• 청정기술
• /
• 제28권2호
• /
• pp.138-146
• /
• 2022

Electricity has become a factor that dramatically affects the market economy. The day-ahead system marginal price determines electricity prices, and system marginal price forecasting is critical in maintaining energy management systems. There have been several studies using mathematics and machine learning models to forecast the system marginal price, but few studies have been conducted to develop, compare, and analyze various machine learning and deep learning models based on a data-driven framework. Therefore, in this study, different machine learning algorithms (i.e., autoregressive-based models such as the autoregressive integrated moving average model) and deep learning networks (i.e., recurrent neural network-based models such as the long short-term memory and gated recurrent unit model) are considered and integrated evaluation metrics including a forecasting test and information criteria are proposed to discern the optimal forecasting model. A case study of South Korea using long-term time-series system marginal price data from 2016 to 2021 was applied to the developed framework. The results of the study indicate that the autoregressive integrated moving average model (R-squared score: 0.97) and the gated recurrent unit model (R-squared score: 0.94) are appropriate for system marginal price forecasting. This study is expected to contribute significantly to energy management systems and the suggested framework can be explicitly applied for renewable energy networks.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.999-1007
• /
• 2006

The semiparametric gamma frailty models have been often used for multivariate survival analysis because they give an explicit marginal likelihood. The commonly used estimation procedure is the profile likelihood method based on marginal likelihood, which provides the same parameter estimates as the EM algorithm. In this paper we show in finite samples the standard profile-likelihood method can lead to an underestimation of parameters, particularly for the frailty parameter. To overcome this problem, we propose an adjusted profile-likelihood method. For the illustration a numerical example and a small-sample simulation study are presented.

• Communications for Statistical Applications and Methods
• /
• 제11권2호
• /
• pp.381-397
• /
• 2004

The marginal likelihood has become an important tool for model selection in Bayesian analysis because it can be used to rank the models. We discuss the marginal likelihood for Poisson regression models that are potentially useful in small area estimation. Computation in these models is intensive and it requires an implementation of Markov chain Monte Carlo (MCMC) methods. Using importance sampling and multivariate density estimation, we demonstrate a computation of the marginal likelihood through an output analysis from an MCMC sampler.

• 대한치과기공학회지
• /
• 제34권2호
• /
• pp.105-111
• /
• 2012

Purpose: The purpose this study was to evaluate the marginal fitness of metal copings fabricated using rapid prototyping method and to compare the fitness with copings by conventional method. Then clinical availability of fixed dental prostheses (FDPs) fabricated using rapid prototyping method shall be confirmed based on marginal fitness. Methods: Ten same cases of3 unit FDPs epoxy models (abutment teeth 14 and 16) were manufactured. Each of ten epoxy models were scanned by 3shape D-700 scanner to be designed by experienced technician, and photopolymer 3 unit FDPs were fabricated using rapid prototyping methodand fabricated using Lost wax technique (LW) with same models. Marginal fitness of 3 unit FDPs were measured by silicone replica technique. T-test of independent sample for statistical analysis was executed with SPSS 12.0K for Windows. (${\alpha}$=.05) Results: Significantly higher mean (SD) marginal fitness (P<.000) were observed in the RP group $(95.9(18.0){\mu}m$ compared to the conventionally LW group $(80.1(13.8){\mu}m$. Conclusion: Marginal fitness of LW group showed excellent rather than RP group. However marginal fitness of 3 unit FDPs fabricated by RP method did not get out of clinical allowance value range significantly to allow clinical application.

• 한국치위생학회지
• /
• 제13권2호
• /
• pp.361-368
• /
• 2013

Objectives : The purpose of this in vitro study was to evaluate the effect of firing cycles on the marginal and internal fit of metal ceramic crown. Methods : Ten same cases of stone models (abutment teeth 11) were manufactured. Ten cobalt-chrome cores were made per each models and the marginal and internal fit was evaluated through a silicone replica technique. The marginal and internal fit of specimens was measured twice. The first measurement was done after manufacturing cobalt-chrome alloy core and the second measurement was done after porcelain firing. T-test of paired sample for statistical analysis was executed with SPSS 12.0K for Windows (${\alpha}$=0.05). Results : Mean(SD) marginal and internal fit were 77.1(23.3) ${\mu}m$ for the cobalt-chrome alloy core group and 84.4(21.9) ${\mu}m$ for the metal-ceramic crown group. They were statistically significant differences between groups for marginal and internal fit (p<.05). Conclusions : All metal ceramic crowns showed marginal and internal fit ranged within the current clinical recommendations.

