• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.647-650
• /
• 2021

The most powerful and modern face recognition techniques are using deep learning methods that have provided impressive performance. The outbreak of COVID-19 pneumonia has spread worldwide, and people have begun to wear a face mask to prevent the spread of the virus, which has led existing face recognition methods to fail to identify people. Mainly, it pushes masked face recognition has become one of the most challenging problems in the face recognition domain. However, deep learning methods require numerous data samples, and it is challenging to find benchmarks of masked face datasets available to the public. In this work, we develop a new simulated masked face dataset that we can use for masked face recognition tasks. To evaluate the usability of the proposed dataset, we also retrained the dataset with ArcFace based system, which is one the most popular state-of-the-art face recognition methods.

• Journal of the Korean Statistical Society
• /
• 제30권2호
• /
• pp.281-290
• /
• 2001

Symmetric estimation and recursive mean adjustment are considered to construct tests for the doble unit root hypothesis for both parametric and semiparametric time series models. It is shown that simultaneous application of symmetric estimation and recursive mean adjustment yields the most powerful test. Moreover, size property of the semiparametric test based on the simultaneous application is bet among all semiparametric tests.

• 한국조경학회지
• /
• 제20권2호
• /
• pp.18-26
• /
• 1992

The purpose of this study is to suggest a method for identifying target markets of potential urban park users by their sociodemographic variables. Data was classified into(ⅰ) users vs. nonusers ; (ⅱ) of chosen three urban parks ; or(ⅲ) users of each urban park then analyzed by discriminant analysis. The results showed that linear combination of selected sociodemographic variables could be used for identifying target markets in some cases. In general, season and sex were the most powerful discriminant variables. But the other cases were not satisfactory. The weak points of this study due to adapting secondary data for analysis were discussed.

• 품질경영학회지
• /
• 제26권4호
• /
• pp.79-87
• /
• 1998

This paper considers the problem of testing a one-sided hypothesis under the generalized sampling plan which is defined by a sequence of independent Bernoulli trials. A certain lexicographic order is defined for the boundary points of the sampling plan. It is shown that the family of probability mass function defined on the boundary points has monotone likelihood ratio, and that the test function is uniformly most powerful.

• Journal of the Korean Statistical Society
• /
• 제33권2호
• /
• pp.149-157
• /
• 2004

The stationarity is one of the most important properties of a time series. We propose robust sign tests for seasonal autoregressive processes to determine whether or not a time series is stationary. The proposed tests are robust to the outliers and the heteroscedastic errors, and they have an exact binomial null distribution regardless of the period of seasonality and types of median adjustments. A Monte-Carlo simulation shows that the sign test is locally more powerful than the tests based on ordinary least squares estimator (OLSE) for heavy-tailed and/or heteroscedastic error distributions.

• Communications for Statistical Applications and Methods
• /
• 제5권3호
• /
• pp.707-722
• /
• 1998

This paper evaluates a new clinical trial designs for low infection rate disease. This type of sparse disease reaction makes the traditional two sample t-test or Wilcoxon rank-sum test inefficient compared to a new test suggested. The new test, which is based solely on the larger changes, is shown to be more effective than existing method by simulation for small samples. However, this test can be shown to be connected to the locally most powerful rank test under certain practical conditions. This design is motivated in testing the treatment effects in periodontal disease research.

• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.293-303
• /
• 1999

When test outcomes of units are dichotomous and he infection rate is small group testing is more efficient that noe-to-one testing in estimating the true p and classifying units as infected or not. In this paper two-sided hypothesis testing and confidence intervals are derived based on the UMP(uniformly most powerful) unbiased test. The UMP unbiased approach is compared with Thompson's and Bhattacharyya et al.'s approaches by computing the length of confidence intervals and capture probabilities and shown to have a number of desirable properties. Unequal allocation one of advantages of the proposed approach is also mentioned.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.317-325
• /
• 1997

Group testing is an efficient method to classify units from a population as infected or non-infected and useful in estimating the infection rate when the population infection rate is small. Upper bounds are the focus of interest in group testing, but has not been studied extensively. In this paper, the upper bound derived from the uniformly most powerful test is proposed and compared with the classical approachers, Thompson's and Bhattacharyya et al.'s methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.620-623
• /
• 1996

POSCO has been developed a general purpose dynamic simulator of the hot strip steel mill. The simulator is a tool for developing the process control system in an industrial system solution business, by making the most use of control and simulation techniques fostered in steelmaking business. This simulator has, not only a powerful numerical analysis function, but an easy-to-use graphic user interface which readily enables to simulate dynamic system. This paper presents the features of the simulator and steel rolling process simulator as its application.

• 아동학회지
• /
• 제20권4호
• /
• pp.195-211
• /
• 1999

This study investigated developmental trends and sex differences in the relation between children's self-esteem and relevant variables by proposing and testing the causal model. The 763 children who participated in the study were 3rd, 5th, and 7th grade students. Major findings were that physical appearance was the most powerful determinant of self-esteem. Students with high self-esteem were more learning oriented, used more motivational behaviors and had higher academic achievement. The findings from this analysis of the causal model revealed remarkable developmental differentiation and stability.