• 한국컴퓨터정보학회논문지
• /
• 제27권6호
• /
• pp.167-174
• /
• 2022

본 논문에서는 여러 개의 독립적인 모집단들 사이에서 상관계수들의 등가성에 대한 퍼뮤테이션 검정을 조사한다. 퍼뮤테이션 검정은 관측값들의 상호교환성에 기초하는 비모수적인 검정 방법이며 상호교환성이란 독립적이고 동일한 확률변수들의 개념을 일반화한 개념이다. 퍼뮤테이션 검정을 사용함으로써 근사적으로 정확한 검정에 가까운 검정을 실시할 수 있다. 퍼뮤테이션 검정은 근사적으로 보수적인 검정만큼의 검정력을 지니며, 표본의 크기가 작거나 정규성 가정이 충족되지 않을 때 유용한 방법이다. 본 논문에서는 먼저 상관계수들의 등가성을 검정하는 모수적인 방법들을 소개하고 이들을 퍼뮤테이션 검정과 비교한다. 끝으로 모든 검정들은 Iris 데이터를 예를 들어 비교된다.

• Computers and Concrete
• /
• 제33권2호
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• Ocean Systems Engineering
• /
• 제6권4호
• /
• pp.377-400
• /
• 2016

Dropped objects are among the top ten causes of fatalities and serious injuries in the oil and gas industry (DORIS, 2016). Objects may accidentally fall down from platforms or vessels during lifting or any other offshore operation. Proper planning of lifting operations requires the knowledge of the risk-free zone on the sea bed to protect underwater structures and equipment. To this end a three-dimensional (3D) theory of dynamic motion of dropped cylindrical object is expanded to also consider ocean currents. The expanded theory is integrated into the authors' Dropped Objects Simulator (DROBS). DROBS is utilized to simulate the trajectories of dropped cylinders falling through uniform currents originating from different directions (incoming angle at $0^{\circ}$, $90^{\circ}$, $180^{\circ}$, and $270^{\circ}$). It is found that trajectories and landing points of dropped cylinders are greatly influenced by the direction of current. The initial conditions after the cylinders have fallen into the water are treated as random variables. It is assumed that the corresponding parameters orientation angle, translational velocity, and rotational velocity follow normal distributions. The paper presents results of DROBS simulations for the case of a dropped cylinder with initial drop angle at $60^{\circ}$ through air-water columns without current. Then the Monte Carlo simulations are used for predicting the landing point distributions of dropped cylinders with varying drop angles under current. The resulting landing point distribution plots may be used to identify risk free zones for offshore lifting operations.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권2호
• /
• pp.663-669
• /
• 2014

Background: With recent progress in health science administration, a huge amount of data has been collected from thousands of subjects. Statistical and computational techniques are very necessary to understand such data and to make valid scientific conclusions. The purpose of this paper was to develop a statistical probability model and to predict future survival times for male breast cancer patients who were diagnosed in the USA during 1973-2009. Materials and Methods: A random sample of 500 male patients was selected from the Surveillance Epidemiology and End Results (SEER) database. The survival times for the male patients were used to derive the statistical probability model. To measure the goodness of fit tests, the model building criterions: Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) were employed. A novel Bayesian method was used to derive the posterior density function for the parameters and the predictive inference for future survival times from the exponentiated Weibull model, assuming that the observed breast cancer survival data follow such type of model. The Markov chain Monte Carlo method was used to determine the inference for the parameters. Results: The summary results of certain demographic and socio-economic variables are reported. It was found that the exponentiated Weibull model fits the male survival data. Statistical inferences of the posterior parameters are presented. Mean predictive survival times, 95% predictive intervals, predictive skewness and kurtosis were obtained. Conclusions: The findings will hopefully be useful in treatment planning, healthcare resource allocation, and may motivate future research on breast cancer related survival issues.

