• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.463-473
• /
• 2001

선형모형의 회귀계수의 L$_1$-추정량의 점근분포는 오차항의 중앙값에 종속되어있는데, 이 값은 잔차의 순서통계량의 함수로 추정될 수 있다. 본 논문에서는 오차항 중앙값의 추정량을 유도하는 몇 가지 방법을 소개하고 몬테칼로 실험을 통하여 가장 바람직한 추정량의 형태를 제안하였다. 또한 제안한 추정량을 이용하면 검정문제에서도 좋은 결과를 얻을 수 있음을 보였다.

• Korean Journal of Optics and Photonics
• /
• v.34 no.1
• /
• pp.22-30
• /
• 2023

The use of segmented mirrors is one of the ways to make the primary mirror of a spaceborne satellite larger, where several small mirrors are combined into a large monolithic mirror. To align multiple segmented mirrors as one large mirror, there must be no discontinuity in the x, y-axis (tilt) and axial alignment error (piston) between adjacent mirrors. When the tilt and piston are removed, we can collect the light in one direction and get an expected clear image. Therefore, we need a precise wavefront sensor that can measure the alignment error of the segmented mirrors in nm scale. The tilt error can be easily detected by the point spread image of the segmented mirrors, while the piston error is hard to detect because of the absence of apparent features, but makes a downgraded image. In this paper we used an optical testing interferometer such as a Fizeau interferometer, which has various advantages when aligning the segmented mirror on the ground, and focused on measuring the axial displacement error of a segmented mirror as the basic research of measuring the piston errors between adjacent mirrors. First, we calculated the relationship between the axial displacement error of the segmented mirror and the surface defocus error of the interferometer and verified the calculated formula through experiments. Using the experimental results, we analyzed the measurement uncertainty and obtained the limitation of the Fizeau interferometer in detecting axial displacement errors.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.30-30
• /
• 2015

유역에 내린 강우의 총량은 홍수나 갈수 측면에서 매우 중요하다. 점 강우량에 의해 측정된 강우량을 이용하여 유역 총강우량으로 환산하는 과정에 많은 오차가 포함되어 있다. 선행연구에 따르면, 우량계를 통한 강우관측에서 언더캐치(undercatch)에 의한 계통오차는 일반적으로 5~16%, 우연오차는 약 5%가 발생된다고 보고하였으며, 점 우량계 자료를 내삽하여 공간자료로 변환할 경우 0.1km 규모에서 표준오차가 4~14%, 1km 규모에서는 33~45%, 10km 규모에서는 약 65% 정도 발생된다고 한다. 이러한 우량계 관측오차 및 강우자료 처리과정에서 발생되는 오차는 유역의 유출량 계산에 영향을 주어 홍수예보 정확도를 크게 떨어뜨릴 수 있다. 우리나라에서는 지금까지 유역 총강우량 산정 측면에서 지점강우량의 불확실성에 대한 연구가 많이 이루어지지 못하였다. 본 연구에서는 우리나라에서 주로 사용되고 있는 전도형 우량계를 이용하여 소규모 구역에서 관측되는 강우관측의 불확실성을 분석하고자 하였다. 연구에 사용된 우량계는 0.5mm 급 표준 전도형 우량계로 정밀도는 시간당 1~100mm 기준으로 ${\pm}1%$를 기록하여 기상검정규격인 ${\pm}3%$를 만족하고 있다. 이 우량계는 한국건설기술연구원 안동하천실험센터 내에 장애물이 없는 평지에 60m 간격으로 총 6대($2{\times}3$)를 설치하여 2014년 7월 11일부터 9월 2일까지 54일간 관측을 수행하였다. 관측기간 동안 2대의 우량계가 수일동안 강우가 기록되지 않아서 분석에서 제외하였다. 우량계 상호 간의 누적강우량(54일간)을 비교한 결과 2.5~25.5mm의 차이를 나타냈다. 강우강도별 강우량 합계를 비교한 결과 시간당 1mm 이상에서는 약 1%의 차이가 났으며, 시간당 15mm 이상에서는 7.4%의 차이를 나타내어 강도가 큰 강우사상에서 우량계 간의 관측오차가 더 크게 나타났다. 또한 우량계 상호 간의 상관계수를 분석한 결과, 우량계 간의 거리가 가까울수록 그리고 누적시간이 길수록 상관계수는 커지는 것을 확인할 수 있었다. 도출된 결과를 토대로 하면 앞서 언급한 바와 같이 점 우량계 자료를 내삽하거나 유역 또는 계산격자의 대푯값으로 사용하여 1시간 이하 단위로 유출모의를 할 경우 심각한 오차를 발생시킬 수 있음을 시사한다. 보다 신뢰성 있는 홍수예보와 효율적인 유역관리를 위해서는 점 중심의 강우 관측이 아닌 면적 우량에 대한 관측이 이루어져야 하며 이를 위한 기술의 개발이 필요하다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.438-441
• /
• 1998

