• 한국운동역학회지
• /
• 제32권2호
• /
• pp.56-68
• /
• 2022

Objective: The purpose of this systematic review and meta-analysis was to investigate potential effects of HRT (hormone replacement therapy) on motor functions in postmenopausal women. Method: In this meta-analysis, 19 studies that examined changes in motor functions between postmenopausal women with and without HRT intervention were qualified. We additionally conducted moderator variable analyses including: (1) motor function type, (2) hormone type, and (3) duration of HRT intervention. Results: The random effects model showed no significant overall effects (SMD = 0.199; SE = 0.115; 95% CI = -0.026~0.425; Z = 1.730; p = 0.084; I² = 93.258%). Additional three moderator variable analyses revealed no significant effect sizes indicating that specific HRT protocols did not improve different motor functions in postmenopausal women. Conclusion: These meta-analytic findings suggest that HRT had no positive effects on motor functions in postmenopausal women.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.79-80
• /
• 2022

본 논문에서는 데이터 증강 기법 중 하나인 EDA를 적용하여 BERT 기반의 감성 분류 언어 모델을 만들고, 성능 개선 방법을 제안한다. EDA(Easy Data Augmentation) 기법은 테이터가 한정되어 있는 환경에서 SR(Synonym Replacement), RI(Random Insertion), RS(Random Swap), RD(Random Deletion) 총 4가지 세부 기법을 통해서 학습 데이터를 증강 시킬 수 있다. 이렇게 증강된 데이터를 학습 데이터로 이용해 구글의 BERT를 기본 모델로 한 전이학습을 진행하게 되면 감성 분류 모델을 생성해 낼 수 있다. 데이터 증강 기법 적용 후 전이 학습을 통해 생성한 감성 분류 모델의 성능을 증강 이전의 전이 학습 모델과 비교해 보면 정확도 측면에서 향상을 기대해 볼 수 있다.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.603-608
• /
• 2024

무응답 및 결측값은 표본 탈락, 설문조사에 대한 답변 회피 등으로 발생하며 정보의 손실 및 편향된 추론의 가능성이 있는 문제가 발생하게 되며, 이 경우 결측값을 적절한 값으로 바꾸는 대체가 필요하게 된다. 본 논문에서는 결측값에 대한 대체 방법으로 제안되었던 평균 대체, 다중회귀 대체, 랜덤 포레스트 대체, K-최근접 이웃 대체, 그리고 딥러닝을 기본으로 한 오토인코더 대체와 잡음제거 오토인코더 대체 방법을 비교한다. 결측값을 대체하는 이러한 방법들에 대해 설명하고, 연속형의 모의실험 데이터와 실제 데이터에 접목시켜 각 방법들을 비교하였다. 비교 결과 대부분의 경우에서 다중 대체 방법인 랜덤 포레스트 대체 방법과 잡음제거 오토인코더 대체 방법의 성능이 좋았음을 확인하였다.

• 한국산업정보학회논문지
• /
• 제17권7호
• /
• pp.139-148
• /
• 2012

분류기의 앙상블 학습은 여러 개의 서로 다른 분류기들의 조합을 통해 만들어진다. 앙상블 학습은 기계학습 분야에서 많은 관심을 끌고 있는 중요한 연구주제이며 대부분의 경우에 있어서 앙상블 모형은 개별 기저 분류기보다 더 좋은 성과를 내는 것으로 알려져 있다. 본 연구는 부도 예측 모형의 성능개선에 관한 연구이다. 이를 위해 본 연구에서는 단일 모형으로 그 우수성을 인정받고 있는 SVM을 기저 분류기로 사용하는 앙상블 모형에 대해 고찰하였다. SVM 모형의 성능 개선을 위해 bagging과 random subspace 모형을 부도 예측 문제에 적용해 보았으며 bagging 모형과 random subspace 모형의 성과 개선을 위해 bagging과 random subspace의 통합 모형을 제안하였다. 제안한 모형의 성과를 검증하기 위해 실제 기업의 부도 예측 데이터를 사용하여 실험하였고, 실험 결과 본 연구에서 제안한 새로운 형태의 통합 모형이 가장 좋은 성과를 보임을 알 수 있었다.

• Journal of Preventive Medicine and Public Health
• /
• 제48권6호
• /
• pp.280-286
• /
• 2015

Objectives: Approximately 10% to 15% of lung cancer cases occur in never-smokers. Hormonal factors have been suggested to lead to an elevated risk of lung cancer in women. This systematic review (SR) aimed to investigate the association between hormonal replacement therapy (HRT) and the risk of lung cancer in women using cohort studies. Methods: We first obtained previous SR articles on this topic. Based on these studies we made a list of refereed, cited, and related articles using the PubMed and Scopus databases. All cohort studies that evaluated the relative risk of HRT exposure on lung cancer occurrence in women were selected. Estimate of summary effect size (sES) with 95% confidence intervals (CIs) were calculated. Results: A total of 14 cohort studies were finally selected. A random effect model was applied due to heterogeneity (I-squared, 64.3%). The sES of the 14 articles evaluating the impact of HRT exposure on lung cancer occurrence in women indicated no statistically significant increase in lung cancer risk (sES, 0.99; 95% CI, 0.90 to 1.09). Conclusions: These results showed that HRT history had no effect on the risk of lung cancer in women, even though the sES of case-control studies described in previous SR articles indicated that HRT had a protective effect against lung cancer. It is necessary to conduct a pooled analysis of cohort studies.