• Journal of Information Processing Systems
• /
• 제11권1호
• /
• pp.57-75
• /
• 2015

In evaluating the performance of a dual-hop wireless link, the effects of large and small scale fading has to be considered. To overcome this fading effect, several schemes, such as multiple-input multiple-output (MIMO) with orthogonal space time block codes (OSTBC), different combining schemes at the relay and receiving end, and orthogonal frequency division multiplexing (OFDM) are used in both the transmitting and the relay links. In this paper, we first make compare the performance of a two-hop wireless link under a different combination of space diversity in the first and second hop of the amplify-and-forward (AF) case. Our second task in this paper is to incorporate the weak signal of a direct link and then by applying the channel model of two random variables (one for a direct link and another for a relayed link) we get very impressive result at a low signal-to-noise ratio (SNR) that is comparable with other models at a higher SNR. Our third task is to bring other three schemes under a two-hop wireless link: use of transmit antenna selection (TAS) on both link with weak direct link, distributed Alamouti scheme in two-hop link and single relay antenna with OFDM subcarrier. Finally, all of the schemes mentioned above are compared to select the best possible model. The main finding of the paper is as follows: the use of MIMO on both hops but application TAS on both links with weak direct link and the full rate OFDM with the sub-carrier for an individual link provide a better result as compared to other models.

• 한국산학기술학회논문지
• /
• 제22권1호
• /
• pp.221-230
• /
• 2021

본 연구에서는 기업의 국제화 수준을 개별 기업의 매출액 대비 해외매출비중(FSTS)으로 측정하고 Sloan(1996)의 모형을 활용 당기순이익과 차기순이익 간의 1차 자기상관관계를 회계이익 지속성의 대용치로 사용하여 기업의 이익지속성에 영향을 미치는 다수의 통제변수들과 함께 실증분석을 실시하였다. 2011년부터 2016년까지 유가증권 시장에 상장된 12월 말 결산법인을 대상으로 고정효과모형을 이용하여 실증분석을 실시한 결과, 기업의 국제화와 회계이익의 지속성은 1% 유의수준에서 양(+)의 효과를 나타내어 개별 기업의 국제화 수준이 증가할수록 기업의 이익 지속성 또한 증가하는 것을 확인 할 수 있었다. 또한 기업규모, 재무건전성, 현금 수반성, 성장성, 투자성은 예측과 일치하게 국제화와 통계적으로 유의한 양(+)의 관계를 나타내어 이들이 기업 이익의 지속성을 증진하는데 중요한 보완적 요인임을 검증하였다. 이는 기업의 규모가 크고 재무건전성 및 현금 수반성이 우수할수록, 성장기회와 투자성향이 높을수록 기업의 이익지속성이 증가함을 의미하여 기존 선행연구들의 결과와도 일치하였다. 이러한 결과는 기업이 국제화 전략 추진을 통해 새로운 해외 시장을 확보하고 성장을 도모함으로서 기업 가치를 안정적으로 유지·확장시킬 수 있음을 시사한다.

• 지능정보연구
• /
• 제24권4호
• /
• pp.67-83
• /
• 2018

2013년 누적인원 2억명을 돌파한 한국의 영화 산업은 매년 괄목할만한 성장을 거듭하여 왔다. 하지만 2015년을 기점으로 한국의 영화 산업은 저성장 시대로 접어들어, 2016년에는 마이너스 성장을 기록하였다. 영화산업을 이루고 있는 각 이해당사자(제작사, 배급사, 극장주 등)들은 개봉 영화에 대한 시장의 반응을 예측하고 탄력적으로 대응하는 전략을 수립해 시장의 이익을 극대화하려고 한다. 이에 본 연구는 개봉 후 역동적으로 변화하는 관람객 수요 변화에 대한 탄력적인 대응을 할 수 있도록 주차 별 관람객 수를 예측하는데 목적을 두고 있다. 분석을 위해 선행연구에서 사용되었던 요인 뿐 아니라 개봉 후 역동적으로 변화하는 영화의 흥행순위, 매출 점유율, 흥행순위 변동 폭 등 선행연구에서 사용되지 않았던 데이터들을 새로운 요인으로 사용하고 Naive Bays, Random Forest, Support Vector Machine, Multi Layer Perception등의 기계학습 기법을 이용하여 개봉 일 후, 개봉 1주 후, 개봉 2주 후 시점에는 차주 누적 관람객 수를 예측하고 개봉 3주 후 시점에는 총 관람객 수를 예측하였다. 새롭게 제시한 변수들을 포함한 모델과 포함하지 않은 모델을 구성하여 실험하였고 비교를 위해 매 예측시점마다 동일한 예측 요인을 사용하여 총 관람객 수도 예측해보았다. 분석결과 동일한 시점에 총 관람객 수를 예측했을 경우 보다 차주 누적 관람객 수를 예측하는 것이 더 높은 정확도를 보였으며, 새롭게 제시한 변수들을 포함한 모델의 정확도가 대부분 높았으며 통계적으로 그 차이가 유의함으로써 정확도에 기여했음을 확인할 수 있었다. 기계학습 기법 중에는 Random Forest가 가장 높은 정확도를 보였다.

