• Wind and Structures
• /
• 제19권3호
• /
• pp.271-294
• /
• 2014

The impact of artefacts in archived wind observations on the design wind speed obtained by extreme value analysis is demonstrated using case studies. A signpost protocol for detecting candidate artefacts is described and its performance assessed by comparing results against previously validated data. The protocol targets artefacts by exploiting the serial correlation between observations. Additional "sieve" algorithms are proposed to identify types of correctable artefact from their "signature" in the data. In extreme value analysis, artefacts displace valid observations only when they are larger, hence always increase the design wind speed. Care must be taken not identify large valid values as artefacts, since their removal will tend to underestimate the design wind speed.

• Journal of the Korean Statistical Society
• /
• 제12권2호
• /
• pp.81-90
• /
• 1983

The least squares estimator of disturbance variance in a regression model is biased under a serial correlation. Under the assumption of an AR(I), Theil(1971) crudely related the bias with the autocorrelation of the disturbances and the autocorrelation of the explanatory variable for a simple regression. In this paper we derive a relation which relates the bias with the autocorrelation of disturbances and the autocorrelation of explanatory variables for a multiple regression with improved precision.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 추계 학술발표회 논문집
• /
• pp.167-173
• /
• 2005

This paper presents an autocorrelation test that is applicable to dynamic panel data models with serially correlated errors. The residual-based GMM t-test is a significance test that is applied after estimating a dynamic model by using the instrumental variable(IV) method and is directly applicable to any other consistently estimated residuals. Monte Carlo simulations show that the t-test has considerably more power than the $m_2$ test or the Sargan test under both forms of serial correlation (i.e., AR(1) and MA(1)).

• Journal of the Korean Statistical Society
• /
• 제34권4호
• /
• pp.367-375
• /
• 2005

This paper presents an autocorrelation test that is applicable to dynamic panel data models with serially correlated errors. The residual-based GMM t-test is a significance test that is applied after estimating a dynamic model by using the instrumental variable (IV) method and is directly applicable to any other consistently estimated residuals. Monte Carlo simulations show that the t-test has considerably more power than the $m_2$ test or the Sargan test under both forms of serial correlation (i.e., AR(1) and MA(1)).

• 물과 미래
• /
• 제13권1호
• /
• pp.49-56
• /
• 1980

The thesis of this analytical study includes 1) the generation of annual and monthly discharge regarding single hydrological variable at single site, 2)comparsion with the historical records and the generation, and 3) changing the monthly generatied discharge into annual. The conclusion of this will be used for the future plan for water resources development. Annual discharges at waegwan are characterized by log-normal distirbution and persistence-absent. Also, the random number generator causes the errors in the generation of annual discharge. The serial correlation coefficients of the generated annual discharge have less value than that of historical records, while the correlation coefficient and slope in January have(+) value and opposite to historical record. To change the monthly generated discharge into annual is not proper.

• 한국농공학회지
• /
• 제41권6호
• /
• pp.44-53
• /
• 1999

The statistical characteristics of the factors related to the daily rainfall prediction model are analyzed . Records of daily precipitation, mean air temperature, relative humidity , dew-point temperature and air pressure from 1973∼1998 at 8 meteorological sttions in south-western part of Korea were used. 1. Serial correlatino of daily precipitaiton was significant with the lag less than 1 day. But , that of other variables were large enough until 10 day lag. 2. Crosscorrelation of air temperature, relative humidity , dew-point temperature showed similar distribution wiht the basin contrours and the others were different. 3. There were significant correlation between the meteorological variables and precipitation preceded more than 2 days. 4. Daily preciption of each station were treated as a truncated continuous random variable and the annual periodic components, mean and standard deviation were estimated for each day. 5. All of the results could be considered to select the input variables of regression model or neural network model for the prediction of daily precipitation and to construct the stochastic model of daily precipitation.

• 한국멀티미디어학회논문지
• /
• 제16권8호
• /
• pp.914-926
• /
• 2013

최근 보안 시스템 중에서 지문인식을 이용한 보안 시스템은 다른 보안 시스템에 비해 유일성과 편의성 등의 장점을 가짐으로써 많은 사람들이 관심을 갖는 분야이다. 지문인식 시스템에 있어서 가장 중요한 사항은 실제 지문과 영상을 통해 얻어진 지문간의 정합에서의 정확성과 지문 인식을 위해 사용하는 영상처리 알고리즘들을 신속하게 처리하는 데 있다. 기존의 지문인식 시스템은 특징 추출을 위해 사용하는 알고리즘들의 처리 시간을 줄이기 위해 전체 처리과정 중 일부 과정들을 생략함으로써 처리시간을 단축한다. 하지만 이 방식은 처리시간을 단축시킬 수 있는 반면 특징 추출에 대한 정확도가 떨어진다. 따라서 본 논문에서는 특징 추출에 대한 정확도를 높이기 위해 전체 처리 과정을 사용하면서 동시에 처리시간도 단축시킬 수 있는 다중 접근 메모리 시스템을 이용한 지문인식 특징 추출 알고리즘을 구현하였고, 구현된 시스템을 사용하였을때 다중접근 메모리 시스템과 시리얼 프로세서의 결과에 대해 correlation을 이용한 검증을 통해 제안된 방법의 신뢰도를 확인하였으며, 시리얼 프로세서에 비해 MAMS-PP64를 이용한 방법은 수행시간에서 약 1.56배 향상되었음을 확인하였다.

