• International Journal of Precision Engineering and Manufacturing
• /
• 제9권1호
• /
• pp.12-18
• /
• 2008

This paper describes two run-to-run controllers, a nonlinear multiple exponential-weight moving-average (NMEWMA) controller and a dynamic model-tuning minimum-variance (DMTMV) controller, for photolithography processes. The relationships between the input recipes (exposure dose and focus) and output variables (critical dimensions) were formed using an experimental design method, and the photolithography process model was built using a multiple regression analysis. Both the NMEWMA and DMTMV controllers could update the process model and obtain the optimal recipes for the next run. Quantified improvements were obtained from simulations and real photolithography processes.

• 한국시뮬레이션학회논문지
• /
• 제23권4호
• /
• pp.203-210
• /
• 2014

본 연구는 생산공정운영시 발생하는 담당자의 의사결정 지원을 위한 학습형 공정 의사결정 시스템 구축방법에 대한 것이다. 먼저 추출 및 누적된 각 공정 별 이력 데이터에서, 주요한 주요자원(Critical Resource)을 단계적 회귀법에 따라 선정한다. 선정된 주요자원을 독립변수로 취급하여 담당자의 의사결정 대상이 되는 공정운영 성과를 종속변수로 하는 회귀모형을 산출하고, 해당 주요자원으로 구성된 시뮬레이션 모형을 설계한다. 메타휴리스틱 방법을 통하여 의사결정 시점의 생산계획 및 목적에 대한 시뮬레이션 분석을 실행하고, 복수 대안 및 가능해(기대성과)를 산출한다. 각각의 대안에서 주요자원 별 회귀모형을 구성하는 분석 값을 회귀식에 대입하고, 여기에서 얻어지는 값과 시뮬레이션 분석에 의해 산출된 가능해 간의 비교를 통하여 그 차이가 가장 작은 대안을 최적대안으로 선정하고 실제 공정운영 의사결정에 반영하여 생산을 실시한다. 이때 발생하는 공정 이력 데이터들은 이후 의사결정을 위한 회귀모형에 피드백 된다.

• Journal of the Korean Statistical Society
• /
• 제22권1호
• /
• pp.27-37
• /
• 1993

Since the analytic expression for a diagnostic in the logistic regression model is not available, one-step estimation is often used by a case-deletion point of view. In this paper, infinitesimal perturbation approach is used, and it is shown that the scale transformation of infinitesimal perturbation approach is eventually equal to the weighted perturbation of local influence approach and the replacement measure. Also, multiple cases deletion for the masking effect is considered.

• Journal of the Korean Statistical Society
• /
• 제12권2호
• /
• pp.81-90
• /
• 1983

The least squares estimator of disturbance variance in a regression model is biased under a serial correlation. Under the assumption of an AR(I), Theil(1971) crudely related the bias with the autocorrelation of the disturbances and the autocorrelation of the explanatory variable for a simple regression. In this paper we derive a relation which relates the bias with the autocorrelation of disturbances and the autocorrelation of explanatory variables for a multiple regression with improved precision.

• Journal of Positioning, Navigation, and Timing
• /
• 제4권2호
• /
• pp.79-85
• /
• 2015

Existing Differential GPS (DGPS) pseudorange correction (PRC) generation techniques based on a virtual reference station cannot effectively assign a weighting factor if the baseline distance between a user and a reference station is not long enough. In this study, a virtual reference station DGPS PRC generation technique was developed based on an enhanced inverse distance weighting method using an exponential function that can maximize a small baseline distance difference due to the dense arrangement of DGPS reference stations in South Korea, and its positioning performance was validated. For the performance verification, the performance of the model developed in this study (EIDW) was compared with those of typical inverse distance weighting (IDW), first- and second-order multiple linear regression analyses (Planar 1 and 2), the model of Abousalem (1996) (Ab_EXP), and the model of Kim (2013) (Kim_EXP). The model developed in the present study had a horizontal accuracy of 53 cm, and the positioning based on the second-order multiple linear regression analysis that showed the highest positioning accuracy among the existing models had a horizontal accuracy of 51 cm, indicating that they have similar levels of performance. Also, when positioning was performed using five reference stations, the horizontal accuracy of the developed model improved by 8 ~ 42% compared to those of the existing models. In particular, the bias was improved by up to 27 cm.

• Journal of Biosystems Engineering
• /
• 제22권3호
• /
• pp.333-342
• /
• 1997

The objective of this research was to develop model equations for measuring rice milling ratio by using visible / HIR spectroscopy. Twelve kinds of brown rice(n = 149) were milled to obtain various milling ratio ranged from 86% to 94%. Visible/NIR spectra were collected with a spectrophotometer with sample transport module. The reflectance and transmission spectra were measured in the range of 400~2, 500nm and 600~1, 400nm, respectively, with 2 nm intervals. Multiple linear regression(MLR), Partial least square (PLS), and Artificial neural network(ANN) were used to develop models. Model developed with reflectance spectra showed better prediction results then those with transmission spectra. The MLR model with six-wavelength obtained from first derivative spectra gave to the best results for measuring the rice milling ratio(SEP = 0.535, , $r^2$ = 0.980). The PLS model(SEP = 0.604, $r^2$= 0.976) and ANN model(SEP = 0.566, $r^2$= 0.978) also can be used to determine the rice milling ratio effectively.