• Communications for Statistical Applications and Methods
• /
• 제15권6호
• /
• pp.969-976
• /
• 2008

Mixed linear models have been widely used in various correlated data including multivariate survival data. In this paper we extend hierarchical-likelihood(h-likelihood) approach for mixed linear models with right censored data to that for left censored data. We also allow a general random-effect structure and propose the estimation procedure. The proposed method is illustrated using a numerical data set and is also compared with marginal likelihood method.

• 대한치과기공학회지
• /
• 제41권1호
• /
• pp.1-7
• /
• 2019

Purpose: The objectives of this study was to evaluate clinical adaptation of dental prostheses printed by 3 dimensional(3D) printing technology. Methods: Ten study models were prepared. Ten specimens of experimental group were printed by 3D printing(3DP group). As a control group, 10 specimens were fabricated by casting method on the same models. Marginal gaps of all specimens were measured to evaluate clinical adaptation. Marginal adaptations were measured using silicone replica technique and measured at 8 sites per specimen. Wilcoxon's signed-ranks test was used for statistical analysis(${\alpha}=0.05$). Results: Means of marginal adaptations were $95.1{\mu}m$ for 3DP group and $75.9{\mu}m$ for CAST group(p < 0.000). Conclusion : However, the mean of the 3DP group was within the clinical tolerance suggested by the previous researchers. Based on this, dental prosthesis fabricated by 3D printing technology is considered to be clinically acceptable.

• 응용통계연구
• /
• 제18권2호
• /
• pp.395-410
• /
• 2005

많은 수의 범주형 변수에 의한 대규모 분할표 분석을 위하여 차원축소(collapsibility) 성질을 이용한 분석 방법을 제안하였다. kullback-Leibler의 발산 측도(divergence measure)를 이용한 서로 완전한 연관을 갖는 변수그룹을 결정하는 방법을 제안하였으며, 제안된 방법에 의한 변수그룹은 주변 로그선형모형(marginal log-linear models)에 의하여 변수들간의 연관성을 식별할 수 있다. 제안된 방법의 적용 예로 데이터 마이닝에서 흔히 접할 수 있는 대규모 분할표 자료인 소비자들의 구매행위 분석을 위한 장바구니 자료의 분석 결과를 제시하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권5호
• /
• pp.1389-1397
• /
• 2016

Semi-parametric frailty model with nonparametric baseline hazards has been widely used for the analyses of clustered survival-time data. The frailty models can be fitted via an auxiliary Poisson hierarchical generalized linear model (HGLM). For the inferences of the frailty model marginal likelihood, which gives MLE, is often used. The marginal likelihood is usually obtained by integrating out random effects, but it often requires an intractable integration. In this paper, we propose to obtain the MLE via Laplace approximation using a Poisson HGLM approach for semi-parametric frailty model. The proposed HGLM approach uses hierarchical-likelihood (h-likelihood), which avoids integration itself. The proposed method is illustrated using a numerical study.

• The Journal of Advanced Prosthodontics
• /
• 제7권3호
• /
• pp.257-263
• /
• 2015

PURPOSE. In this study, we aimed to evaluate the amount of marginal gap with two different substructure materials using identical margin preparations. MATERIALS AND METHODS. Twenty stainless steel models with a chamfer were prepared with a CNC device. Marginal gap measurements of the galvano copings on these stainless steel models and Co-Cr copings obtained by a laser-sintering method were made with a stereomicroscope device before and after the cementation process and surface properties were evaluated by scanning electron microscopy (SEM). A dependent t-test was used to compare the mean of the two groups for normally distributed data, and two-way variance analysis was used for more than two data sets. Pearson's correlation analysis was also performed to assess relationships between variables. RESULTS. According to the results obtained, the marginal gap in the galvano copings before cementation was measured as, on average, $24.47{\pm}5.82{\mu}m$ before and $35.11{\pm}6.52{\mu}m$ after cementation; in the laser-sintered Co-Cr structure, it was, on average, $60.45{\pm}8.87{\mu}m$ before and $69.33{\pm}9.03{\mu}m$ after cementation. A highly significant difference (P<.001) was found in marginal gap measurements of galvano copings and a significant difference (P<.05) was found in marginal gap measurements of the laser-sintered Co-Cr copings. According to the SEM examination, surface properties of laser sintered Co-Cr copings showed rougher structure than galvano copings. The galvano copings showed a very smooth surface. CONCLUSION. Marginal gaps values of both groups before and after cementation were within the clinically acceptable level. The smallest marginal gaps occurred with the use of galvano copings.