• 응용통계연구
• /
• 제34권4호
• /
• pp.537-556
• /
• 2021

통계적 공정관리절차의 특성은 해석적 해를 얻기가 어려운 경우가 많이 있으나 Markov연쇄를 적용하면 가능한 경우가 많이 있다. 이 논문에서는 공정 통계량이 Markov특성을 따르는 경우, Markov연쇄를 생성하는 방법과 이를 이용한 공정관리 절차의 특성을 도출하는 방법에 대해 설명하고 있다. 관리도의 통계적 설계, 경제적 설계 및 변량표본 추출비 설계 등의 특성 규명을 위한 Markov연쇄의 적용에 대한 기존의 알려진 방법을 복습하고 또한 새로운 공정관리 분야인 재조정 관리도에의 적용방법에 대한 연구결과도 보여주고 있다. 공정관리의 특성연구에서 해석적 해가 가능한 경우에도 이 과정이 복잡하여 Markov연쇄를 병행 사용하면 특성 규명이 명확해지며, 모의실험보다는 짧은 시간에 더 정밀한 결과를 얻을 수 있어 널리 이용되고 있다.

• 대기
• /
• 제31권1호
• /
• pp.29-43
• /
• 2021

In this study, two-step statistical approach including Principal Component Analysis (PCA) and Multiple Linear Regression (MLR) was employed, and main meteorological factors explaining the high-PM2.5 episodes were identified in two regions: Seoul and Busan. We first performed PCA to isolate the Principal Component (PC) that is linear combination of the meteorological variables observed at two levels: surface and 850 hPa level. The employed variables at surface are: temperature (T2m), wind speed, sea level pressure, south-north and west-east wind component and those at 850 hPa upper level variables are: south-north (v850) and west-east (u850) wind component and vertical stability. Secondly we carried out MLR analysis and verified the relationships between PM2.5 daily mean concentration and meteorological PCs. Our two-step statistical approach revealed that in Seoul, dominant factors for influencing the high PM2.5 days are mainly composed of upper wind characteristics in winter including positive u850 and negative v850, indicating that continental (or Siberian) anticyclone had a strong influence. In Busan, however, the dominant factors in explanaining in high PM2.5 concentrations were associated with high T2m and negative u850 in summer. This is suggesting that marine anticyclone had a considerable effect on Busan's high PM2.5 with high temperature which is relevant to the vigorous photochemical secondary generation. Our results of both differences and similarities between two regions derived from only statistical approaches imply the high-PM2.5 episodes in Korea show their own unique characteristics and seasonality which are mostly explainable by two layer (surface and upper) mesoscale meteorological variables.

• 한국터널지하공간학회 논문집
• /
• 제12권6호
• /
• pp.463-473
• /
• 2010

통계 관리도 기법을 활용한 터널 굴착면 전방 단층대 예측 기법을 제시하고 적용성을 검토하였다. 5개의 RMR 변수와 기초 RMR에 대한 $x-R_s$ 관리도를 작성하여 단층대로 접근함에 따른 각 변수의 변화 분석을 통해 이상 구간을 통계적인 기준에 의해 판정하였으며, 이러한 이상 구간을 단층대 구간으로 간주하였다. 관리도 평가 기법을 터널 시공현장에 적용한 결과, 선진수평시추 및 막장 관찰을 통해 확인된 3 개소의 단층대 구간은 관리도 판정에 의해 단층대가 출현하는 시점보다 각각 1~3 굴착면 이전에 인지되었으며, 거리로 환산하면 2.2 m, 5.0 m, 6.0 m 이전에 해당된다.

• 한국음향학회지
• /
• 제27권7호
• /
• pp.372-378
• /
• 2008

음성 검출기 (VAD, Voice Activity Detector)는 이동 통신이나 음성신호처리 등에 매우 중요한 기법으로 사용된다. 일반적인 음성 검출방식은 이산 푸리에 변환 (DFT, Discrete Fourier Transform)영역에서 통계적인 모델을 기반으로 하여 우도비검정 (LRT, Likelihood Ratio Test)을 하게 된다. 그리고 이 값을 임계값과 비교하며 음성인지 아닌지 판단하게 된다. 본 논문에서는 신호 준공간 (Signal Subspace)에 기반한 새로운 통계적 음성 검출 기법을 제안하다. 확률적인 주성분 분석 (PPCA, Probabilistic Principal Component Analysis)은 신호 준공간 방법에서 잡음신호에 대한 확률적인 모델을 얻기 위해 사용된다. 제안된 기법은 신호 준공간 영역에서 우도비검정에 기반을 두는 결정규칙을 적용하였다. 음성 검출 실험 결과는 신호 준공간 모델에 근거한 음성 검출기 기법이 주파수 영역에 기반한 가우시안 (Gaussian) 음성 검출기 보다 향상된 검출 결과를 보여준다.