최근 미국 내 표준안으로서 많이 사용되고 있는 AC-3 오디오 알고리듬은 그 복잡성으로 인하여 실시간 구현을 위해선 프로세서로 구현하는 것이 적합하다. AC-3 복호화 알고리듬은 많은 부분이 실수연산으로 이루어져 있으므로 소수점을 고려한 연산이 필요한데, 프로세서로 구현할 때는 적은 비용과 빠른 속도로 실수연산을 수행하기 위해서 부동소수점보다는 고정소수점 연산이 유리하다. 그러나 고정소수점 연산시 발생하는 유한 단어길이 효과로 인하여 양자화 오차가 발생하므로 복호화된 오디오 신호의 음질저하를 최소화하기 위해서는 최적화가 필요하다. 본 논문에서는 AC-3 복호화 알고리듬의 부분별 양자화 오차를 분석하고 그 결과 가장 많은 오차를 발생시키는 역 TDAC 변환의 오차를 최적화하였다. Fast TDAC 변환이 FFT로 이루어져 있으므로 고정 소수점 연산시 오차가 적은 FFT 구조를 제안하였다. 제안된 구조를 사용하여 AC-3 고정소수점 복호화기를 C 언어를 사용하여 구현하였으며, AC-3 부동소수점 복호화기와 최종 PCM을 비교하여 그 성능을 평가하였다.

• The korean journal of orthodontics
• /
• v.40 no.2
• /
• pp.77-86
• /
• 2010

Objective: The purposes of this study were to evaluate the reproducibility and reliability of head posture obtained by registering outer canthus as a soft tissue landmark with the Outer Canthus Indicator (OCI). Methods: Twenty-one adults with normal facial morphology were enrolled in this study (mean age $27.5\;{\pm}\;1.72$ years). To register initial head posture, height of the outer canthus from the ear rod plane was measured using OCI. Head posture was reproduced by moving the head upwards and downwards until the outer canthus was in a straight line with the indicator set at a registered height. After the head posture is reproduced by two operators after two days, lateral photographs were taken. Computerized photometric analyses of the photographs were performed. Results: The head rotations around the transverse axis were $0.69\;{\pm}\;0.43^{\circ}$, $0.98\;{\pm}\;0.65^{\circ}$ from each of the two operators. Standard errors were $0.09^{\circ}$ and $0.14^{\circ}$ each, which were similar to results from past research findings. There were no significant differences between the data from the two operators (p > 0.05). There were no correlations between the head rotation around the horizontal and vertical axes (p > 0.05). Conclusions: The present study suggests that OCI-registered head posture may minimize errors from vertical head rotation in cephalometry and photometry.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.2
• /
• pp.149-160
• /
• 2015

