• Journal of the Korean Statistical Society
• /
• v.30 no.2
• /
• pp.179-192
• /
• 2001

When a statistical model has a hierarchical structure such as multilayer perceptrons in neural networks or Gaussian mixture density representation, the model includes distribution with unidentifiable parameters when the structure becomes redundant. Since the exact structure is unknown, we need to carry out statistical estimation or learning of parameters in such a model. From the geometrical point of view, distributions specified by unidentifiable parameters become a singular point in the parameter space. The problem has been remarked in many statistical models, and strange behaviors of the likelihood ratio statistics, when the null hypothesis is at a singular point, have been analyzed so far. The present paper studies asymptotic behaviors of the maximum likelihood estimator and the Bayesian predictive estimator, by using a simple cone model, and show that they are completely different from regular statistical models where the Cramer-Rao paradigm holds. At singularities, the Fisher information metric degenerates, implying that the cramer-Rao paradigm does no more hold, and that he classical model selection theory such as AIC and MDL cannot be applied. This paper is a first step to establish a new theory for analyzing the accuracy of estimation or learning at around singularities.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.2
• /
• pp.135-147
• /
• 1990

A nuclear power plant can be viewed as a large complex man-machine system where high system reliability is obtained by ensuring that sub-systems are designed to operate at a very high level of performance. The chance of severe accident involving at least partial core-melt is very low but once it happens the consequence is very catastrophic. The prediction of risk in low probability, high-risk incidents must be examined in the contest of general engineering knowledge and operational experience. Engineering knowledge forms part of the prior information that must be quantified and then updated by statistical evidence gathered from operational experience. Recently, Bayesian procedures have been used to estimate rate of accident and to predict future risks. The Bayesian procedure has advantages in that it efficiently incorporates experts opinions and, if properly applied, it adaptively updates the model parameters such as the rate or probability of accidents. But at the same time it has the disadvantages of computational complexity. The predictive distribution for the time to next incident can not always be expected to end up with a nice closed form even with conjugate priors. Thus we often encounter a numerical integration problem with high dimensions to obtain a predictive distribution, which is practically unsolvable for a model that involves many parameters. In order to circumvent this difficulty, we propose a method of approximation that essentially breaks down a problem involving many integrations into several repetitive steps so that each step involves only a small number of integrations.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.1
• /
• pp.21-30
• /
• 1997

In accelerated life tests, the failure time of an item is observed under a high stress level, and based on the time the performances of items are investigated at the normal stress level. In this paper, when the mean of the prior of a failure rate is known in the exponential lifetime distribution with censored accelerated failure time data, we utilize the empirical Bayesian method by using the moment estimators in order to estimate the parameters of the prior distribution and obtain the empirical Bayesian predictive density and predictive intervals for a future observation under the normal stress level.

• Journal of Distribution Science
• /
• v.14 no.6
• /
• pp.27-37
• /
• 2016

Purpose - This study aims to suggest a developmental direction to small enterprisers who start their business. The developmental direction makes the small enterprisers more stable with providing the Business District Information System service, which offers the location and business area's information aimed at pre-enterprisers after analyzing its overcrowded index's current state and problems. Research design, data, and methodology - This research proposes the developmental direction for helping the pre-small enterprisers to have more stability through examining the Business District Information System's-operated by Small Enterprise and Market Service-overcrowded index's current state and problems. Results - This system has drawbacks about giving the start-up overcrowded index as follows: ① non-accurate consultative group for sharing the DB ② providing analysis information, not evaluation information ③ not to anticipate the changes of business types & the flow of business district and perceive the symptom data with providing predictive information. Conclusions - This system should be more publicized through the mass media for making it approachable with collecting the user's opinion and investigating customer satisfaction & the level of awareness.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.18-30
• /
• 2022

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

• Journal of Digital Contents Society
• /
• v.19 no.3
• /
• pp.529-535
• /
• 2018

