• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.167-175
• /
• 2003

In this paper we develop a robust procedure to estimate regression coefficients for a linear model with censored and truncated data based on simplicial regression depth. Simplicial depth of a point is defined as the proportion of data simplices containing it. This simplicial depth can be extended to regression problem with censored and truncated data. Any line can be given a depth and the deepest regression line is the line with the maximum simplicial regression depth. We show how the proposed regression performs through analyzing AIDS incubation data.

• 응용통계연구
• /
• 제20권2호
• /
• pp.313-322
• /
• 2007

오염이 있는 생존자료에서 여러 가지 회귀뎁스(regression depth)를 비교 연구하였다. 중도절단 자료에서 회귀뎁스에 대한 정의는 Park과 Hwang(2003)의 반공간회귀뎁스(halfspace regression depth)와 Park(2003)의 심플리셜 회귀뎁스(simplicial regression depth)가 있다. 본 논문은 Hubert 등(2001)이 제안한 사영회귀뎁스(projection regression depth)를 생존자료에서 사용하는 방법을 제시하고 이 방법과 기존의 뎁스기반 회귀모형과의 비교를 다양한 오염 상황에서 실시하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제15권2호
• /
• pp.307-316
• /
• 2004

Principal Component Regression(PCR) and Partial Least Squares Regression(PLSR) are the two most popular regression techniques in chemometrics. In the field of chemometrics usually the number of regressor variables greatly exceeds the number of observation. So we have to reduce the number of regressors to avoid the identifiability problem. In this paper we compare PCR and PLSR techniques combined with various robust regression methods including regression depth estimation. We compare the efficiency, goodness-of-fit and robustness of each estimators under several contamination schemes.

• 응용통계연구
• /
• 제17권3호
• /
• pp.475-488
• /
• 2004

위치추정량에서 로버스트한 추정기법 중의 하나로 알려진 데이터 뎁스(depth)를 회귀추정에 적용한 회귀뎁스(regression depth)는 Rousseeuw and Hubert(1999)에 의하여 제안되었다. 이 이외의 회귀뎁스 추정량으로는 심플리셜(simplicial) 뎁스와 사영(projection) 개념의 뎁스 회귀추정량들이 있다. 본 논문에서는 뎁스 기반 회귀추정량들의 성능에 대한 모의실험을 여러 오염 조건에서 행하여 비교하였으며 기존의 우수한 로버스트성을 지니는 추정량으로 최근에 제안된 HBR추정량(Chang et al., 1999)들과의 비교연구도 하였다. 2차원 공간에서의 실험은 전반적으로 사영뎁스기반 회귀추정량이 좋은 결과를 보여주었다.

• 반도체디스플레이기술학회지
• /
• 제11권3호
• /
• pp.19-25
• /
• 2012

The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.

• 한국기계가공학회지
• /
• 제11권6호
• /
• pp.36-41
• /
• 2012

In this study, we turning plastic mold steel (STAVAX) against cutting speed, depth of cut, feed rate using whisker reinforced ceramic tool (WA1). To predict cutting force, analyze principal, radial, feed force with multi-regression analysis. Results are follows: From the analysis of variance, affected factor to cutting force feed rate, depth of cut, cutting speed in order and cutting speed was very small affect to cutting force. From multi-regression analysis, we extracted regression equation and the coefficient of determination$(R^2)$ was 0.9, 0.88, 0.856 at principal, radial and feed force. It means regression equation is significant. From the experimental verification, it was confirmed that principal, radial and feed force was predictable by regression equation.

• Journal of Biosystems Engineering
• /
• 제9권2호
• /
• pp.27-36
• /
• 1984

This study was carried out to investigate the effects of the tilling depth, tilling travel speed and soil shear stress on the tilling load characteristics and power requirement for rotary tillers. The results obtained from the study are summarized as follows. 1. The average and maximum PTO torque increased as the tilling depth, tilling pitch and soil shear stress increased. A multiple linear regression equation to estimate the average PTO torque in terms of the above parameters was developed. 2. The ratios of maximum PTO torque to the average torque were in the range of 1.17 to 1.65 for the various tilling conditions tested. The variation in PTO torque increased greatly as the tilling pitch and soil shear stress increased, but decreased as the tilling depth increased. 3. Power requirement for the PTO shaft increased with the tilling depth, travel speed and soil shear stress, but decreased slightly as the tilling pitch increased. A multiple linear regression equation to estimate power requirement for the PTO shaft in terms of the above parameters was developed. 4. The specific power requirement for the rotary tiller was in the range of $0.008-0.015ps/cm^2$ for the various tilling conditons tested. The specific tilling capacity decreased as the tilling depth and soil shear stress increased, but increased with the tilling pitch. A multiple linear regression equation to estimate the specific tilling capacity in terms of the above parameters was developed.

• 한국생산제조학회지
• /
• 제25권1호
• /
• pp.83-88
• /
• 2016

Because of the increasing tool cost for cutting hard-to-cut materials, abrasive water jet (AWJ) milling recently has been regarded as a potential alternative machining method. However, it is difficult to control the depth and width of cut in AWJ milling because they vary depending on many AWJ cutting parameters. On 27 conditions within a limited range of pressure, feed rate, and abrasive flow rate, AWJ cutting was conducted on titanium, and depth profiles were measured with a laser sensor. From the depth profile data, depth and width of cut were acquired at each condition. The relationships between depth and parameters and between width and parameters were derived through regression analysis. The former can provide proper cutting conditions and the latter the proper pick feed necessary to generate a milled surface. It is verified that pressure mostly affects depth, whereas abrasive flow rate mostly affects width.

• 한국농공학회논문집
• /
• 제47권1호
• /
• pp.35-42
• /
• 2005

The research has been done to obtain a empirical equation for the depth of replacement by the analysis of data collected from 8 sea-dike construction sites of south coast of Korean peninsula. The correlation analysis results show that the depth of replacement was mainly dependent upon the height of embankment and the undrained shear strength of soft soil. The suggested regression equation was quite well predicted the depth of replacement and recommended to use under certain restrictions where the embankment height was less than 10m and under 0.2 kgf/cm^{2} of the undrained shear strength of soil.

• 한국터널지하공간학회 논문집
• /
• 제12권1호
• /
• pp.1-14
• /
• 2010

지금까지 Martin 등(1999)의 선형관계식에 의한 스폴링 깊이 평가법이 널리 이용되어 왔으나, 이 방법은 원형 공동에만 적용될 수 있으며 실제 스폴링 발생현장에 적용한 결과 과대평가하는 결과를 보였다. 한편, 스폴링 폭을 평가하는 방법은 아직까지 제시되어 있지 않아 적절하게 평가가 이루어지지 못했다. 그러나, 스폴링 영역에 대한 적절한 보강을 위해서는 스폴링 깊이와 스폴링 폭에 대한 정량적인 평가가 필수적이다. 본 연구에서는 스폴링 관측사례와 스폴링 발생현장의 CWFS 수치해석 사례를 통해 3가지 스폴링 평가인자의 함수로 표현되는 정규화 스폴링 깊이와 정규화 스폴링 폭의 선형회귀식을 도출하였고, 통계추론에 의한 95% 신뢰구간을 통해 회귀식의 신뢰성을 검증하였다. 제안된 선형회귀식으로부터 예측된 스폴링 깊이와 스폴링 폭은 회귀관계의 분산도를 고려한 가중치를 적용함으로써 현장관측결과를 합리적으로 예측할 수 있었다.