• Journal of the Korean Operations Research and Management Science Society
• /
• v.12 no.1
• /
• pp.27-33
• /
• 1987

A stochastic model for an inventory system in which depletion of stock takes place due to random demand as well as random loss of items is studied under the assumption that the intervals between cussessive unit demands as well as those between cussessive unit losses, are independently and identically distributed random variables having negative exponential distributions with respective parameters .mu. and .lambda. It is further assumed that leadtime for each order is an outstanding-order-dependent random variable. The steady state probability distribution of the net inventory level is derived under the continuous review (S -1, S) inventory policy, from which the total expected coast expression is formulated.

• Journal of Korean Society for Quality Management
• /
• v.18 no.1
• /
• pp.129-147
• /
• 1990

This study is to refer to the optimization problems when the stress and strength follow the time dependent model, considering a decision making process in the design methodology from reliability viewpoint. Reliability of a component can be expressed and computed if the probability distributions for the stress and strength in the time dependent case are known. The factors which determine the parameters of the distributions for stress and strength random variables can be controlled in design problems. This leads to the problem of finding the optimal values of these parameters subject to resources and design constraints. This paper is to present techniques for solving the optimization problems at the design stage like as minimizing the total cost to be spent on controlling the stress and strength parameters for random variables subject to the constraint that the component must have a specified reliability, alternatively, maximizing the component reliability subject to certain constraints on amount of resources available to control the parameters. The derived expressions and computations of reliability in the time dependent case and some optimization models of these cases are discussed. The special structure of these models is exploited to develop the optimization techniques which are illustrated by design examples.

• Journal of applied mathematics & informatics
• /
• v.30 no.1_2
• /
• pp.327-336
• /
• 2012

Let {$X_{ni}$, $i{\geq}1$, $n{\geq}1$} be an array of rowwise and pairwise negatively quadrant dependent random variables with mean zero, {$a_{ni}$, $i{\geq}1$, $n{\geq}1$} an array of weights and {$b_n$, $n{\geq}1$} an increasing sequence of positive integers. In this paper we consider some results concerning complete convergence of ${\sum}_{i=1}^{bn}a_{ni}X_{ni}$.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.175-183
• /
• 1996

Let $S_n,n$ = 1, 2,... denote the partial sums of not necessarily in-dependent random variables. Let N(c) = min${ n ; S_n > c}$, c $\geq$ 0. Theorem 2 states that N (c), (suitably normalized), tends to 0 in p-mean, 1 $\leq$ p < 2, as c longrightarrow $\infty$ under mild conditions, which generalizes earlier result by Gut(1974). The proof follows by applying Theorem 1, which generalizes the known result $E$\mid$S_n$\mid$^p$ = o(n), 0 < p< 2, as n .rarw..inf. to randomly indexed partial sums.

• Journal of the Korean Mathematical Society
• /
• v.54 no.6
• /
• pp.1879-1903
• /
• 2017

In this paper we study the closure property and probability tail asymptotics for randomly weighted sums $S^{\Theta}_n={\Theta}_1X_1+{\cdots}+{\Theta}_nX_n$ for long-tailed random variables $X_1,{\ldots},X_n$ and positive bounded random weights ${\Theta}_1,{\ldots},{\Theta}_n$ under similar dependence structure as in [26]. In particular, we study the case where the distribution of random vector ($X_1,{\ldots},X_n$) is generated by an absolutely continuous copula.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.137-144
• /
• 2024

The purpose of this paper is to analyze the significance of independent variables in estimating crack density using machine learning algorithms. The algorithms used were random forest and SHAP, with the independent variables being compressional wave velocity, shear wave velocity, porosity, and Poisson's ratio. Rock samples were collected from construction sites and processed into cylindrical forms to facilitate the acquisition of each input property. Artificial weathering was conducted twelve times to obtain values for both independent and dependent variables with multiple features. The application of the two algorithms revealed that porosity is a crucial independent variable in estimating crack density, whereas shear wave velocity has a relatively low impact. These results suggested that the four physical properties set as independent variables were sufficient for estimating crack density. Additionally, they presented a methodology for verifying the appropriateness of the independent variables using algorithms such as random forest and SHAP.