• 품질경영학회지
• /
• 제48권1호
• /
• pp.201-214
• /
• 2020

Purpose: The purpose of this paper is to determine an optimal number of cycle times for the replacement under the circumstance where the system is replaced at the periodic time and the multiple number of working cycles whichever occurs first and the system is minimally repaired between the replacements if it fails. Methods: The system is replaced at periodic time () or cycle time, whichever occurs first, and is repaired minimally when it fails between successive replacements. To determine the optimal number of cycle times, the expected total cost rate is optimized with respect to the number of cycle times, where the expected total cost rate is defined as the ratio of the expected total cost between replacements to the expected time between replacements. Results: In this paper, we conduct a sensitivity analysis to find the following results. First, when the expected number of failures per unit time increases, the optimal number of cycle times decreases. Second, when the periodic time for replacement becomes longer, the optimal number of cycle times decreases. Third, when the expected value for exponential distribution of the cycle time increases, the optimal number of cycle times increases. Conclusion: A mathematical model is suggested to find the optimal number of cycle times and numerical examples are provided through the sensitivity analysis on the model parameters to see the patterns for changes of the optimal number of cycle times.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제57권4호
• /
• pp.413-431
• /
• 2018

In this study, I developed an activity oriented lesson to support the understanding of probabilistic and quantitative estimating population ratios according to the standard statistical principles and discussed its implications in didactical respects. The developed activity lesson, as an efficient physical simulation activity by sampling with replacement, simulates unknown populations and real problem situations through completely closed 'Closed Box' in which we can not see nor take out the inside balls, and provides teaching and learning devices which highlight the representativeness of sample ratios and the sampling variability. I applied this activity lesson to the gifted students who did not learn estimating population ratios and collected the research data such as the activity sheets and recording and transcribing data of students' presenting, and analyzed them by Qualitative Content Analysis. As a result of an application, this activity lesson was effective in recognizing and reflecting on the representativeness of sample ratios and recognizing the random sampling variability. On the other hand, in order to show the sampling variability clearer, I discussed appropriately increasing the total number of the inside balls put in 'Closed Box' and the active involvement of the teachers to make students pay attention to controlling possible selection bias in sampling processes.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.481-491
• /
• 2010

수강하는 학생 개개인이 응답한 여러 개의 파일을 한 파일에 모은 다음 이 자료를 가지고 난수생성, 표본추출 과정과 방법, 모수와 통계량을 비교하는 프로그램을 엑셀 매크로로 작성하였다. 모집단에서 일부분의 표본을 추출하여 모수와 통계량의 차이를 비교하는 등 자료의 생성, 분석, 결과의 해석을 빠른 시간내에 해결하여 학생들이 흥미를 가지고 수업에 참여하도록 유도한다. 엑셀에서는 난수발생시 중복된 값이 발생하는데 본 연구에서는 비주얼베이직 매크로로 비복원추출 프로그램을 작성하여 활용한다.

• International Journal of Reliability and Applications
• /
• 제14권1호
• /
• pp.41-54
• /
• 2013

In this paper, cost analysis is conducted using inter-failure interval under renewable warranty subject to imperfect repair for multi-component system. One way to model the imperfect repair is to use the quasi-renewal process (Wang and Pham 1996). Two alternative quasi-renewal processes were suggested by Park and Pham (2010) using quasi-renewal process; first is an altered quasi-renewal process with random variable parameter and second is a mixed quasi-renewal process considering replacement service and repair service, simultaneously. In this study, we use the altered and mixed quasi-renewal processes and develop the warranty cost model to obtain the expected value of warranty cost and to help company make important decisions regarding the warranty policy. Numerical examples are used to demonstrate the applicability of the methodology derived in the paper.

• Journal of the Korean Data and Information Science Society
• /
• 제4권
• /
• pp.65-74
• /
• 1993

Suppose that we have two populations(or systems), say ${\Pi}_{1}\;and\;{\Pi}_{2}$, to be tested. A random sample of size n from each population is taken and the test for each system will be terminated when the first r failures among n random samples are observed. This kind of test is caned the type-II censored (or item-censored) testing without replacement. Under this scheme we consider the problem of estimating the unknown parameters of interests and the reliability for a given time t for each population.