• Resources Recycling
• /
• v.27 no.1
• /
• pp.84-91
• /
• 2018

In this study, a novel soft information based most probable classification scheme is proposed for sorting recyclable metal alloys with laser induced breakdown spectroscopy (LIBS). Regression analysis with LIBS captured spectrums for estimating concentrations of common elements can be efficient for classifying unknown arbitrary metal alloys, even when that particular alloy is not included for training. Therefore, partial least square regression (PLSR) is employed in the proposed scheme, where spectrums of the certified reference materials (CRMs) are used for training. With the PLSR model, the concentrations of the test spectrum are estimated independently and are compared to those of CRMs for finding out the most probable class. Then, joint soft information can be obtained by assuming multi-variate normal (MVN) distribution, which enables to account the probability measure or a prior information and improves classification performance. For evaluating the proposed schemes, MVN soft information is evaluated based on PLSR of LIBS captured spectrums of 9 metal CRMs, and tested for classifying unknown metal alloys. Furthermore, the likelihood is evaluated with the radar chart to effectively visualize and search the most probable class among the candidates. By the leave-one-out cross validation tests, the proposed scheme is not only showing improved classification accuracies but also helpful for adaptive post-processing to correct the mis-classifications.

• The Korean Journal of Applied Statistics
• /
• v.18 no.1
• /
• pp.183-196
• /
• 2005

In this paper we studied the saddlepoint approximations to the distribution of non-homogeneous quadratic forms in normal variables. The results are the extension of Kuonen's which provide the same approximations to homogeneous quadratic forms. The CGF of interested statistics and related properties are derived for applications of saddlepoint techniques. Simulation results are also provided to show the accuracy of saddlepoint approximations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.325-327
• /
• 2001

본 논문은 온라인 문자 인식을 연속 밀도 HMM의 구조의 최적화 문제를 다룬다. 최적이란 최소한의 모델 파라미터를 사용하여 최소한의 오류를 허용하는 것이라고 정의할 수 있다. 본 연구에서는 HMM 구조의 최적화를 위해 Bayesian 모델 선택 방법론을 사용한다. 먼저 잘 알려진 BIC(Bayesian Information Criterion)을 적용해보고, 그것을 HMM의 복잡한 구조에 적합하도록 본 논문에서 제안한 HBIC(HMM-Oriented BIC)와 비교해본다. BIC는 모델의 사전 확률 분포를 추정하지 않고 다변량 정규분포라고 가정하는데 비해 HBIC는 모델의 각 파라미터로부터 사전 확률을 추정한 후 그것들을 사용함으로써 더 좋은 결과를 얻도록 한다. 실험 결과 BIC와 HBIC 둘 다 기존 방법보다 모델의 파라미터 수를 현저히 감소시킴을 확인했고, HBIC가 BIC에 비해 더 적은 수의 파라미터를 사용해도 비슷한 인식률을 얻을 수 있었다.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.449-461
• /
• 2009

Higher sigma quality level is generally perceived by customers as improved performance by assigning a correspondingly higher satisfaction score. The process capability indices and the sigma level $Z_{st}$ ave been widely used in six sigma industries to assess process performance. Most evaluations on process capability indices focus on statistical estimation under normal process which may result in unreliable assessments of process performance. In this paper, we consider statistical estimation for bivariate VPCI(Vector-valued Process Capability Index) $C_{pkl}=(C_{pklx},\;C_{pklx})$ under Marshall and Olkin (1967)'s bivariate exponential process. First, we derive some limiting distribution for statistical inference of bivariate VPCI $C_{pkl}$. And we propose two asymptotic normal confidence regions for bivariate VPCI $C_{pkl}$. The proposed method may be very useful under bivariate exponential process. A numerical result based on our proposed method shows to be more reliable.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.797-810
• /
• 2017

The Korean peninsula is exposed to typhoons every year. Typhoons cause huge socioeconomic damage because tropical cyclones tend to occur with strong winds and heavy precipitation. In order to understand the complex dependence structure between strong winds and heavy precipitation, the copula links a set of univariate distributions to a multivariate distribution and has been actively studied in the field of hydrology. In this study, we carried out analysis using data of wind speed and precipitation collected from the weather stations in Busan and Jeju. Log-Normal, Gamma, and Weibull distributions were considered to explain marginal distributions of the copula. Kolmogorov-Smirnov, Cramer-von-Mises, and Anderson-Darling test statistics were employed for testing the goodness-of-fit of marginal distribution. Observed pseudo data were calculated through inverse transformation method for establishing the copula. Elliptical, archimedean, and extreme copula were considered to explain the dependence structure between strong winds and heavy precipitation. In selecting the best copula, we employed the Cramer-von-Mises test and cross-validation. In Busan, precipitation according to average wind speed followed t copula and precipitation just as maximum wind speed adopted Clayton copula. In Jeju, precipitation according to maximum wind speed complied Normal copula and average wind speed as stated in precipitation followed Frank copula and maximum wind speed according to precipitation observed Husler-Reiss copula.

