• Title/Summary/Keyword: Statistical Factor

Search Result 3,815, Processing Time 0.03 seconds

The Use of Local Outlier Factor(LOF) for Improving Performance of Independent Component Analysis(ICA) based Statistical Process Control(SPC) (LOF를 이용한 ICA 기반 통계적 공정관리의 성능 개선 방법론)

  • Lee, Jae-Shin;Kang, Bok-Young;Kang, Suk-Ho
    • Journal of the Korean Operations Research and Management Science Society
    • /
    • v.36 no.1
    • /
    • pp.39-55
    • /
    • 2011
  • Process monitoring has been emphasized for the monitoring of complex system such as chemical processing industries to achieve the efficiency enhancement, quality management, safety improvement. Recently, ICA (Independent Component Analysis) based MSPC (Multivariate Statistical Process Control) was widely used in process monitoring approaches. Moreover, DICA (Dynamic ICA) has been introduced to consider the system dynamics. However, the existing approaches show the limitation that their performances are strongly dependent on the statistical distributions of control variables. To improve the limitation, we propose a novel approach for process monitoring by integrating DICA and LOF (Local Outlier Factor). In this paper, we aim to improve the fault detection rate with the proposed method. LOF detects local outliers by using density of surrounding space so that its performance is regardless of data distribution. Therefore, the proposed method not only can consider the system dynamics but can also assure robust performance regardless of the statistical distributions of control variables. Comparison experiments were conducted on the widely used benchmark dataset, Tennessee Eastman process (TE process), and showed the improved performance than existing approaches.

An Analysis on the Variables' Significance to 'Quality of Life' Based on the "2011 Seoul Survey" ("2011서울서베이"를 이용한 '삶의 질' 관련 변수의 유의성 분석)

  • Kim, Dong-Yoon
    • Journal of The Korean Digital Architecture Interior Association
    • /
    • v.12 no.3
    • /
    • pp.39-47
    • /
    • 2012
  • General concern over 'Quality of Life(QOL)' has caused many researches, which compare nations' or cities' QOL by the normative criteria proposed by themselves. The fact that these are characterized by subjectiveness makes this study have a purpose of trying to enhance the intersubjectiveness by means of quantitive analysis to find the factors on the QOL. This study uses statistical methods such as multiple regression and factor analysis based on the secondary data from the "2011 Seoul Survey". The survey includes many items, for example happiness index and satisfaction for work, amenity, etc.. And the analysis tells three findings as follows; Firstly, five subcategories of happiness have relative importance in the order of (1)financial condition, (2)health, (3)social activities, (4)community relationship and (5)family life. These generally constitute the first factor extracted by factor analysis and named 'abundance-family-intimacy factor.' Secondly, the 'abundance-family-intimacy factor' and the 'information-danger factor' among five factors(the others are 'learning-giving factor', 'local patriotism-hope for rise factor' and 'amenity-comfort factor') have statistically significant effect to QOL. Thirdly, the first factor has positive effect, but the second has negative to QOL. Note is needed to the fact that the items on SNS and internet belong to second factor and to the result that these make QOL deteriorate. These results should be considered as having limited meaning of statistical aspect. But accumulation of following studies by quantitive approach is anticipate to make more practical and general meaning.

Unbiasedness or Statistical Efficiency: Comparison between One-stage Tobit of MLE and Two-step Tobit of OLS

  • Park, Sun-Young
    • International Journal of Human Ecology
    • /
    • v.4 no.2
    • /
    • pp.77-87
    • /
    • 2003
  • This paper tried to construct statistical and econometric models on the basis of economic theory in order to discuss the issue of statistical efficiency and unbiasedness including the sample selection bias correcting problem. Comparative analytical tool were one stage Tobit of Maximum Likelihood estimation and Heckman's two-step Tobit of Ordinary Least Squares. The results showed that the adequacy of model for the analysis on demand and choice, we believe that there is no big difference in explanatory variables between the first selection model and the second linear probability model. Since the Lambda, the self- selectivity correction factor, in the Type II Tobit is not statistically significant, there is no self-selectivity in the Type II Tobit model, indicating that Type I Tobit model would give us better explanation in the demand for and choice which is less complicated statistical method rather than type II model.

Investigation of dynamic P-Δ effect on ductility factor

  • Han, Sang Whan;Kwon, Oh-Sung;Lee, Li-Hyung
    • Structural Engineering and Mechanics
    • /
    • v.12 no.3
    • /
    • pp.249-266
    • /
    • 2001
  • Current seismic design provisions allow structures to deform into inelastic range during design level earthquakes since the chance to meet such event is quite rare. For this purpose, design base shear is defined in current seismic design provisions as the value of elastic seismic shear force divided by strength reduction factor, R (${\geq}1$). Strength reduction factor generally consists of four different factors, which can account for ductility capacity, overstrength, damping, and redundancy inherent in structures respectively. In this study, R factor is assumed to account for only the ductility rather than overstrength, damping, and redundancy. The R factor considering ductility is called "ductility factor" ($R_{\mu}$). This study proposes ductility factor with correction factor, C, which can account for dynamic P-${\Delta}$ effect. Correction factor, C is established as the functional form since it requires computational efforts and time for calculating this factor. From the statistical study using the results of nonlinear dynamic analysis for 40 earthquake ground motions (EQGM) it is shown that the dependence of C factor on structural period is weak, whereas C factor is strongly dependant on the change of ductility ratio and stability coefficient. To propose the functional form of C factor statistical study is carried out using 79,920 nonlinear dynamic analysis results for different combination of parameters and 40 EQGM.

