• Journal of the Korean Statistical Society
• /
• 제11권1호
• /
• pp.12-24
• /
• 1982

Selection procedures are proposed for selecting the 'best' industrial process with the smallest fraction defective. For normally distributed industrial processes, this is equivalent to selecting in terms of coefficients of variation. For the case of known vairances, selection procedures by Bechhofer (1954), and Bechhofer and Turnball (1978) are appropriate. We treat this problem for the case of uknown variances with or without reference to a standard. The large sample solutions of design constants are tabulated and the performance of these approximate solutions are investigated.

• 공업화학
• /
• 제9권3호
• /
• pp.430-434
• /
• 1998

제조용 액체 크로마토그래피는 주로 생화학물질에서 유용성분을 분리하는 데 사용된다. 본 연구에서는 제조용 충전물($15{\mu}m$)이 채워진 역상 액체 크로마토그래피를 이용하여 sample size에 따른 흡착특성을 고찰하였다. 시료는 향미제인 5'-GMP이고 이동상은 $KH_2PO_4$ 수용액 20mM과 메탄올을 97:3 (vol.%)으로 혼합하여 사용하였다. 실험결과에 의하면 sample size가 증가해도 체류인자는 거의 일정하였지만 $1{\mu}g$ 이상에서는 peak의 모양이 비대칭성이 되었다. 또한 sample size가 증가함에 따라서 이론단수는 감소하였고 농도가 작은 경우 peak width가 크기 때문에 이론단수는 더 작았다. 본 실험조건에서 5'-GMP는 Freundlich 비선형흡착식에 비교적 잘 일치하였다.

• Structural Engineering and Mechanics
• /
• 제33권6호
• /
• pp.725-745
• /
• 2009

In this paper, probabilistic seismic performance assessment of a typical non-seismic RC frame building representative of a large inventory of existing buildings in developing countries is conducted. Nonlinear time-history analyses of the sample building are performed with 20 large-magnitude medium distance ground motions scaled to different levels of intensity represented by peak ground acceleration and 5% damped elastic spectral acceleration at the first mode period of the building. The hysteretic model used in the analyses accommodates stiffness degradation, ductility-based strength decay, hysteretic energy-based strength decay and pinching due to gap opening and closing. The maximum inter story drift ratios obtained from the time-history analyses are plotted against the ground motion intensities. A method is defined for obtaining the yielding and collapse capacity of the analyzed structure using these curves. The fragility curves for yielding and collapse damage levels are developed by statistically interpreting the results of the time-history analyses. Hazard-survival curves are generated by changing the horizontal axis of the fragility curves from ground motion intensities to their annual probability of exceedance using the log-log linear ground motion hazard model. The results express at a glance the probabilities of yielding and collapse against various levels of ground motion intensities.

• Communications for Statistical Applications and Methods
• /
• 제8권1호
• /
• pp.51-63
• /
• 2001

We are interested in the conditional independence in sparse $2\tims2\tims$K tables with very rare cell counts. The most popular test is Cochran-Mantel-Haenszel statistic when sample sizes are moderately large enough to guarantee the chi-square approximation. We will consider jackknifing the CMH test and also suggest an approximate normal distribution for the standardized jackknifed CMH statistic. The main focus of this paper is to improve the chi-squared approximation to the CMH test by using the asymptotic normality of the jackknifed CMH test when sample sizes are very sparse but K and N$\infty$. The performance of the proposed jackknifed test, in the sense of significance level control and power, will be compared with that of the CMH test through a Monte Carlo study.

• 무역학회지
• /
• 제44권3호
• /
• pp.227-252
• /
• 2019

This study explores the effects of exports on the innovation of Korean firms listed on two Korean stock markets, the Korean Stock Exchange and the Korean Securities Dealers Quotations, between 1999 and 2016. By matching exporting firms to non-exporting ones with propensity score matching, this study accounts for a problem from sample selection bias that may arise from differences in firm-characteristics between the two groups. From the study results, first, both export participation and export volume significantly increase subsequent innovation performance, as measured by the number of patent applications. This result seems to support the "learning by exporting" hypothesis for Korean listed firms. Second, both export participation and export volume narrow innovation scope, proxied as the number of unique International Patent Classification (IPC) codes of the patent applied, the degree to which patents are concentrated in a particular class, and the degree of proximity in the patents. The findings of innovation scope suggest a possible explanation that the learning effect appears in familiar technology fields that firms have previously held, rather than in unfamiliar ones. Third, these results are robust using alternative proxies in the innovation scope, Tobit regressions to consider the non-trivial portion of sample firms with patent applications equal to zeros, and generalized method of moments (GMM) to control for the persistence of innovation measures hearing over years. Finally, the two main results are more pronounced in large firms than in small and medium-sized ones. As for Chaebol firms, however, these results do not appear.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2006년도 PROCEEDINGS OF JOINT CONFERENCEOF KDISS AND KDAS
• /
• pp.163-169
• /
• 2006

This paper deals with the comparison of parameter estimation methods in a 3-parameter Kappa distribution which is sometimes used in flood frequency analysis. The method of moment estimation(MME), L-moment estimation(L-ME), and maximum likelihood estimation(MLE) are applied to estimate three parameters. The performance of these methods are compared by Monte-carlo simulations. Especially for computing MME and L-ME, ike dimensional nonlinear equations are simplied to one dimensional equation which is calculated by the Newton-Raphson iteration under constraint. Based on the criterion of the mean squared error, the L-ME is recommended to use for small sample size $(n\leq100)$ while MLE is good for large sample size.

