Citations2004Dong‐Her Shih, Hsiu‐Sen Chiang +1 more
The prototype of the bagged classifier is utilized in the implementation of the malicious email detection system and comparison results show the accuracy in the detection of new malicious emails.
International Conference on Machine Learning and ApplicationsFast Class-Attribute Interdependence Maximization (CAIM) Discretization Algorithm.
21 Citations2003Lukasz Kurgan, Krzysztof J. Cios
The paper describes a Fast Class-Attribute Interdependence Maximization (F-CAIM) algorithm that is an extension of the original CAIM algorithm that works with supervised data by maximization of the classattribute interdependence.
Information SciencesEstimating sentence types in computer related new product bulletins using a decision tree
14 Citations2004Hidekazu Tokunaga, Atlam El-Sayed +4 more
The present paper reveals that the estimation of four sentence types (HATSUBAI [sales], SHIYO [specifications], KOZO [structure], KINO [function]) is an effective as preprocessing for information extraction and automatic text summarization.
A Top-Down and Greedy Method for Discretization of Continuous Attributes
13 Citations2007Chien-I Lee, Cheng‐Jung Tsai +2 more
Compared with CAIM, this method can generate a better discretization scheme to bring on the improvement of accuracy of classification and achieves comparable results with regard to the number of generated rules and execution time of a classifier.
Lecture notes in computer scienceImprovement of Decision Accuracy Using Discretization of Continuous Attributes
12 Citations2006Qingxiang Wu, David Bell +4 more
The experimental results on benchmark data sets show that the naive Bayes classifier with the new discretizer can reach higher accuracy than the C5.0 tree.
Correlation Preserving Discretization
6 Citations2005S. A. Mehta, Srinivasan Parthasarathy +1 more
A novel PCA-based unsupervised algorithm for the discretization of continuous attributes in multivariate datasets is presented, which leverages the underlying correlation structure in the dataset to obtain the discrete intervals, and ensures that the inherent correlations are preserved.