• 한국정보처리학회논문지
• /
• 제4권12호
• /
• pp.3200-3210
• /
• 1997

훼손된 타원 및 복잡한 형태의 영상에서 타원 검출에 최소자승법(LSM : Least Square Method)을 적용할 수 있는데 이는 데이터가 비정규 오류 분포를 따르거나 특이한점들이 있는 상태에서는 신뢰할 수 있는 결과를 얻을 수 없다. 특히 최소자승법은 훼손된 부분을 데이터가 없는 것으로 가정 하고 모든 데이터를 동일한 비중으로 연산하므로 훼손된 부분은 더욱 훼손된 모양으로 검출되는 문제점 있다. 본 논문에서 변형된 최소자승 법(MLSM: Modified Least Square Method)이란 훼손부분의 가까운점에 큰 비중을 둠으로 원래의 모양에 접근하는 형상(feature)의 타원을 검출하려는 것으로 훼손점 부근의 2점과 그외 중요한 l점을 강제로 만족하는 방법이다. 3점을 만족시키는 제한 조건을 주고 2개의 파라미터는 최소자승법으로 구하고, 나머지 3개는 제한 조건으로 구하여 타원 검출에 적용한 결과 실제 영상에서 타원의 검출 및 판별에 좋은 효과가 있었으며, 특히 인간의 치열의 곡선 모양을 결정하는테 좋은 효과가 있음을 보였다.

• 천문학회보
• /
• 제40권2호
• /
• pp.40.1-40.1
• /
• 2015

Off-axis reflective optical systems have attractive advantages relative to their on-axis or refractive counterparts, for example, zero chromatic aberration, no obstruction, and a wide field of view. For the efficient operation of off-axis reflective system, the surface accuracy of freeform mirrors should be higher than the order of wavelengths at which the reflective optical systems operate. Especially for applications in shorter wavelength regions, such as visible and ultraviolet, higher surface accuracy of freeform mirrors is required to minimize the light scattering. In this work, we propose the error compensation algorithm (ECA) for the correction of wavefront errors on freeform mirrors. The ECA converts a form error pattern into polynomial expression by fitting a least square method. The error pattern is measured by using an ultra-high accurate 3-D profilometer (UA3P, Panasonic Corp.). The measured data are fitted by two fitting models: Sag (Delta Z) data model and form (Z) data model. To evaluate fitting accuracy of these models, we compared the fitted error patterns with the measured error pattern.

• Wind and Structures
• /
• 제19권4호
• /
• pp.371-387
• /
• 2014

Probability plotting positions are popular and used as the basis for distribution fitting and for inspecting the quality of the fit because of its simplicity. The plotting positions that lead to excellent approximation to the mean of the order statistics should be used if the objective of the fitting is to estimate quantiles. Since the mean depends on the sample size and is not amenable for simple to use closed form solution, many plotting positions have been presented in the literature, including a new plotting position that is derived based on the weighted least-squares method. In this study, the accuracy of using the new plotting position to fit the Gumbel distribution for estimating quantiles is assessed. Also, plotting positions derived by fitting the mean of the order statistics for all ranks is proposed, and an approximation to the covariance of the order statistics for the Gumbel (and Weibull) variate is given. Relative bias and root-mean-square-error of the estimated quantiles by using the proposed plotting position are shown. The use of the proposed plotting position to estimate the quantiles of annual maximum wind speed is illustrated.

• 한국군사과학기술학회지
• /
• 제9권2호
• /
• pp.20-25
• /
• 2006

Low frequency towed line array with high array gain and beam resolution is a long range surveillance sensor for anti-submarine warfare. The beam characteristics is however deteriorated due to the distorted line array sensor caused by low towing speed, wind, current, and towing ship maneuvering. An adaptive beamforming method is utilized in this paper to enhance the distorted line array beam performance by estimating and compensating the nonlinear array shape. A polynomial curve fitting in the least square sense is used to estimate the array shape iteratively with the distributed heading sensors data along the array. Real time array shape estimation and nonlinear array beam calculation is applied to a very long towed line array sensor system and the beam performance is evaluated and compared to the linear beamformer for the simulation and sea trial data.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.557-571
• /
• 2020

The existing methods for detection of fire smoke in a video easily lead to misjudgment of cloud, fog and moving distractors, such as a moving person, a moving vehicle and other non-smoke moving objects. Therefore, an algorithm for detection of fire smoke in a video based on wavelet energy slope fitting is proposed in this paper. The change in wavelet energy of the moving target foreground is used as the basis, and a time window of 40 continuous frames is set to fit the wavelet energy slope of the suspected area in every 20 frames, thus establishing a wavelet-energy-based smoke judgment criterion. The experimental data show that the algorithm described in this paper not only can detect smoke more quickly and more accurately, but also can effectively avoid the distraction of cloud, fog and moving object and prevent false alarm.

