• 응용통계연구
• /
• 제31권6호
• /
• pp.693-706
• /
• 2018

노인의 신체기능에 부합하는 복지용구를 제공하는 것은 노인이 가능한 한 오랫동안 자신의 집과 지역사회에서 자립하여 생활할 수 있도록 돕기 위해 매우 중요하다. 본 연구는 수급자의 신체 및 인지 기능 상태를 고려하여 개개인에게 적합한 복지용구 품목을 권고할 수 있는 과학적인 복지용구 표준급여모형 알고리즘을 개발하고자 수행되었다. 모형개발에는 데이터마이닝기법인 의사결정나무를 활용하였다. 수급자 8,084명의 장기요양인정조사자료와 파워어세서가 작성한 표준급여계획, 수급자 특성 자료를 이용하여 데이터를 구축하였고, 15개 복지용구 품목별로 표준급여모형을 개발하였다. 본 연구는 노인장기요양보험의 복지용구 급여계획의 객관성 및 과학성을 확보하고 수급자의 자립생활과 안전을 향상시키는 데에 기여할 것으로 기대된다.

• 품질경영학회지
• /
• 제49권2호
• /
• pp.213-231
• /
• 2021

Purpose: This study intends to provide decision-making information to improve efficiency by analyzing the management efficiency of smart greenhouse business entities and identifying factors that affect the efficiency based on input and output. Methods: The subjects of analysis were business entities for cultivating strawberries in smart greenhouses in Jeolla region (northern and southern Jeolla provinces), and the analysis focused on the management performance of the 2019-2020 crop period (year). Data Envelopment Analysis(DEA) was applied as an analysis method for efficiency analysis, Quantile Regression(QR) analysis was applied as a factor affecting the efficiency. Results: The reason for the efficiency gap between business entities was that there were many business entities that did not minimize the input cost at the current level of output, and the area where the variance among business entities was large was the fixed cost per 10a. In the results of the affecting factor analysis, it was found that the seed-seedlings cost, fertilizer cost, other material cost, and employment and labor cost had a negative (-) effect on the efficiency, and that the repair and maintenance cost had a positive (+) effect. Conclusion: Therefore, to achieve the efficiency of scale, it is necessary to reduce the input scale to an appropriate level. In the case of business entities with low efficiency by quartile, the seed-seedlings, fertilizer, and other material costs reduce expenditures, and repair maintenance costs can improve efficiency by increasing expenditures.

• 노동경제논집
• /
• 제43권4호
• /
• pp.1-34
• /
• 2020

글로벌 금융위기 이후 전통적인 실업률의 유용성에 대한 의문이 제기되었으며, 본 연구는 2015년부터 통계청이 공식적으로 발표하고 있는 고용보조지표의 활용 가능성에 대해 살펴보았다. 이를 위해 고용보조지표의 정의를 2003년부터 2014년까지 경제활동인구조사 원자료에 소급 적용하여 고용보조지표를 추산하고, 이를 활용한 노동시장 유휴생산능력 지표에 대한 실증분석을 시도하였다. 실증분석 결과, 보완적 고용지표를 활용한 고용률갭이 여타 노동시장 유휴생산능력 지표에 비해 총산출갭과의 상관성이 높을 뿐만 아니라, 인플레이션에 대한 예측력 개선효과도 비교적 뚜렷한 것으로 나타나, 보완적 고용지표를 활용한 고용률 기반 지표의 유용성이 상대적으로 높음을 시사한다고 할 수 있다.

• 인터넷정보학회논문지
• /
• 제21권6호
• /
• pp.133-139
• /
• 2020

Big data, artificial intelligence (AI), and machine learning are keywords that represent the Fourth industrial Revolution. In addition, as the development of science and technology, the Korean government, public institutions and industries want professionals who can collect, analyze, utilize and predict data. This means that data analysis and utilization education become more important. Education on data analysis and utilization is increasing with trends in other academy. However, it is true that not many academy run long-term and systematic education. Korea Institute of Science and Technology Information (KISTI) is a data ecosystem hub and one of its performance missions has been providing data utilization and analysis education to meet the needs of industries, institutions and governments since 1966. In this study, KISTI's data education was analyzed using the number of curriculum trainees per year from 2001 to 2019. With this data, the change of interest in education in information and data field was analyzed by reflecting social and historical situations. And we identified the characteristics of KISTI and trainees. It means that the identity, characteristics, infrastructure, and resources of the institution have a greater impact on the trainees' interest of data-use education.In particular, KISTI, as a research institute, conducts research in various fields, including bio, weather, traffic, disaster and so on. And it has various research data in science and technology field. The purpose of this study can provide direction forthe establishment of new curriculum using data that can represent KISTI's strengths and identity. One of the conclusions of this paper would be KISTI's greatest advantages if it could be used in education to analyze and visualize many research data. Finally, through this study, it can expect that KISTI will be able to present a new direction for designing data curricula with quality education that can fulfill its role and responsibilities and highlight its strengths.