• 한국도로학회논문집
• /
• 제15권3호
• /
• pp.93-101
• /
• 2013

PURPOSES : This study is to investigate the relationship of socioeconomic characteristics and road network structure with traffic growth patterns. The findings is to be used to tweak traffic forecast provided by traditional four step process using relevant socioeconomic and road network data. METHODS: Comprehensive statistical analysis is used to identify key explanatory variables using historical observations on traffic forecast, actual traffic counts and surrounding environments. Based on statistical results, a multiple regression model is developed to predict the effects of socioeconomic and road network attributes on traffic growth patterns. The validation of the proposed model is also performed using a different set of historical data. RESULTS : The statistical analysis results indicate that several socioeconomic characteristics and road network structure cleary affect the tendency of over- and under-estimation of road traffics. Among them, land use is a key factor which is revealed by a factor that traffic forecast for urban road tends to be under-estimated while rural road traffic prediction is generally over-estimated. The model application suggests that tweaking the traffic forecast using the proposed model can reduce the discrepancies between the predicted and actual traffic counts from 30.4% to 21.9%. CONCLUSIONS : Prediction of road traffic growth patterns based on surrounding socioeconomic and road network attributes can help develop the optimal strategy of road construction plan by enhancing reliability of traffic forecast as well as tendency of traffic growth.

• 한국지리정보학회지
• /
• 제20권3호
• /
• pp.181-194
• /
• 2017

본 연구의 목적은 산림재적 현장자료와 항공 LiDAR 자료 기반의 산림재적 추정을 위한 회귀모델의 개발이다. 추정 모델은 경상북도 봉화군 지역에서 임의추출법에 의해 선정된 30개의 원형 표본지로부터 산출한 표본지별 산림재적을 반응변수로 하고, 항공 LiDAR 원자료로부터 개별 표본지의 고도분포 백분위수(Height Percentiles, HP) 및 층위 단위 점 개체수 백분율(Height Bin, HB)을 추출하여 예측변수로 사용하여 구성하였다. 단순선형회귀분석, 이차 다항회귀분석 및 단계적 회귀분석 방법을 이용한 다중회귀분석을 실시하여 적합모델들의 후보들을 도출하였으며, 검증을 위하여 각 모델별로 교차 타당성 검증을 실시하여 PRESS 통계치를 구하였다. 모델의 $R^2$ 및 PRESS을 비교하여 적합성을 검토한 결과, $HB_{5-10}$, $HB_{15-20}$, $HB_{20-25}$, $HBgt_{25}$의 다중회귀모델의 $R^2$이 0.509로 가장 높고, $HP_{25}$ 단순회귀모델의 PRESS 값이 122.352으로 가장 낮은 것으로 나타났다. 수직구조가 복잡한 우리나라 산림재적을 추정하는 모델로는 다양한 수직적 정보를 포함하고 있는 $HB_{5-10}$, $HB_{15-20}$, $HB_{20-25}$, $HBgt_{25}$이 상대적으로 보다 적합하다고 사료된다.

• 대한인간공학회지
• /
• 제20권1호
• /
• pp.45-62
• /
• 2001

This study suggests a genetic algorithm-based partial least squares (GA-based PLS) method to select the design variables for building a usability model. The GA-based PLS uses a genetic algorithm to minimize the root-mean-squared error of a partial least square regression model. A multiple linear regression method is applied to build a usability model that contains the variables seleded by the GA-based PLS. The performance of the usability model turned out to be generally better than that of the previous usability models using other variable selection methods such as expert rating, principal component analysis, cluster analysis, and partial least squares. Furthermore, the model performance was drastically improved by supplementing the category type variables selected by the GA-based PLS in the usability model. It is recommended that the GA-based PLS be applied to the variable selection for developing a usability model.

• Journal of Korea Artificial Intelligence Association
• /
• 제1권1호
• /
• pp.11-16
• /
• 2023

Accurate hospital case modeling and prediction are crucial for efficient healthcare. In this study, we demonstrate the implementation of regression analysis methods in machine learning systems utilizing mathematical statics and machine learning techniques. The developed machine learning model includes Bayesian linear, artificial neural network, decision tree, decision forest, and linear regression analysis models. Through the application of these algorithms, corresponding regression models were constructed and analyzed. The results suggest the potential of leveraging machine learning systems for medical research. The experiment aimed to create an Azure Machine Learning Studio tool for the speedy evaluation of multiple regression models. The tool faciliates the comparision of 5 types of regression models in a unified experiment and presents assessment results with performance metrics. Evaluation of regression machine learning models highlighted the advantages of boosted decision tree regression, and decision forest regression in hospital case prediction. These findings could lay the groundwork for the deliberate development of new directions in medical data processing and decision making. Furthermore, potential avenues for future research may include exploring methods such as clustering, classification, and anomaly detection in healthcare systems.