• Journal of KIISE:Software and Applications
• /
• v.28 no.11
• /
• pp.833-841
• /
• 2001

Abstract In this work, we analyze the Levy mutation operations based on the Levy probability distribution in the evolutionary programming via the mean square displacement and the distinctness. The Levy probability distribution is characterized by an infinite second moment and has been widely studied in conjunction with the fractals. The Levy mutation operators not only generate small varied offspring, but are more likely to generate large varied offspring than the conventional mutation operators. Based on this fact, we prove mathematically, via the mean square displacement and the distinctness, that the Levy mutation operations can explore and exploit a search space more effectively. As a result, one can get better performance with the Levy mutation than the conventional Gaussian mutation for the multi-valued functional optimization problems.

• Journal of the Ergonomics Society of Korea
• /
• v.12 no.2
• /
• pp.63-83
• /
• 1993

The primary objective of the research is to develop a mathematical method to incorporate the variability of anthropometric body dimensions and joint strengths of individuals in a biomechanical analysis. A multivariate normal simulation model estimated anthropometric body dimensions and joint strengths of the random link-person, based on the assumptions that the vari- ables of body dimensions and joint strengths are correlated and follow normal distributions. Statistical comparative analysis demonstrated that the random link-person represented a more realistic human-like form in an anthropometric sense than the proportional link-person whose body dimensions were estimated proportionally. Estimated joint strengths for the random link-person, however, did not match the measured joint strengths as closely as the estimated body dimensions. The random link-person will allow biomechanical analysis of manual materials handling tasks to be individualized with respect to the anthropometry and a static strength.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.1-9
• /
• 2010

This paper suggests a mixed-effects model for analyzing split-plot data when there is a repeated measures factor that affects on the response variable. Covariance structures are discussed among the observations because of the assumption of a repeated measures factor as one of explanatory variables. As a plausible covariance structure, compound symmetric covariance structure is assumed for analyzing data. The restricted maximum likelihood (REML)method is used for estimating fixed effects in the model.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.633-644
• /
• 1998

혼합설계의 교호작용에 대한 F 검정이 유효하려면 다표본 구형성(multisample sphericity) 가정과 다변량 정규분포 가정이 만족되어야 한다. F 검정을 실시하기 위한 가정들이 위반된 조건하에서 혼합설계의 교호작용에 대한 검정법들의 1종오류가 비교되었다. 비교된 검정법들은 (1) F 검정(F), (2) 절사평균을 사용한 F 검정($F_T$)(3)$\varepsilon$-수정 F 검정($\varepsilon)$(4) 절사평균을 사용한 $\varepsilon$-수정 F 검정$(\varepsilon_T$) (5) CIGA검정(CIGA), (6) 절사평균을 사용한 CIGA검정($CIGA_T$)이었다. 결과는 CIGA와 $CIGA_T$는 1종오류를 대체로 잘 관리하나, F검정들과 ($\varepsilon$)검정들은 일부 조건에서 아주 작은 1종오류나 아주 큰 1종오류를 갖는 것으로 나타났다.

• Korean Journal of Remote Sensing
• /
• v.15 no.3
• /
• pp.195-208
• /
• 1999

In the classification of satellite images, the representative of training of classes is very important factor that affects the classification accuracy. Hence, in order to improve the classification accuracy, it is required to optimize pre-classification stage which determines classification parameters rather than to develop classifiers alone. In this study, the normality of training are calculated at the preclassification stage using SPOT XS and LANDSAT TM. A correlation coefficient of multivariate Q-Q plot with 5% significance level and a variance of initial training are considered as an object function of genetic algorithm in the training normalization process. As a result of normalization of training using the genetic algorithm, it was proved that, for the study area, the mean and variance of each class shifted to the population, and the result showed the possibility of prediction of the distribution of each class.