• Journal of Korean Society for Quality Management
• /
• v.47 no.3
• /
• pp.537-552
• /
• 2019

Purpose: The development of information technology makes it easy to utilize high-dimensional categorical data. In this regard, the purpose of this study is to propose a novel method to select the proper categorical variables in high-dimensional categorical data. Methods: The proposed feature selection method consists of three steps: (1) The first step defines the goodness-to-pick measure. In this paper, a categorical variable is relevant if it has relationships among other variables. According to the above definition of relevant variables, the goodness-to-pick measure calculates the normalized conditional entropy with other variables. (2) The second step finds the relevant feature subset from the original variables set. This step decides whether a variable is relevant or not. (3) The third step eliminates redundancy variables from the relevant feature subset. Results: Our experimental results showed that the proposed feature selection method generally yielded better classification performance than without feature selection in high-dimensional categorical data, especially as the number of irrelevant categorical variables increase. Besides, as the number of irrelevant categorical variables that have imbalanced categorical values is increasing, the difference in accuracy between the proposed method and the existing methods being compared increases. Conclusion: According to experimental results, we confirmed that the proposed method makes it possible to consistently produce high classification accuracy rates in high-dimensional categorical data. Therefore, the proposed method is promising to be used effectively in high-dimensional situation.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.2
• /
• pp.98-104
• /
• 2014

Locality-sensitive hashing techniques have been developed to efficiently handle nearest neighbor searches and similar pair identification problems for large volumes of high-dimensional data. This study proposes a locality-sensitive hashing method that can be applied to nearest neighbor search problems for data sets containing both numerical and categorical attributes. The proposed method makes use of dual hashing functions, where one function is dedicated to numerical attributes and the other to categorical attributes. The method consists of creating indexing structures for each of the dual hashing functions, gathering and combining the candidates sets, and thoroughly examining them to determine the nearest ones. The proposed method is examined for a few synthetic data sets, and results show that it improves performance in cases of large amounts of data with both numerical and categorical attributes.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.815-825
• /
• 2016

Marginalized random effects models (MREMs) are often used to analyze longitudinal categorical data. The models permit direct estimation of marginal mean parameters and specify the serial correlation of longitudinal categorical data via the random effects. However, it is not easy to estimate the random effects covariance matrix in the MREMs because the matrix is high-dimensional and must be positive-definite. To solve these restrictions, we introduce two modeling approaches of the random effects covariance matrix: partial autocorrelation and the modified Cholesky decomposition. These proposed methods are illustrated with the real data from Korean genomic epidemiology study.

• Journal of Digital Convergence
• /
• v.13 no.11
• /
• pp.157-164
• /
• 2015

This paper describes subspace clustering of categorical data for convergence and integration. Because categorical data are not designed for dealing only with numerical data, The conventional evaluation measures are more likely to have the limitations due to the absence of ordering and high dimensional data and scarcity of frequency. Hence, conditional entropy measure is proposed to evaluate close approximation of cohesion among attributes within each cluster. We propose a new objective function that is used to reflect the optimistic clustering so that the within-cluster dispersion is minimized and the between-cluster separation is enhanced. We performed experiments on five real-world datasets, comparing the performance of our algorithms with four algorithms, using three evaluation metrics: accuracy, f-measure and adjusted Rand index. According to the experiments, the proposed algorithm outperforms the algorithms that were considered int the evaluation, regarding the considered metrics.

• Industrial Engineering and Management Systems
• /
• v.14 no.2
• /
• pp.210-219
• /
• 2015

A classification task requires an exponentially growing amount of computation time and number of observations as the variable dimensionality increases. Thus, reducing the dimensionality of the data is essential when the number of observations is limited. Often, dimensionality reduction or feature selection leads to better classification performance than using the whole number of features. In this paper, we study the possibility of utilizing the Markov blanket discovery algorithm as a new feature selection method. The Markov blanket of a target variable is the minimal variable set for explaining the target variable on the basis of conditional independence of all the variables to be connected in a Bayesian network. We apply several Markov blanket discovery algorithms to some high-dimensional categorical and continuous data sets, and compare their classification performance with other feature selection methods using well-known classifiers.

