• Communications for Statistical Applications and Methods
• /
• 제29권5호
• /
• pp.547-559
• /
• 2022

For a chi-squared test, which is a statistical method used to test the independence of a contingency table of two factors, the expected frequency of each cell must be greater than 5. The percentage of cells with an expected frequency below 5 must be less than 20% of all cells. However, there are many cases in which the regional expected frequency is below 5 in general small area studies. Even in large-scale surveys, it is difficult to forecast the expected frequency to be greater than 5 when there is small area estimation with subgroup analysis. Another statistical method to test independence is to use the Bayes factor, but since there is a high ratio of data dependency due to the nature of the Bayesian approach, the low expected frequency tends to decrease the precision of the test results. To overcome these limitations, we will borrow information from areas with similar characteristics and pool the data statistically to propose a pooled Bayes test of independence in target areas. Jo et al. (2021) suggested hierarchical Bayesian pooling models for small area estimation of categorical data, and we will introduce the pooled Bayes factors calculated by expanding their restricted pooling model. We applied the pooled Bayes factors using bone mineral density and body mass index data from the Third National Health and Nutrition Examination Survey conducted in the United States and compared them with chi-squared tests often used in tests of independence.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권3호
• /
• pp.155-160
• /
• 2017

최근 컴퓨터를 이용한 다양한 인식 문제를 해결하기 위해 딥 러닝을 적용하는 사례가 늘어나고 있다. 딥 러닝은 학습에 필요한 요소를 학습데이터를 통해 스스로 도출해내기 때문에, 수작업(hand-craft)을 통해 특징을 도출하던 기존의 기계학습 방법보다 더 많은 장점을 갖는다. 행동인식을 위한 기존의 심층 신경망은 비디오 데이터를 일정 프레임의 이미지로 분할한 후, 분할된 각 이미지 사이의 시간적 연계성 분석을 통해 행동을 분류한다. 그러나 이러한 신경망은 소규모 행동 클래스를 갖는 분류 문제에서 학습 데이터의 부족 문제 및 과적합(overfitting) 문제로 인해 이를 실제 문제에 적용하기 어려운 경우가 많다. 이에 본 논문에서는 5가지의 소규모 행동 클래스를 정의하고, 기존 행동 인식 신경망의 최적화를 통해 이를 분류하였다. 700개의 비디오데이터를 통해 행동 데이터베이스를 구성하였고, 약 74.00%의 분류 정확도를 얻을 수 있었다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권6호
• /
• pp.19-27
• /
• 2020

This research investigates the determinants of investment capital size in Vietnam's small and medium-sized firms. The study employs a sample of 458 small and medium-sized enterprises in the country. The study is based on data collects in the areas of Hanoi, Bac Can, Buon Ma Thuot and Pleiku Provinces at time series data of October 2019. This study also identifies the factors that affect the size of investment capital in medium and small-sized enterprises in Vietnam. Data are processed via STATA 14.0 and SPSS 20.0 software. The research results indicate that (1) business lines, (2) import and export business, (3) type of business registration, (4) business location, (5) operating time, and (6) the percentage of the organization's capital contribution are factors that impact on the size of the investment capital of the business. Business line and business location have negative impacts on investment capital size. The operating time, the percentage of the organization's capital contribution, import and export business, and the type of business registration have positive impacts on investment capital size. In addition, the findings of this study also suggest that the operation time has the highest impact on investment capital size of the small and medium-sized firms in Vietnam.

