• 제목/요약/키워드: Hotelling's $T^2$

검색결과 30건 처리시간 0.021초

Hotelling의 T-square 통계량을 이용한 강우유발 사면붕괴 예측 (Prediction of Rainfall-Induced Slope Failure Using Hotelling's T-Square Statistic)

  • 김슬비;나종화;서용석
    • 지질공학
    • /
    • 제25권3호
    • /
    • pp.331-337
    • /
    • 2015
  • 본 연구에서는 화강암 풍화토와 편마암 풍화토를 대상으로 모형시험 수행 중 획득한 간극수압, 함수비 데이터를 대상으로 Hotelling의 T2 분석을 실시하여 사면의 이상거동을 감지할 수 있는 기법을 개발하였다. 각 시험에서는 간극수압 3개와 함수비 3개가 동시에 측정되며, 이들의 상관관계를 이용하여 신뢰구간 95.0%와 90.0%를 기준으로 T2 통계량을 계산하였다. 분석결과에 의하면 모형사면 내의 국부적인 붕괴는 센서 위치에 따라 감지하지 못하는 경우가 있으며, 사면 전체붕괴의 경우 수백 초에서 수천 초 전에 T2 통계량이 신뢰구간 90%를 초과하여 이상거동을 감지할 수 있었다. Hotelling의 T2 분석은 동일 사면 내 다양한 측정치 간의 상관성을 분석할 수 있어 유일한 관리기준치를 설정할 수 있으며, 신뢰도 수준에 따라 단계적인 예경보 기준설정이 가능하다.

기계학습을 활용한 IoT 플랫폼의 이상감지 시스템 (Anomaly Detection System of IoT Platform using Machine Learning)

  • 임선열;최효근;이규열;이태훈;유헌창
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2018년도 추계학술발표대회
    • /
    • pp.1001-1004
    • /
    • 2018
  • 많은 양의 데이터가 수집되는 산업분야에서의 IoT 플렛폼 활용도가 높아지면서 IoT플랫폼의 성능과 이상 감지가 중요한 요소가 되고 있다. 본 논문에서는 IoT 플랫폼의 데이터 수집 성능을 저해하지 않으면서 산업분야에 활용되는 디바이스의 이상을 감지하는 시스템을 제안한다. 제안한 시스템은 Soft Real-time 서비스를 제공하기 위해 데이터 전송주기를 고려한 Micro Batch를 활용했으며, 실험에는 산업분야의 이상 상황에 대한 자료수집이 사전에 이루어지기 어려운 상황을 고려해 Hotelling's $T^2$를 활용한 분석모델을 적용하였고 Hotelling's $T^2$는 이상징후를 사전에 감지하였다.

호텔링 T2의 이상신호 원인 식별 (Identification of the out-of-control variable based on Hotelling's T2 statistic)

  • 이성임
    • 응용통계연구
    • /
    • 제31권6호
    • /
    • pp.811-823
    • /
    • 2018
  • 호텔링 $T^2$ 통계량에 근거한 다변량 관리도는 공정의 이상상태를 식별하는 통계적 공정관리의 강력한 도구 중 하나이다. 다수의 품질 특성치를 동시에 모니터링하는데 사용된다. $T^2$ 관리도를 통해 이상신호가 탐지된다는 것은 평균 벡터의 변화가 있다는 것을 의미하게 된다. 그러나, 이러한 다변량 통계량의 신호는 이상신호에 대한 원인을 식별하기 어렵게 한다. 이 논문에서는 $T^2$ 통계량을 서로 독립인 항으로 분해한 Mason, Young, Tracy (MYT) 분해에 기반한 원인 식별 방법들을 살펴본다. 또한, R 소프트웨어를 사용하여 사례분석을 하고, 모의실험을 통해 각 절차의 성능을 비교 평가해보고자 한다.

Estimating the Number of Clusters using Hotelling's

  • Choi, Kyung-Mee
    • Communications for Statistical Applications and Methods
    • /
    • 제12권2호
    • /
    • pp.305-312
    • /
    • 2005
  • In the cluster analysis, Hotelling's $T^2$ can be used to estimate the unknown number of clusters based on the idea of multiple comparison procedure. Especially, its threshold is obtained according to the probability of committing the type one error. Examples are used to compare Hotelling's $T^2$ with other classical location test statistics such as Sum-of-Squared Error and Wilks' $\Lambda$ The hierarchical clustering is used to reveal the underlying structure of the data. Also related criteria are reviewed in view of both the between variance and the within variance.

Unbalanced ANOVA for Testing Shape Variability in Statistical Shape Analysis

  • Kim, Jong-Geon;Choi, Yong-Seok;Lee, Nae-Young
    • 응용통계연구
    • /
    • 제23권2호
    • /
    • pp.317-323
    • /
    • 2010
  • Measures are very useful tools for comparing the shape variability in statistical shape analysis. For examples, the Procrustes statistic(PS) is isolated measure, and the mean Procrustes statistic(MPS) and the root mean square measure(RMS) are overall measures. But these measures are very subjective, complicated and moreover these measures are not statistical for comparing the shape variability. Therefore we need to study some tests. It is well known that the Hotelling's $T^2$ test is used for testing shape variability of two independent samples. And for testing shape variabilities of several independent samples, instead of the Hotelling's $T^2$ test, one way analysis of variance(ANOVA) can be applied. In fact, this one way ANOVA is based on the balanced samples of equal size which is called as BANOVA. However, If we have unbalanced samples with unequal size, we can not use BANOVA. Therefore we propose the unbalanced analysis of variance(UNBANOVA) for testing shape variabilities of several independent samples of unequal size.