• Animal Bioscience
• /
• 제34권4호
• /
• pp.506-515
• /
• 2021

Objective: Initial consequence of inbreeding is inbreeding depression which impairs the performance of growth, production, health, fertility and survival traits in different animal breeds and populations. The effect of inbreeding on economically important traits should be accurately estimated. The effect of inbreeding depression on growth traits in sheep has been reported in many breeds. Based on this, the main objective of the present research was to evaluate the impact of inbreeding on some growth traits of Iranian Baluchi sheep breed using quantile regression model. Methods: Pedigree and growth traits records of 13,633 Baluchi lambs born from year 1989 to 2016 were used in this research. The traits were birth weight, weaning weight, six-month weight, nine-month weight, and yearling weight. The contribution, inbreeding and co-ancestry software was used to calculate the pedigree statistics and inbreeding coefficients. To evaluate the impact of inbreeding on different quantiles of each growth trait, a series of quantile regression models were fitted using QUANTREG procedure of SAS software. Annual trend of inbreeding was also estimated fitting a simple linear regression of lamb's inbreeding coefficient on the birth year. Results: Average inbreeding coefficient of the population was 1.63 percent. Annual increase rate of inbreeding of the flock was 0.11 percent (p<0.01). The results showed that the effect of inbreeding in different quantiles of growth traits is not similar. Also, inbreeding affected differently on growth traits, considering lambs' sex and type of birth. Conclusion: Quantile regression revealed that inbreeding did not have similar effect on different quantiles of growth traits in Iranian Baluchi lambs indicating that at a given age and inbreeding coefficient, lambs with different sex and birth type were not equally influenced by inbreeding.

• Journal of Animal Science and Technology
• /
• 제63권2호
• /
• pp.440-452
• /
• 2021

The purpose of this study was to determine if an 8-week therapeutic riding (TR) program was effective in improving the walking ability of students with intellectual disabilities. Thirteen students diagnosed with intellectual disabilities participated in the TR program. TR sessions were conducted twice a week (30 min per session), with a total of 16 rides taking place over an 8-week period. A gait measurement analyzer was used to measure progress based on a turn test (6-m walking and turning test), walk test (10-m walking), and timed up and go (TUG) test. Measurements were made three times: before horse-riding (P0), after 4 weeks (8 rides) of horse-riding (P1), and after 8 weeks (16 rides) of horse-riding (P2). Data analysis was conducted using SPSS software (ver. 22.0). Descriptive statistics were generated on the general characteristics of the subjects, and the Kolmogorov-Smirnov test was used to verify the normality of the data. Because of the lack of normality, the data were analyzed using a nonparametric method and the significance level was set to 0.05. Measurements of the duration of the forward gait cycle (s) in the turn test and the forward gait speed (m/s) in the walk test indicated improved walking ability after the TR program (p < 0.001); the stride length (% height) also increased significantly (p < 0.05). The walk test revealed a significant effect of the program on the duration of the forward gait cycle (p < 0.05), while there were significant improvements on the left and right of the elaborated strides (p < 0.001). No significant improvement in TUG test performance was observed after the TR program. In this study, an 8-week TR program had positive results on gait. Therefore, further research is merited, where TR programs are likely to improve the walking ability of individuals with intellectual disabilities.