This study aims to estimate the forest volumes of the upper region of Nam-Han River in ecosystem zoning by forest types and age classes, and to suggest the optimal estimation method through the comparison of the standard errors according to the spatial unit. In the estimation of forest volumes, we used both of direct estimation, which uses sample plots of the target area only, and synthetic estimation, which includes sample plots of the expanded areas as well as those of the target area. As for the spatial expansion, we applied four standards for synthetic estimator: Mountainous zone, Neighbor ecosystem region, Gangwon province, and Buffer zone. The results show that average forest volume per ha, calculated by direct estimation, was $143.5m^3/ha$, while that by synthetic estimation with each standard, was estimated at $146.9m^3/ha$ by Gangwon province, $144.8m^3/ha$ by Buffer zone, $139.8m^3/ha$ by Neighbor ecosystem region, and $138.6m^3/ha$ by Mountainous zone, respectively. The standard errors of direct estimation was $1.79m^3/ha$, while those of synthetic estimation showed not a great difference among the errors. Meanwhile, considering the standard errors by forest type, the lowest was ${\pm}2.3m^3/ha$ of broad-leaved forest, followed by ${\pm}3.3m^3/ha$ of mixed forest, and ${\pm}4.8m^3/ha$ of coniferous forest.

• Journal of the Speleological Society of Korea
• /
• v.14 no.15
• /
• pp.42-90
• /
• 1987

Lee, Moon Won reported by 63 kinds lescribing the petrography and bulk chemical Composition in Petrology of Cheju volcanic island. The total Chemical Composition data was analyzed by the program of FORTRAN77. First, the Conversition equations and the scatter diagram were examined to the analysis, by the least square method. Next, a statistical data requested a mean Value, maximum value, minimum value, the range, the standard deviation, the variance, the Standord Error and the Coefficient of variation. In the standard deviation, a small Composition is MnO and P$_2$O$\sub$5/, a large Composition is SiO$_2$, Mgo and FeO. The Standard error and the variance were the tandency looked like the Standard deviation well. However, the Coefficient Variation differs from the Standard deviation. Where, a large Coefficient of variation are H$_2$O$\^$-/ and H$_2$O$\^$+/, a small Coefficient of variation are Al$_2$O$_3$ and SiO$_2$. The Correlation of Coefficient Can be Calculated numerically from the relation between SiO$_2$, Al$_2$O$_3$ and TiO$_2$ to other Compositions.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.8
• /
• pp.572-579
• /
• 2003

By comparing the measured optical reflection spectra with calculated one by the transfer-matrix method (TMM) in epitaxial wafers for vertical-cavity surface-emitting lasers (VCSELs), we have estimated the systematic thickness errors in a simple and nondestructive way. The experimentally confirmed technique is based on the finding that the shape of the reflection spectra depends mainly on a newly defined single parameter, the effective error in the n-mirror layers, and the thickness error in the active cavity simply shifts the Fabry-Perot resonance wavelength. Also shown is that the proposed method is reliable when the relative standard deviation of the random thickness errors is less than 0.005. Because reflection spectra are routinely measured, we can easily estimate the thickness errors nondestructively with high spatial resolution.

• Korean Journal of Food Science and Technology
• /
• v.38 no.6
• /
• pp.835-837
• /
• 2006

The geographical origin of Tricholoma matsutake mushrooms was studied using near-infrared spectroscopy. Modified partial least-square regression analyses were used to discriminate geographical origin. Two-hundred fifty-six of 259 actual domestic Tricholoma matsutake were classified as domestic produce, Sixty of 81 actual imported mushrooms were correctly classified as imported, while the other 21 imported from North Korea were not clearly classified. The accuracy of geographical origin discrimination was 92.94% The correlation coefficient, standard error of calibration, and standard error of prediction from modified partial least-square regression analysis were 0.84, 15.10% and 18.30% respectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1406-1411
• /
• 2005

The creep rupture data for type 316LN stainless steels were collected through literature survey or experimental data produced in KAERI. Using these data, polynomial equations for predicting creep life were obtained by Larson-Miller (L-M), Orr-Sherby-Dorn (O-S-D) and Manson-Haferd (M-H) etc. time-temperature parametric (TTP) methods. Standard error of estimate (SEE) values for the each parameter was obtained with different temperatures through the statistical process of the creep data. The results of L-M, O-S-D and M-H methods showed good creep-life prediction, but M-H method showed better agreement than L-M and O-S-D methods. Especially, it was found that SEE values of M-H method at $700^{\circ}C$ were lower than that of L-M and O-S-D methods.