Statistical Analysis for Feature Subset Selection Procedures.

  • Kim, In-Young;Lee, Sun-Ho;Kim, Sang-Cheol;Rha, Sun-Young;Chung, Hyun-Cheol;Kim, Byung-Soo
    • 한국생물정보학회:학술대회논문집
    • /
    • 한국생물정보시스템생물학회 2003년도 제2차 연례학술대회 발표논문집
    • /
    • pp.101-106
    • /
    • 2003
  • In this paper, we propose using Hotelling's T2 statistic for the detection of a set of a set of differentially expressed (DE) genes in colorectal cancer based on its gene expression level in tumor tissues compared with those in normal tissues and to evaluate its predictivity which let us rank genes for the development of biomarkers for population screening of colorectal cancer. We compared the prediction rate based on the DE genes selected by Hotelling's T2 statistic and univariate t statistic using various prediction methods, a regulized discrimination analysis and a support vector machine. The result shows that the prediction rate based on T2 is better than that of univatiate t. This implies that it may not be sufficient to look at each gene in a separate universe and that evaluating combinations of genes reveals interesting information that will not be discovered otherwise.

  • PDF

Comparison of Univariate and Multivariate Gene Set Analysis in Acute Lymphoblastic Leukemia

  • Soheila, Khodakarim;Hamid, AlaviMajd;Farid, Zayeri;Mostafa, Rezaei-Tavirani;Nasrin, Dehghan-Nayeri;Syyed-Mohammad, Tabatabaee;Vahide, Tajalli
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제14권3호
    • /
    • pp.1629-1633
    • /
    • 2013
  • Background: Gene set analysis (GSA) incorporates biological with statistical knowledge to identify gene sets which are differentially expressed that between two or more phenotypes. Materials and Methods: In this paper gene sets differentially expressed between acute lymphoblastic leukaemia (ALL) with BCR-ABL and those with no observed cytogenetic abnormalities were determined by GSA methods. The BCR-ABL is an abnormal gene found in some people with ALL. Results: The results of two GSAs showed that the Category test identified 30 gene sets differentially expressed between two phenotypes, while the Hotelling's $T^2$ could discover just 19 gene sets. On the other hand, assessment of common genes among significant gene sets showed that there were high agreement between the results of GSA and the findings of biologists. In addition, the performance of these methods was compared by simulated and ALL data. Conclusions: The results on simulated data indicated decrease in the type I error rate and increase the power in multivariate (Hotelling's $T^2$) test as increasing the correlation between gene pairs in contrast to the univariate (Category) test.

Asymptotic Relative Efficiencies of Chaudhuri′s Estimators for the Multivariate One Sample Location Problem

  • Park, Kyungmee
    • Communications for Statistical Applications and Methods
    • /
    • 제8권3호
    • /
    • pp.875-883
    • /
    • 2001
  • We derive the asymptotic relative efficiencies in two special cases of Chaudhuri's estimators for the multivariate one sample problem. And we compare those two when observations are independent and identically distributed from a family of spherically symmetric distributions including normal distributions.

  • PDF

CIMS에서 다변량 ARMA 공정제어 (Multivariate Autoregressive Moving Average(ARMA) process Control in Computer Integrated Manufacturing Systems (CIMS))

  • 최성운
    • 산업경영시스템학회지
    • /
    • 제15권26호
    • /
    • pp.181-187
    • /
    • 1992
  • 본 논문은 CIMS에서 적응되는 ARMA 공정제어의 새로운 3단계절차를 제안한다. 첫번째 단계는 다변량 ARMA모델을 식별하여 모수를 추정하고, white noise로 진단된 잔차 series에 대하여 다변량 제어통계량(즉, 다변량 Hotelling T$^2$통계량, 다변량 CUSUM, 다변량 EWHA 통계량, 다변량 MA 통계량)등을 계산한다. 마지막으로 본 논문에서 제안한 8가지 다변량 제어통계량을 상호비교하여 이상점을 발견한다.

  • PDF

건식 진공펌프의 상태진단 및 예지보수 기법 (Predictive Diagnosis and Preventive Maintenance Technologies for Dry Vacuum Pumps)

  • 정완섭
    • 진공이야기
    • /
    • 제2권1호
    • /
    • pp.31-34
    • /
    • 2015
  • This article introduces fundamentals of self-diagnosis and predictive (or preventive) maintenance technologies for dry vacuum pumps. The state variables of dry pumps are addressed, such as the pump and motor body temperatures, consumption currents of main and booster pumps, mechanical vibration, and exhaust pressure, etc. The adaptive parametric models of the state variables of the dry pump are exploited to provide dramatic reduction of data size and computation time for self-diagnosis. Two indicators, the Hotelling's $T^2$ and the sum of squares residuals (Q), are illustrated to be quite effective and successful in diagnosing dry pumps used in the semiconductor processes.