• 한국농공학회지
• /
• 제23권4호
• /
• pp.46-52
• /
• 1981

The aim at this study has the stochastic hydrological analysis for the annual mean discharge and monthly discharge which were observed at Lobith of River Rhine in the Netherlands from 1901 to 1972. After this study was analysed by computer IBM 370 and Hewlett Parkard 9800, the results were as follows; 1.When 72 data was divided into two groups of subsample data as 36 data, they do not have their properties to be non-homogeneous and inconsistent due to F-test and t-test. 2.The credit limits of the serial correlation coefficient was fluctuated $\pm$0. 231 which was shown in Fig. 3. at significant level 99% by Anderson's test. 3.The correlogram at short term was shown to be no short-term persistence as Fig. 3. 4.Since the correlogram at long term has displayed that Hurst's coefficient was 0.6144 between 0.6 and 0.7, it was to be no long-term persistence. 5.The stochastic model with annual discharge of this River Rhine was shown with $\chi$t=2195+483. 8 $\varepsilon$t as $\chi$t=$\mu$+oet and $\varepsilon$t=$_1$ø$\varepsilon$t-$_1$+ζt where t=1,2,3,..., ζt is an independent series with mean zero and variance (1-ø2), $\varepsilon$t is the dependent series, and 4' is the parameter of the model. 6.The serial correlation coefficient of monthly discharge was explained as $\chi$$_1$ = 0.34 . sin(6-$\pi$t+$\pi$) as Fig.4. and the River Rhine has no large fluctuation and smoothly changed during that time.

• 한국임상수의학회지
• /
• 제37권1호
• /
• pp.9-14
• /
• 2020

Left atrial enlargement (LAE) is an important diagnostic factor in dogs with myxomatous mitral valve disease (MMVD). It is associated with the onset of congestive heart failure (CHF). Recently, a new radiographic left atrial measurement called vertebral left atrial size (VLAS) was introduced. This can be considered as a left atrial enlargement above 2.3. It appears to be related to the severity of MMVD. However, serial changes in VLAS in relation to disease progression and improvement in patients have yet to be studied. This study aims to assess the value of VLAS as a left atrial size monitoring indicator by examining correlations with VHS, LA/Ao ratio and LVIDDN, and comparing serial changes in dogs. A total of 126 dogs were studied with their owners' consent. The dogs were classified into four MMVD groups (Control, B1, B2, C-D) following the ACVIM Guideline by performing a physical examination, radiography and echocardiography. Besides, 24 and 17 dogs were reevaluated to compare values in relation to the progression and improvement of MMVD. VLAS showed significant increase according to the progress of the MMVD stage. This was the same in the Maltese breed group. A strong positive correlation was found between LVIDDN, VHS, LA/Ao ratio, and VLAS. The results of this study found VLAS to be significantly different according to left atrium size, and there was a correlation between disease progression and VLAS levels in each dog. Therefore, VLAS may be used to detect changes in left atrium size as an additional monitoring index of MMVD.

• 정보보호학회논문지
• /
• 제13권5호
• /
• pp.137-145
• /
• 2003

무선통신의 발달로 인해 사람들은 언제, 어디서나 서로 통화할 수 있는 시대에 살고 있다. 하지만, 이동통신의 개방성은 심각한 보안위협에 노출되며, 안전한 통신채널을 제공하기 위해 이동통신망에서 보안은 필수적이다. 이동통신망의 보안을 위해서 사용하는 가장 일반적인 방법중의 하나는 스트림 암호이다. 일반적으로, 이 스트림 암호는 LFSR (Linear Feedback Shift Reigster)을 주로 사용하여 구현된다. 본 고에서는 이동통신망의 스트림 암호의 비도를 향상시키기 위해서 블록 암호알고리즘에서 주로 사용하는 S박스의 변형된 메커니즘을 제안하며. 이 메커니즘은 랜덤성을 고려한 3개의 변형된 S박스 메커니즘이다. 일반적으로, S박스는 비선형 특성을 가진 함수로서 임의 데이터를 공격에 더 강하도록 만들어준다. 제안된 알고리즘의 랜덤성 테스트는 Ent 의사난수 테스트 프로그램을 사용하고, 실험결과 각각의 테스트에서 기존의 스트림 알고리즘보다 더 좋은 랜덤성과 serial correlation coefficient를 가진다는 것을 증명한다.