• Bulletin of the Korean Mathematical Society
• /
• v.34 no.4
• /
• pp.603-615
• /
• 1997

In this paper, we introduce and study a new class of random completely generalized nonlinear variational inclusions with non-compact valued random mappings and construct some new iterative algorithms. We prove the existence of random solutions for this class of random variational inclusions and the convergence of random iterative sequences generated by the algorithms.

• Journal of the Korean Statistical Society
• /
• v.34 no.2
• /
• pp.125-140
• /
• 2005

In this paper, we consider the estimation of the correlation coefficient in the bivariate normal distribution, based on a sample obtained using a modification of the moving extreme ranked set sampling technique (MERSS) that was introduced by Al-Saleh and Al-Hadhrami (2003a). The modification involves using a concomitant random variable. Nonparametric-type methods as well as the maximum likelihood estimation are considered under different settings. The obtained estimators are compared to their counterparts that are obtained based simple random sampling (SRS). It appears that the suggested estimators are more efficient

• Communications for Statistical Applications and Methods
• /
• v.5 no.2
• /
• pp.439-445
• /
• 1998

In this paper we introduce the definition for fuzzy random set by Puri and Ralescu(1985) and show strong laws of large numbers for fuzzy random sets on Banach spaces.

• Journal of the Korean Mathematical Society
• /
• v.39 no.1
• /
• pp.51-60
• /
• 2002

Some random fixed point theorems for nonexpansive and *-nonexpansive random operators defined on convex and star-shaped sets in a Frechet space are proved. Our work extends recent results of Beg and Shahzad and Tan and Yaun to noncontinuous multivalued random operators, sets analogue to an earlier result of Itoh and provides a random version of a deterministic fixed point theorem due to Singh and Chen.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.4
• /
• pp.1951-1956
• /
• 2013

Distribution-matching type algorithms based on a set of symbols generated in random order provide a limited performance under biased impulsive noise since the performance criterion for the algorithms has no variables for biased signal. For the immunity against biased impulsive noise, we propose, in this paper, a modified performance criterion and derived related blind algorithms based on augmented filter structures and the distribution-matching method using a set of random symbols. From the simulation results, the proposed algorithm based on the proposed criterion yielded superior convergence performance undisturbed by the strong biased impulsive noise.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.696-700
• /
• 1998

Fuzzy random variables with piecewise linear membership functions are introduced from a practical viewpoint. The estimation of the expected values of these fuzzy random variables is also discussed and statistical application is denonstratied by using a real data set.

• Journal of the Korean Mathematical Society
• /
• v.53 no.3
• /
• pp.503-517
• /
• 2016

For positive integers d and n, let $[n]^d$ be the set of all vectors ($a_1,a_2,{\cdots},a_d$), where ai is an integer with $0{\leq}a_i{\leq}n-1$. A subset S of $[n]^d$ is called a Sidon set if all sums of two (not necessarily distinct) vectors in S are distinct. In this paper, we estimate two numbers related to the maximum size of Sidon sets in $[n]^d$. First, let $\mathcal{Z}_{n,d}$ be the number of all Sidon sets in $[n]^d$. We show that ${\log}(\mathcal{Z}_{n,d})={\Theta}(n^{d/2})$, where the constants of ${\Theta}$ depend only on d. Next, we estimate the maximum size of Sidon sets contained in a random set $[n]^d_p$, where $[n]^d_p$ denotes a random set obtained from $[n]^d$ by choosing each element independently with probability p.

• Journal of the Korean Mathematical Society
• /
• v.41 no.5
• /
• pp.933-944
• /
• 2004

Packing dimension of a set is an upper bound for the packing dimensions of measures on the set. Recently the packing dimension of statistically self-similar Cantor set, which has uniform distributions for contraction ratios, was shown to be its Hausdorff dimension. We study the method to find an upper bound of packing dimensions and the upper Renyi dimensions of measures on a statistically quasi-self-similar Cantor set (its packing dimension is still unknown) which has non-uniform distributions of contraction ratios. As results, in some statistically quasi-self-similar Cantor set we show that every probability measure on it has its subset of full measure whose packing dimension is also its Hausdorff dimension almost surely and it has its subset of full measure whose packing dimension is also its Hausdorff dimension almost surely for almost all probability measure on it.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.7
• /
• pp.139-148
• /
• 2012

An ensemble of classifiers is to employ a set of individually trained classifiers and combine their predictions. It has been found that in most cases the ensembles produce more accurate predictions than the base classifiers. Combining outputs from multiple classifiers, known as ensemble learning, is one of the standard and most important techniques for improving classification accuracy in machine learning. An ensemble of classifiers is efficient only if the individual classifiers make decisions as diverse as possible. Bagging is the most popular method of ensemble learning to generate a diverse set of classifiers. Diversity in bagging is obtained by using different training sets. The different training data subsets are randomly drawn with replacement from the entire training dataset. The random subspace method is an ensemble construction technique using different attribute subsets. In the random subspace, the training dataset is also modified as in bagging. However, this modification is performed in the feature space. Bagging and random subspace are quite well known and popular ensemble algorithms. However, few studies have dealt with the integration of bagging and random subspace using SVM Classifiers, though there is a great potential for useful applications in this area. The focus of this paper is to propose methods for improving SVM performance using hybrid ensemble strategy for bankruptcy prediction. This paper applies the proposed ensemble model to the bankruptcy prediction problem using a real data set from Korean companies.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.2
• /
• pp.75-84
• /
• 2019

In this study, the random forest approach was used to predict the national mean rice yield of South Korea by using mean climatic factors at a national scale. A random forest model that used monthly climate variable and year as an important predictor in predicting crop yield. Annual yield change would be affected by technical improvement for crop management as well as climate. Year as prediction factor represent technical improvement. Thus, it is likely that the variables of importance identified for the random forest model could result in a large error in prediction of rice yield in practice. It was also found that elimination of the trend of yield data resulted in reasonable accuracy in prediction of yield using the random forest model. For example, yield prediction using the training set (data obtained from 1991 to 2005) had a relatively high degree of agreement statistics. Although the degree of agreement statistics for yield prediction for the test set (2006-2015) was not as good as those for the training set, the value of relative root mean square error (RRMSE) was less than 5%. In the variable importance plot, significant difference was noted in the importance of climate factors between the training and test sets. This difference could be attributed to the shifting of the transplanting date, which might have affected the growing season. This suggested that acceptable yield prediction could be achieved using random forest, when the data set included consistent planting or transplanting dates in the predicted area.