• 응용통계연구
• /
• 제35권2호
• /
• pp.177-188
• /
• 2022

일반적으로 support vector machine (SVM)은 높은 수준의 분류 정확도를 제공함으로써 다양한 분야의 분류분석에서 널리 사용되고 있다. 그러나 SVM은 최적화 계산식이 이차계획법(quadratic programming)으로 공식화되어 많은 계산 비용이 필요하므로 대용량 자료의 분류분석에는 그 사용이 제한된다. 또한 불균형 자료(imbalanced data)의 분류분석에서는 다수집단에 편향된 분류함수를 추정함으로써 대부분의 자료를 다수집단으로 분류하여 소수집단의 분류 정확도를 현저히 감소시키게 된다. 이러한 문제점들을 해결하기 위하여 본 논문에서는 다수집단을 분할(divide)하고, 소수집단을 과대추출(oversampling)하여 여러 분류함수들을 추정하고 이들을 통합(conquer)하는 DOC-SVM 분류기법을 제안한다. 제안한 DOC-SVM은 분할정복 알고리즘을 다수집단에 적용하여 SVM의 계산 효율을 향상시키고, 과대추출 알고리즘을 소수집단에 적용하여 SVM 분류함수의 편향을 줄이게 된다. 본 논문에서는 모의실험과 실제자료 분석을 통해 제안한 DOC-SVM의 효율적인 성능과 활용 가능성을 확인하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권2호
• /
• pp.81-86
• /
• 2022

시계열 데이터는 주식, IoT, 공장 자동화와 같은 다양한 실생활에서 수집되고 활용되고 있으며, 정확한 시계열 예측은 해당 분야에서 운영 효율성을 높일 수 있어서 전통적으로 중요한 연구 주제이다. 전반적인 시계열 데이터의 향상된 특징을 추출할 수 있는 대표적인 시계열 데이터 분석 방법인 다층 수평 예측은 최근 부가적 정보를 포함하는 시계열 데이터에 내재한 이질성(heterogeneity)까지 포괄적으로 분석에 활용하여 향상된 시계열 예측한다. 하지만 대부분의 심층 학습 기반 시계열 분석 모델들은 시계열 데이터의 이질성을 반영하지 못했다. 따라서 우리는 잘 알려진 temporal fusion transformers 방법을 사용하여 실생활과 밀접한 실제 데이터를 이질성을 고려한 다층 수평 예측에 적용하였다. 결과적으로 주식, 미세먼지, 전기 소비량과 같은 실생활 시계열 데이터에 적용한 방법이 기존 예측 모델보다 향상된 정확도를 가짐을 확인할 수 있었다.

• 대한한방부인과학회지
• /
• 제35권2호
• /
• pp.54-69
• /
• 2022

Objectives: The purpose of this study is to reflect the patient's perspective in the process of developing Korean medicine clinical practice guideline (CPG) of puerperal wind disorder by survey. Methods: Five hundred fifty patients were surveyed from November 3rd, 2021 to November 8th, 2021 by internet. This study is an exploratory cross-sectional survey study, and descriptive statistics and frequency analysis were conducted on respondents' general characteristics, postpartum symptoms, the history of using treatment institution for puerperal wind disorder, satisfaction of medical institutions and perception of postpartum care. Results: Survey results showed that 92.0% of respondents experienced symptoms after childbirth, and 56.2% of the symptoms were arthralgia, followed by obesity with 41.8%. Among puerperal wind disorder patients, 34.2% had treatment history, and 54.3% received Korean medical treatment. Treatment satisfaction was confirmed to be higher in Korean medical treatment. The necessity of postpartum care was recognized at 95.7% of respondents, and the performance rate of traditional Korean postpartum care was also high. Conclusions: Based on a realistic patient-centered basis, it is a study that can lay the foundation for standardizing Korean medicine treatment and strengthening coverage in the future.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.206-208
• /
• 2022

최근 빅데이터 산업이 큰 폭으로 발전하는 만큼 개인정보 유출로 인한 사생활 침해 문제의 관심도 높아졌다. 자연어 처리 분야에서는 이를 개체명 인식을 통해 자동화하려는 시도들이 있었다. 본 논문에서는 한국어 위키피디아 문서의 본문에서 비식별화 정보를 지닌 문장을 식별해 반자동으로 개체명 인식 데이터를 구축한다. 이는 범용적인 개체명 인식 데이터에 반해 비식별화 대상이 아닌 정보에 대해 학습되는 비용을 줄일 수 있다. 또한, 비식별화 정보를 분류하기 위해 규칙 및 통계 기반의 추가적인 시스템을 최소화할 수 있는 장점을 가진다. 본 논문에서 제안하는 개체명 인식 데이터는 총 12개의 범주로 분류하며 의료 기록, 가족 관계와 같은 비식별화 대상이 되는 정보를 포함한다. 생성된 데이터셋을 이용한 실험에서 KoELECTRA는 0.87796, RoBERTa는 0.88575의 성능을 보였다.