• 유통과학연구
• /
• 제11권4호
• /
• pp.89-97
• /
• 2013

Purpose - The purpose of this study is to systematically review the background of the Korean distribution promotion policy and distribution adjustment policies along with related regulations and policies. Research design, data, and methodology - Domestic distribution policy and relevant laws were examined through a review of existing research literature. The results of the development process of the domestic distribution policy, promotion policies, and adjustment policies are summarized below. Results - The results are summarized as follows. First, the purpose of the development of the domestic distribution promotion policy was to strengthen the competitiveness of the small and medium business industry through structural advancement of the small and medium industry. By expanding the managerial base for the small and medium industry, a new balance could be created in the national economy. There was a requirement for an early assistance policy for small and medium businesses as a base of these businesses in the distribution industry developed from their original model of catering to a traditional market of retail shops. Since 1996, there was a need for this early assistance policy due to the expansion and rapid growth of large scale stores causing a change in the consumption pattern for distribution markets and the decline of large enterprises. Second, the government supports small and medium business distribution through distribution promotion policies by supporting an organization promoting small business and supporting innovation in the distribution system. Third, in 1961 a business mediation system was established to protect small and medium industries. The Small and Medium Business Administration advises conglomerates to postpone acquisitions, restrain expansion of the business, or to reduce business scale if small businesses undergo an adverse effect such as decreasing demand because large companies are expanding into their areas. Fourth, the Distribution Adjustment Policy managed large-scale store regulation as follows: ① limitation on construction by urban planning ordinance, ② limitation on location based on traffic impact assessments, ③ regulation based on business guidelines by chiefs of autonomous bodies, ④ regulation on mandatory holidays and limitation of business hours. This large-scale store regulation is a policy introduced by authority to increase competitiveness of small and medium business distribution by the government. Conclusions - As discussed in this study, the distribution promotion policy and distribution adjustment policy are government distribution policies focused on the protection of the small and medium distribution businesses. This study is timely, since it was planned when the strengthening of the revisions of the Distribution Industry Development Act, aimed to protect small and medium retailers and merchants, was under discussion. The significance of this study is that it offers insights for the development of new policies in the future and an opportunity to consider the background of the distribution policy by the government.

• 한국BIM학회 논문집
• /
• 제6권3호
• /
• pp.24-33
• /
• 2016

Planning occurs from day-to-day, small-scale decisions to large-scale infrastructure investment decisions. For that reason, various attempts have been made to appropriately assist decision-making process and its optimization. Lately, initiation of a large amount of data, also known as big data has received great attention from diverse disciplines because of versatility and adoptability in its use and possibility to generate new information. Accordingly, implementation of big data and other information management systems, such as geographic information systems (GIS) and building information modeling (BIM) have received enough attention to establish each of its own profession and other associated activities. In this extent, this study illustrates a series of big data implementation cases that can provide a lesson to urban planning domain. In specific, case studies analyze how data was used to extract the most optimized solution and what aspects could be helpful in relation to planning decisions. Also, important notions about GIS and its application in various urban cases are examined.

• 보건의료산업학회지
• /
• 제11권3호
• /
• pp.23-35
• /
• 2017

Objectives : This study analyzed the trends of patient costs in 7diagnosis-related groups(DRG) since July 2013 when the government made it mandatory for all hospitals and clinics. Methods : Data were collected from the 7DRG score chart published by the Ministry of Health and Welfare(MoHW) from July 2013 to January 2017. The average value of the weekday relative value scale was multiplied by unit price, referred to as'- "patient costs by disease group"-' and they were analyzed by time series. Results : Patient costs had increased among all patients with a comprehensive disease. Small and medium-sized hospitals (hospitals and clinics) showed a slight increase in patient costs. Conclusions : Enforcement of the Korean diagnosis-related groups has led to management crisis in small and medium-sized hospitals and deterioration medical service quality. To solve this problem, The weekday relative value scale of small and medium-sized hospitals should be increased significantly.

• 천문학회보
• /
• 제42권2호
• /
• pp.81.3-81.3
• /
• 2017

In this paper, we report a small-scale emerging island and double arc loops, which are associated with a M6.5 flare, in Active Region 12371. We investigate the spatial and temporal changes of both photospheric magnetic fields using SDO/HMI data and coronal magnetic structures obtained from nonliner force-free field (NLFFF) extrapolation. From the vector magnetograms, we find a small-scale emerging island near the main polarityy inversion line about three hours before the flare. The island has a strong shear angle, which is determined by difference between transverse component of observed field and potential field, of around 90 degrees. Furthermore, the NLFFF well reproduces a sigmoidal structure seen in SDO/AIA 94, which is consistent with the double arc loops configuration suggested by Ishiguro and Kusano (2017) who introduced a magnetic configuration showing the double arc instability. The observed emerging island is located among the double arc loops, which is also supproted by their model. Finally, there was an eruption (M6.5 flare) associated with the loops. We discuss a possible role of the double arc instability for the eruption.