Data is explosively growing, but many companies are still using data analysis only for descriptive analysis or diagnostic analysis, and not appropriately for predictive analysis or enterprise technology strategy analysis. In this study, we analyze the structured & unstructured patent data such as IPC code, inventor, filing date and so on by using big data analysis techniques such as network analysis and TF-IDF. Through this analysis, we propose analysis process to understand the core technology and technology distribution of competitors and prove it through data analysis.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.5
• /
• pp.31-40
• /
• 2020

This study investigates whether other comprehensive income (OCI) reported in the statement of comprehensive income (one of the main financial statements after the adoption of K-IFRS) predicts a firm's future performance. Using the quarterly data of Korean listed companies, we examine the association between OCI estimates and future earnings. First of all, we find that OCI is positively associated with earnings in both 1- and 2-quarter ahead, supporting the predictive value of OCI. When we break down OCI into its individual components, our results suggest that the net unrealized gains/losses on available-for-sale (AFS) investment securities are positively associated with future earnings, while the other components (e.g., net unrealized gains/losses on valuation of cash flow hedge derivatives) present insignificant results. In addition, we investigate whether the reliability in OCI estimates enhances the predictive value of OCI to predict future performance. We find that the predictive ability of OCI, in particular the net unrealized gains/losses on available-for-sale (AFS) investment securities, becomes more pronounced when firms are audited by the Big 4 audit firms. Overall, our study suggests that information content embedded in OCI can provide decision-useful information that is helpful for the prediction of future firm performance.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.7
• /
• pp.85-93
• /
• 2020

In peer-to-peer (P2P) loan markets, as most lenders are unskilled and inexperienced ordinary individuals, it is important to know the characteristics of borrowers that significantly impact their repayment performance. This study investigates the effects and importance of borrowers' past repayment performance track record within the platform to identify its predictive power. To this end, I analyze the detailed loan repayment data from two leading P2P lending platforms in Korea using a Cox proportional hazard, multiple linear regression, and logit models. Furthermore, the predictive power of the factors proxied by borrowers' track records are evaluated through the receiver operating characteristic (ROC) curves. As a result, it is found that the borrowers' past track record within the platform have the most important impact on the repayment performance of their current loans. In addition, this study also reveals that the borrowers' track record is much more predictive of their repayment performance than any other factor. The findings of this study emphasize that individual lenders must take into account the quality of borrowers' past transaction history when making a funding decision, and that platform operators should actively share the borrowers' past records within the markets with lenders.

• Journal of Welding and Joining
• /
• v.28 no.4
• /
• pp.33-40
• /
• 2010

The purpose of this study is to establish a predictive equation of transverse residual stress at the thick FCA butt weldment of large container vessel. The variables used were restraint degree, yield strength of base material, thickness of weldment and welding heat input. Restraint degree at the thick weldment of container ship having the various welding sequence was calculated using FEA. From the result, the H-type specimen was designed to reproduce the level of restraint degree at the actual weldment of containership. Based on the results, the predictive equations of the mean value and the distribution of transverse residual stress at each location of the weldment were established using dimensional analysis and multiple-regression method. The predictive equations were verified by comparing with those measured by XRD in the actual weldment of the ship.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.20 no.5
• /
• pp.448-455
• /
• 2015

A model predictive control (MPC) method without individual PWM has been recently researched to simplify and improve the control flexibility of a multilevel inverter. However, the input power of each H-bridge cell and the switching frequency of switching devices are unbalanced because of the use of a restricted switching state in the MPC method. This paper proposes a control method for balancing the switching patterns and cell power supplied from each isolated dc source of a cascaded H-bridge inverter. The supplied dc power from isolated dc sources of each H-bridge cells is balanced with the proposed cell balancing method. In addition, the switching frequency of each switching device of the CHB inverter becomes equal. A simulation and experimental results are presented with nine-level and five-level three-phase CHB inverter to validate the proposed balancing method.