• 터널과지하공간
• /
• 제12권1호
• /
• pp.19-30
• /
• 2002

절리 방향은 절리 크기 및 밀집도와 더불어 암반 사면 및 터널과 같은 암반구조물의 안정성에 영향을 미치는 중요한 기하학적 속성이다. 이와 같은 절리 기하학적 속성들에 대한 통계 모델링은 암반공학적 문제에 대한 확률론적 접근법을 제공할 수 있다. 암반 공학적 문제의 확률론적 모델링의 결과는 어떠한 통계 모델을 선택하느냐에 따라 많은 영향을 받는다. 따라서 , 절리 방향성 자료에 대한 대표적인 통계 모델을 정의하고 각 모델에 대한 분석적 검증과 자료의 통계적 특성에 기초한 모델링 과정의 정립은 매우 중요하다. 이에 본 연구에서는 회전대칭성 모델인 Fisher 분포와 회전 비대칭성 모델인 이변량 정규분포 모델에 대한 통계량 추정 및 검증에 대한 이론적 방법론에 대해 검토하고 , 암반 절리계 모사 및 위험도 분석에 유용하게 사용할 수 있는 인공자료 발생기 알고리즘을 제안하였다.

• 대한인간공학회지
• /
• 제29권4호
• /
• pp.631-637
• /
• 2010

The aim of affective engineering is to develop a new product by translating customer affections into design factors. Affective data have so far been analyzed using a multivariate statistical analysis, but the affective data do not always have linear features assumed under normal distribution. Rough sets model is an effective method for knowledge discovery under uncertainty, imprecision and fuzziness. Rough sets model is to deal with any type of data regardless of their linearity characteristics. Therefore, this study utilizes rough sets model to extract affective knowledge from affective data. Four types of scent alternatives and four types of sounds were designed and the experiment was performed to look into affective differences in subject's preference on air conditioner. Finally, the purpose of this study also is to extract knowledge from affective data using rough sets model and to figure out the relationships between rough sets based affective engineering method and statistical one. The result of a case study shows that the proposed approach can effectively extract affective knowledge from affective data and is able to discover the relationships between customer affections and design factors. This study also shows similar results between rough sets model and statistical method, but it can be made more valuable by comparing fuzzy theory, neural network and multivariate statistical methods.

• 대기
• /
• 제24권2호
• /
• pp.245-251
• /
• 2014

Statistical trajectory analysis has been widely used to identify potential source regions for chemically and radiatively important chemical species in the atmosphere. The most widely used method is a statistical source-receptor model developed by Stohl (1996), of which the underlying principle is that elevated concentrations at an observation site are proportionally related to both the average concentrations on a specific grid cell where the observed air mass has been passing over and the residence time staying over that grid cell. Thus, the method can compute a residence-time-weighted mean concentration for each grid cell by superimposing the back trajectory domain on the grid matrix. The concentration on a grid cell could be used as a proxy for potential source strength of corresponding species. This technical note describes the statistical trajectory approach and introduces its application to estimate potential source regions of $CO_2$ enhancements observed at Korean Global Atmosphere Watch Observatory in Anmyeon-do. Back trajectories are calculated using HYSPLIT 4 model based on wind fields provided by NCEP GDAS. The identified $CO_2$ potential source regions responsible for the pollution events observed at Anmyeon-do in 2010 were mainly Beijing area and the Northern China where Haerbin, Shenyang and Changchun mega cities are located. This is consistent with bottom-up emission information. In spite of inherent uncertainties of this method in estimating sharp spatial gradients within the vicinity of the emission hot spots, this study suggests that the statistical trajectory analysis can be a useful tool for identifying anthropogenic potential source regions for major GHGs.

• 한국디지털정책학회:학술대회논문집
• /
• 한국디지털정책학회 2004년도 International Conference on Digital Policy & Management
• /
• pp.39-53
• /
• 2004

Data production systems are generally very large, distributed and complex systems used for creating advanced (mainly statistical) reports. Typically, data is gathered periodically and then subsequently aggregated and separated during numerous production steps. These production steps are arranged in a specific sequence (workflow or production chain), and can be located worldwide. Today, a need for improving and automating methods of supervision for data production systems has been recognized. Supervision in this context entails planning, monitoring and controlling data production. Two significant approaches are introduced here for improving this supervision. The first is a 'closely-coupledd' approach (meaning direct communication between production jobs and supervisory tool, informing the supervisory tod immediately about delays in production) - based upon traditional production planning methods typically used for manufacturing (goods) and adopted for working with data production. The second is a 'loosely-coupled' approach (meaning no direct communication between supervisory tool and production jobs is used) - having its origins in proven traditional project management. The supervisory tool just enquires continuously the progress of production. In both cases, dates, costs, resources, and system health information is made available to management. production operators and administrators to support a timely and smooth production of periodic data. Both approaches are theoretically described and compared. The main finding is that, both are useful, but in different cases. The main advantages of the closely coupled approach are the large production optimisation potential and a production overview in form of a job execution plan, whereas the loosely coupled method mainly supports unhindered job execution and offers a sophisticated production overview in form of a milestone schedule. Ideas for further research include investigation of other potential approaches and theoretical and practical comparison.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1245-1245
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145-154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1152-1152
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145 154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.