• Industry Promotion Research
• /
• v.7 no.1
• /
• pp.1-8
• /
• 2022

We investigated various types of machine learning methods that can be applied to censored data. Exploratory data analysis reveals the distribution of each feature, relationships among features. Next, classification problem has been set up where the dependent variable is death_event while the rest of the features are independent variables. After applying various machine learning methods to the data, it has been found that just like many other reports from the artificial intelligence arena random forest performs better than logistic regression. But recently well performed artificial neural network and gradient boost do not perform as expected due to the lack of data. Finally Kaplan-Meier and Cox proportional hazard model have been employed to explore the relationship of the dependent variable (t_i, δ_i) with the independent variables. Also random forest which is used in machine learning has been applied to the survival analysis with censored data.

• Journal of applied mathematics & informatics
• /
• v.27 no.3_4
• /
• pp.829-842
• /
• 2009

Let {$X_{ni}|1\;{\le}\;i\;{\le}\;n$, $n\;{\ge}\;1$} be an array of rowwise negatively associated random variables and let $\alpha$ > 1/2, 0 < p < 2 ${\alpha}p\;{\ge}\;1$. In this paper we discuss $n^{{\alpha}p-2}h(n)$ max $_{1\;{\le}\;k{\le}n}\;|\;{\sum}^k_{i=1}\;X_{ni}|/n^{\alpha}\;{\to}\;0$ completely as $n\;{\to}\;{\infty}$ under not necessarily identically distributed with a suitable conditions and h(x) > 0 is a slowly varying function as $x\;{\to}\;{\infty}$. In addition, we obtained that $n^{{\alpha}p-2}h(n)$ max $_{1\;{\le}\;k{\le}n}\;|\;{\sum}^k_{i=1}\;X_{ni}|/n^{\alpha}\;{\to}\;0$ completely as $n\;{\to}\;{\infty}$ if and only if $E|X_{11}|^ph(|X_{11}|^{1/\alpha})\;<\;{\infty}$ and $EX_{11}\;=\;0$ under identically distributed case and some corollaries are obtained.

• Human Ecology Research
• /
• v.53 no.6
• /
• pp.641-654
• /
• 2015

This study identifies and tracks changes gender differences in adolescent users' problematic online behavior. This study used Korea Youth Panel Survey (KYPS), which has tracked respondents over 7 years, with self-control theory and social learning theory applied as a theoretical framework. The model included individual-level variables such as self-control and respondent's experience of problematic behavior (offline), as well as socialization variables such as the number close friends who engaged in problematic offline behavior, parent-child relationships, and parental monitoring. Dependent variables included problematic online behavior, unauthorized ID use (ID theft) and cyberbullying (cursing/insulting someone in a chat room or on a bulletin board). Control variables consisted of academic performance, time spent on a computer, monthly household income, and father's educational attainment. Random and fixed effects models were performed by gender. Results supported self-control theory even for the within-level analysis (fixed effects models) regardless of gender, while social learning theory was partially supported. Only peer effects were found significant (except for unauthorized ID use) among girls. Year dummy variables showed significant negative associations; however, academic performance and time spent using computers were significant in some models. Father's educational attainment and monthly household income were found insignificant, even in the random effects models. We also discuss implications and suggestions for future research and policy makers.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.10a
• /
• pp.239-247
• /
• 2003

Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, fraud dection, data reduction and variable screening, etc. CHAID(Chi-square Automatic Interaction Detector), is an exploratory method used to study the relationship between a dependent variable and a series of predictor variables. In this paper we propose and CHAID algorithm by cube-based sampling and explore CHAID algorithm in view of accuracy and speed by the number of variables.