Resistant Principal Factor Analysis

  • Park, Youg-Seok;Byun, Ho-Seon
    • Journal of the Korean Statistical Society
    • /
    • v.25 no.1
    • /
    • pp.67-80
    • /
    • 1996
  • Factor analysis is a multivariate technique for describing the in-terrelationship among many variables in terms of a few underlying but unobservable random variables called factors. There are various approaches for this factor analysis. In particular, principal factor analysis is one of the most popular methods. This follows the mathematical algorithm of the principal component analysis based on the singular value decomposition. But it is known that the singular value decomposition is not resistant, i.e., it is very sensitive to small changes in the input data. In this article, using the resistant singular value decomposition of Choi and Huh (1994), we derive a resistant principal factor analysis relatively little influenced by notable observations.

  • PDF

Intrinsic Priors for Testing Two Normal Means with the Default Bayes Factors

  • Jongsig Bae;Kim, Hyunsoo;Kim, Seong W.
    • Journal of the Korean Statistical Society
    • /
    • v.29 no.4
    • /
    • pp.443-454
    • /
    • 2000
  • In Bayesian model selection or testing problems of different dimensions, the conventional Bayes factors with improper noninformative priors are not well defined. The intrinsic Bayes factor and the fractional Bayes factor are used to overcome such problems by using a data-splitting idea and fraction, respectively. This article addresses a Bayesian testing for the comparison of two normal means with unknown variance. We derive proper intrinsic priors, whose Bayes factors are asymptotically equivalent to the corresponding fractional Bayes factor. We demonstrate our results with two examples.

  • PDF

Volatility Analysis for Multivariate Time Series via Dimension Reduction (차원축소를 통한 다변량 시계열의 변동성 분석 및 응용)

  • Song, Eu-Gine;Choi, Moon-Sun;Hwang, S.Y.
    • Communications for Statistical Applications and Methods
    • /
    • v.15 no.6
    • /
    • pp.825-835
    • /
    • 2008
  • Multivariate GARCH(MGARCH) has been useful in financial studies and econometrics for modeling volatilities and correlations between components of multivariate time series. An obvious drawback lies in that the number of parameters increases rapidly with the number of variables involved. This thesis tries to resolve the problem by using dimension reduction technique. We briefly review both factor models for dimension reduction and the MGARCH models including EWMA (Exponentially weighted moving-average model), DVEC(Diagonal VEC model), BEKK and CCC(Constant conditional correlation model). We create meaningful portfolios obtained after reducing dimension through statistical factor models and fundamental factor models and in turn these portfolios are applied to MGARCH. In addition, we compare portfolios by assessing MSE, MAD(Mean absolute deviation) and VaR(Value at Risk). Various financial time series are analyzed for illustration.

Application of Piezoelectric Smart Structures for Statistical Energy Analysis (압전 지능 구조물을 이용한 통계적 에너지 해석 기법)

  • 김재환;김정하;김재도
    • Journal of KSNVE
    • /
    • v.11 no.2
    • /
    • pp.257-264
    • /
    • 2001
  • In this research, piezoelectric smart structures are applied for SEA(Statistical Energy Analysis), which is well known approach for high frequency analysis. A new input power measurement based on piezoelectric electrical power measurement is proposed and compared with the conventional method in SEA. As an example, a simple aluminum beam on which piezoelectric actuator is attached is considered. By measuring the electrical impedance and electrical current of the piezoelectric actuator, the electrical power given on the actuator is found and this is In turn converted into the mechanical energy. From the measured value of the stored energy of the beam, the Internal loss factor is calculated and this value shows a good agreement with that given by the conventional method as well as the theoretical value. To compare the coupling loss factor, L-shape beam system which consists of a aluminum beam subsystem and a steel beam subsystem coupled by three pin is taken as second example. The input power and stored energy of each subsystem are found by the proposed approach. The coupling loss factor found by the electrical input power obtained from the piezoelectric actuator exhibits similar trend to the value found by the conventional method as well as the theoretical value. In conclusion, the use of SEA for high frequency application of piezoelectric smart structures is Possible. Especially, the input power that is essential for SEA can be found accurately by measuring the electrical input power of the piezoelectric actuator.

  • PDF

Development of Accelerated Life Test Method for UHF RFID Tags for Medicine Supply Management (의약품 유통 관리용으로 사용되는 UHF 대역 RFID Tag의 가속수명시험법 개발)

  • Yang, Il Young;Yu, Sang Woo;Park, Jung Won;Joe, Won-Seo
    • Journal of Applied Reliability
    • /
    • v.14 no.2
    • /
    • pp.93-96
    • /
    • 2014
  • RFID (Radio Frequency IDentification) system is recognition technology which can maintain various object's information. Reliability of RFID tags is the most important factor in RFID system. In this paper, we proposed ALT (Accelerated Life Test) method for UHF RFID tags. Temperature and humidity were adopted as stress factors and the accelerated life tests were conducted in three different conditions. We performed failure analysis for identifying failure mechanism and statistical analysis of test data. In the statistical analysis, we employed Inverse Power law for relationship between tag's life and stress. Through the statistical analysis, we proposed acceleration factor for several levels of temperature-humidity. The reliability qualification test plans were also designed for the tag's target reliability.