• 로봇학회논문지
• /
• 제4권3호
• /
• pp.169-176
• /
• 2009

Low-cost sensors have been widely used for mobile robot navigation in recent years. However, navigation performance based on low-cost sensors is not good enough to be practically used. Among many navigation techniques, building of an accurate map is a fundamental task for service robots, and mapping with low-cost IR sensors was investigated in this research. The robot's orientation uncertainty was considered for mapping by modifying the Bayesian update formula. Then, the data association scheme was investigated to improve the quality of a built map when the robot's pose uncertainty was large. Six low-cost IR sensors mounted on the robot could not give rich data enough to align the range data by the scan matching method, so a new sample-based method was proposed for data association. The real experiments indicated that the mapping method proposed in this research was able to generate a useful map for navigation.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.285-294
• /
• 2005

This paper deals with the comparison of parameter estimation methods in a 3-parameter Kappa distribution which is sometimes used in flood frequency analysis. Method of moment estimation(MME), L-moment estimation(L-ME), and maximum likelihood estimation(MLE) are applied to estimate three parameters. The performance of these methods are compared by Monte-carlo simulations. Especially for computing MME and L-ME, three dimensional nonlinear equations are simplified to one dimensional equation which is calculated by the Newton-Raphson iteration under constraint. Based on the criterion of the mean squared error, L-ME (or MME) is recommended to use for small sample size( n$\le$100) while MLE is good for large sample size.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.454-462
• /
• 2014

Retention of possible churning customer is one of the most important issues in customer relationship management, so companies try to predict churn customers using their large-scale high-dimensional data. This study focuses on dealing with large data sets by reducing the dimensionality. By using six different dimension reduction methods-Principal Component Analysis (PCA), factor analysis (FA), locally linear embedding (LLE), local tangent space alignment (LTSA), locally preserving projections (LPP), and deep auto-encoder-our experiments apply each dimension reduction method to the training data, build a classification model using the mapped data and then measure the performance using hit rate to compare the dimension reduction methods. In the result, PCA shows good performance despite its simplicity, and the deep auto-encoder gives the best overall performance. These results can be explained by the characteristics of the churn prediction data that is highly correlated and overlapped over the classes. We also proposed a simple out-of-sample extension method for the nonlinear dimension reduction methods, LLE and LTSA, utilizing the characteristic of the data.

• 한국컴퓨터정보학회논문지
• /
• 제27권7호
• /
• pp.1-7
• /
• 2022

최근 대용량 데이터를 프로그램 자체에서 생성시키면서 구동되는 빅데이터 프로그램, 머신 러닝 프로그램 같은 응용 프로그램의 사용이 일상화됨에 따라 기존의 메인 메모리만으로는 메모리가 부족하여 프로그램의 빠른 실행이 어려운 경우가 발생하고 있다. 특히, 코로나 변이 바이러스 발생으로 염기서열 전체의 유전 변이 여부를 분석해야 하는 상황에는 더욱 빠르게 결과를 도출해야 하는 필요성이 대두되었다. 대용량 데이터를 병렬실행으로 빠른 결과를 필요로 하는 전장유전체(WGS; Whole Genome Sequencing) 분석 방법에 기존 SSD에서 대용량 데이터를 처리하는 것이 아닌 자체 개발한 메모리풀 MOCA host adapter가 장착된 컴퓨팅 시스템에 적용하여 성능을 측정한 결과 기존 SSD 시스템에 비해 16%의 성능 향상이 있었다. 그리고, 그 외의 다양한 벤치마크 시험에서도 워크플로우의 task별 SortSampleBam, ApplyBQSR, GatherBamFiles등 메모리풀 MOCA host adapter가 장착된 컴퓨팅 시스템에서도 SSD를 사용한 경우보다 IO 성능이 각각 92.8%, 80.6%, 32.8% 실행시간 단축을 보였다. 전장유전체파이프라인 분석같이 대용량 데이터 분석시 본 연구에서 개발한 메모리풀 MOCA host adapter가 장착된 컴퓨팅 시스템에서 분석할 경우 런타임(run time)시 발생하는 측정 지연을 줄일 수 있을 것으로 판단된다.