• Clinical and Experimental Pediatrics
• /
• 제59권10호
• /
• pp.414-420
• /
• 2016

Purpose: We investigated behavioral problems, attention problems, and cognitive function in children and adolescents born small for gestational age (SGA). Methods: Forty-six SGA children born at term and 46 appropriate for gestational age (AGA) children born at term were compared. Psychiatric symptoms were examined with reference to the Korean-Child Behavior Checklist, Korean-Youth Self Report, and Attention Deficit Hyperactivity Disorder Rating Scale (ADHD-RS). Cognitive function was estimated using the Wechsler Intelligence Scale. Sociodemographic data were recorded from interviews. Results: SGA children had high scores on delinquent behavior, aggressive behavior, and the externalizing scale, and they also showed a propensity for anxiety and depression. The SGA group had a higher mean ADHD-RS score than the AGA group ($10.52{\pm}8.10$ vs.$9.93{\pm}7.23$), but the difference was not significant. The SGA group had a significantly lower verbal intelligence quotient (IQ) than the AGA group, but the mean scores of both groups were within normal limits. Conclusion: This study indicates marked behavioral problems, such as delinquency, aggressiveness, and anxiety and depression, as well as low verbal IQ in the SGA group than in the AGA group. Even in cases in which these symptoms are not severe, early detection and proper treatment can help these children adapt to society.

• 한국지구과학회지
• /
• 제31권1호
• /
• pp.1-7
• /
• 2010

그 동안 많은 연구에서 지형보정을 위한 프로그램들이 개발되어왔으며, 매우 효과적으로 지형보정을 수행하는 것으로 인정받아왔다. 특히, 한반도 뿐만이 아니라 세계적으로도 수치 지형자료가 보편적으로 보급되어 지형보정을 위한 기반 자료는 충분히 확보되고 있다. 이번 연구는 일반적인 광역탐사가 아닌 소규모 광체나 지질구조에 대한 정밀한 중력탐사에 대한 자동지형보정을 수행할 수 있도록 하는 프로그램을 개발하였다. 소규모 지하자원이나 지하공동 등의 소규모 지질현상에 대한 중력탐사에는 기존의 광역탐사에 적합한 지형보정프로그램보다 더욱 정밀한 지형보정프로그램이 필요하다. 따라서 본 연구를 통해서 개발된 자동정밀지형보정프로그램으로 정밀중력탐사를 보다 효율적으로 수행할 수 있게되었다. 본 연구에서 개발된 정밀지형보정프로그램에서는 multiquadric equation을 이용한 지형구현을 통해 보다 정밀한 지형 생성이 가능하게 설계하였으며, 연구자의 설정에 따라 중력측정점 주변에 자세한 지형값을 넣어 정밀한 지형보정이 가능하도록 하였다. 또한 기존의 광역중력탐사에서 무시되던 지형과 중력계 사이의 거리 차에 따른 옵션을 설정하여 정밀한 지형보정 수치를 산출하도록 하였다.

• 한국콘텐츠학회논문지
• /
• 제19권4호
• /
• pp.54-62
• /
• 2019

산업 재해와 관련하여 대기업 및 공공기관에서는 체계적인 관리를 통해 지속적으로 재해감소가 이루어지고 있으나 소규모 영세사업장에서는 지속적으로 산업재해가 증가하고 있는 추세이다. 이에 정부에서는 근로자의 안전을 위해 소규모 사업장을 대상으로 재정지원사업을 실시함으로써 산업재해 예방에 필요한 물품구입을 지원하고 있다. 하지만, 이러한 재정적 투입에도 불구하고 사업에 대한 효과성은 검증이 거의 이루어지지 않는 실정이다. 본 연구에서는 2007년부터 2016년까지 최근 10년간 산업재해 발생현황, 연도별 사업장 현황 및 재정지원사업 수혜 사업장 현황 데이터를 바탕으로 이중차분법을 이용하여 소규모 사업장을 대상으로 한 산업재해 예방 재정지원 사업의 정책적 효과성을 분석하였다. 본 연구는 소규모 사업장 대상으로 재해 감소를 위한 재정지원사업의 순수 효과를 분석하였다는 점에서 의의가 있다.