• 대한기계학회논문집A
• /
• 제27권10호
• /
• pp.1712-1719
• /
• 2003

This paper concerns on application of active magnetic bearing(AMB) system to levitate the elevation axis of an electro-optical sight mounted on moving vehicles. In such a system, it is desirable to retain the elevation axis within the predetermined air-gap while the vehicle is moving. An optimal base acceleration feedforward control is proposed to reduce the base motion response. In the consideration of the uncertainty of the system model, a filtered-x least-mean-square(FXLMS) algorithm is used to estimate the frequency response function of the feedforward control which cancels base motions. The frequency response function is fitted to an optimal feedforward control. Experimental results demonstrate that the proposed control reduces the air-gap deviation to 27.7% that by feedback control alone.

• International Journal of Precision Engineering and Manufacturing
• /
• 제6권2호
• /
• pp.12-18
• /
• 2005

A geometric compensation of thin-walled molded parts in reverse engineering is presented. Researches in reverse engineering have focused on the fitting of points to curves and surfaces. However, the reconstructed model is not the geometric model because the molded parts have some dimensional errors in measurements and deformation during molding. Geometric information can give an improved accuracy in reverse engineering. Thus, measurement data must be compensated with geometric information to reconstruct the mathematical model. The functional and geometric concepts of the part can be derived from geometric information. LSM (Least square method) is adopted to determine the geometric information. Also, an example of geometric compensation is given to improve the accuracy of geometric model and to inspect the reconstructed model.

• Communications for Statistical Applications and Methods
• /
• 제30권3호
• /
• pp.273-289
• /
• 2023

In this paper, we develop a new time series model for predicting IPO (initial public offering) data with non-negative integer value. The proposed model is based on integer-valued autoregressive (INAR) model with a Poisson thinning operator. Just as the heterogeneous autoregressive (HAR) model with daily, weekly and monthly averages in a form of cascade, the integer-valued heterogeneous autoregressive (INHAR) model is considered to reflect efficiently the long memory. The parameters of the INHAR model are estimated using the conditional least squares estimate and Yule-Walker estimate. Through simulations, bias and standard error are calculated to compare the performance of the estimates. Effects of model fitting to the Korea's IPO are evaluated using performance measures such as mean square error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) etc. The results show that INHAR model provides better performance than traditional INAR model. The empirical analysis of the Korea's IPO indicates that our proposed model is efficient in forecasting monthly IPO volumes.

• Communications for Statistical Applications and Methods
• /
• 제25권6호
• /
• pp.673-685
• /
• 2018

Procrustes analysis is a useful technique useful to measure, compare shape differences and estimate a mean shape for objects; however it is based on a least squares criterion and is affected by some outliers. Therefore, we propose two generalized Procrustes analysis methods based on M-estimation and least median of squares estimation that are resistant to object outliers. In addition, two algorithms are given for practical implementation. A simulation study and some examples are used to examine and compared the performances of the algorithms with the least square method. Moreover since these resistant GPA methods are available for higher dimensions, we need some methods to visualize the objects and mean shape effectively. Also since we have concentrated on resistant fitting methods without considering shape distributions, we wish to shape analysis not be sensitive to particular model.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.840-843
• /
• 2016

원호는 산업 환경에서 객체의 검출 및 인식에 매우 유용한 특성이다. 본 논문에서는 새로운 원호 검색 방법을 제안한다. 원호 검출은 중점과 원호의 반지름, 두 개의 호 끝점이 필요하다. 제안하는 새로운 검출 방법은 호를 따라 지정한 세 점을 이용하여 가장 좋은 부분을 결정한다. 최소자승법을 적용하여 원호의 최적점과 중점 그리고 반지름을 얻는다. 남은 모서리 점들의 거리와 반지름은 원호의 두 끝점을 찾는데 이용된다.