• Communications for Statistical Applications and Methods
• /
• v.25 no.1
• /
• pp.61-70
• /
• 2018

Modeling of the random effects covariance matrix in generalized linear mixed models (GLMMs) is an issue in analysis of longitudinal categorical data because the covariance matrix can be high-dimensional and its estimate must satisfy positive-definiteness. To satisfy these constraints, we consider the autoregressive and moving average Cholesky decomposition (ARMACD) to model the covariance matrix. The ARMACD creates a more flexible decomposition of the covariance matrix that provides generalized autoregressive parameters, generalized moving average parameters, and innovation variances. In this paper, we analyze longitudinal count data with overdispersion using GLMMs. We propose negative binomial loglinear mixed models to analyze longitudinal count data and we also present modeling of the random effects covariance matrix using the ARMACD. Epilepsy data are analyzed using our proposed model.

• Journal of KIISE:Databases
• /
• v.37 no.2
• /
• pp.71-81
• /
• 2010

The problem of finding clusters is widely used in numerous applications, such as pattern recognition, image analysis, market analysis. The important factors that decide cluster quality are the similarity measure and the number of attributes. Similarity measures should be defined with respect to the data types. Existing similarity measures are well applicable to numerical attribute values. However, those measures do not work well when the data is described by categorical attributes, that is, when no inherent similarity measure between values. In high dimensional spaces, conventional clustering algorithms tend to break down because of sparsity of data points. To overcome this difficulty, a subspace clustering approach has been proposed. It is based on the observation that different clusters may exist in different subspaces. In this paper, we propose a new similarity measure for clustering of high dimensional categorical data. The measure is defined based on the fact that a good clustering is one where each cluster should have certain information that can distinguish it with other clusters. We also try to capture on the attribute dependencies. This study is meaningful because there has been no method to use both of them. Experimental results on real datasets show clusters obtained by our proposed similarity measure are good enough with respect to clustering accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.192-194
• /
• 2000

최근 데이터 마이닝에서 대용량 데이터를 처리하는 응용이 많아짐에 따라, 클러스터링(Clustering) 및 분류(Classification)방법이 중요한 분야가 되고 있다. 특히 분류방법에 관한 기존 연구들은 단지 메모리 상주(memory-resident) 데이터에 대해 한정되며 고차원 데이터를 효율적으로 처리할 수 없다. 따라서 본 논문에서는 대용량 고차원 데이터를 효과적으로 처리할 수 있는 새로운 분류 알고리즘을 제안한다. 이는 데이터들을 차원 공간상의 셀(cell)로 표현함으로써 수치(numerical) 애트리뷰트와 범주(categorical) 애트리뷰트 모두 처리할 수 있는 알고리즘을 제안한다. 아울러, 실험결과를 통해 제안한 알고리즘이 데이터의 양,차원 그리고 속성에 관계없이 분류를 효과적으로 수행함을 보인다.

• Communications for Statistical Applications and Methods
• /
• v.19 no.6
• /
• pp.899-904
• /
• 2012

High-dimensional categorical data models with small sample sizes have not been used extensively in genomic sequences that involve count (or discrete) or purely qualitative responses. A basic task is to identify differentially expressed genes (or positions) among a number of genes. It requires an appropriate test statistics and a corresponding multiple testing procedure so that a multivariate analysis of variance should not be feasible. A family wise error rate(FWER) is not appropriate to test thousands of genes simultaneously in a multiple testing procedure. False discovery rate(FDR) is better than FWER in multiple testing problems. The data from the 2002-2003 SARS epidemic shows that a conventional FDR procedure and a proposed test statistic based on a pseudo-marginal approach with Hamming distance performs better.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.181-183
• /
• 2006

본 논문은 고차원의 범주형 데이터에 대한 군집화에 대해서 다룬다. 기존의 범주형 데이터 객체를 위한 유사성(상이성) 계측들의 기저에 깔려 있는 한계점은 수치형 데이터에서와 같은 순서화 (ordering)의 부재와 데이터의 고차원성과 희소성에 기인하는데, 이를 효과적으로 극복할 수 있는 기법이 투영 군집화이다. 본 논문에서는 고차원의 범주형 데이터를 효과적으로 처리할 수 있는 투영 군집화를 다루며 핵심 요소인 군집 차원의 정의와 군집 응집도를 제안한다.