• Journal of Animal Science and Technology
• /
• 제47권5호
• /
• pp.703-710
• /
• 2005

한우의 성장과 도체형질에 대한 유전능력 평가모형을 개발하기 위해 4가지 공분산 모형을 적용하여 후대검정에 공시된 수소와 거세 수소의 자료에 대한 표현형 및 유전자형에 대한 분산－공분산을 추정하였다. 4가지 모형은 검정소와 검정차수로 구분한 동기그룹의 고정효과와 임의효과인 종모우 효과로 구성된 부계 반형매 모형을 적용하였다. 도체형질에 대해서는 4가지 공변량을 추가하였는데 모형 1에는 도축일령의 1차식효과를, 모형 2에는 도축연령의 1차와 2차식 효과를 사용하였고, 모형 3에는 절식체중을 모형 4에는 등지방두께를 각기 1차식 공변량으로 사용하였다. 도축일령의 2차식 효과는 유의적이지 않았으나 도축일령에 대한 회귀로 인하여 4개 도체형질에 대한 유전 분산－공분산 성분에 큰 차이를 보였다. 도축 일령을 공변량으로 하였을 때 등지방 두께, 등심단면적, 도체중, 근내지방도와 도체율에 대한 유전력은 각기 0.34, 0.22, 0.24, 0.42, 0.18로 추정되었다. 도체중과 다른 도체형질간에는 정(+)의 유전상관을 보였으나, 등지방 두께와 등심단면적, 그리고 근내지방도와 도체율 간에는 낮은 부(－)의 유전상관을 보였다. 절식체중에 대한 회귀는 도체중에 대한 유전분산과 타 도체형질과의 유전 공분산을 감소시켰으며, 등지방 두께에 대한 회귀는 등심단면적에 대한 유전분산과 등심단면적과 도체중 간의 유전 공분산을 증가시켰다. 절식체중이나 등지방두께를 공변량으로 한 모형으로부터 추정된 분산－공분산 성분은 도축 일령을 공변량으로 했을 때와 상이한 구조를 보였는데, 이들 두 가지 공변량은 골격－근육－지방조직으로 구성되는 신체 부분적 발달 정도와 관련이 있는 것으로 판단된다.

• 대한치과기공학회지
• /
• 제38권1호
• /
• pp.37-49
• /
• 2016

Purpose: This research is performed through the analysis of the dental technology students' life-style factors of their daily lives that have a close relation with health, and the self-reported symptoms which are related to psychosomatic diseases, for the production of basic data for the change of life-styles and the development of educational programmes. Methods: This research has been performed through questionnaires from the beginning of October of 2014 till the end of November through the Dental Technology students of G-do, chosen by random sampling method after informed consent, where out of the 270 papers, 258 results were used for the analysis. Results: Firstly, the results of the research was as follows: Non-smokers accounted for 61.2%, student who did not do regular physical activities accounted for 50.4%, students who had sleeping hours of 6 to 7 hours accounted for 35.7%, students who eat snacks accounted for 63.2%, students who eat breakfast once to twice a week accounted for 30.6%, students who had an average number of drinks of once to twice a week accounted for 39.9%, and students with BMI of '$18.5^{\circ}{{\neq}}22.9$' accounted for 56.2%, being the highest. Secondly, in gender, smoking (p<.001), regular physical activity (p<.001), BMI (p<.001), eat snacks (p<.05), average number of drinks (p<.05), and of the health check-up, eat breakfast (p<.05), of the year level, eat snack (p<.01), BMI (p<.01), hours of sleep (p<.05), of major satisfaction, regular physical activity (p<.01), and BMI (p<.05), and there was a significant statistical difference, but there were no significant statistical difference in religion. Thirdly, of the bodily self-reported symptoms of the correlation analysis within the life-style variables and the self-reported symptoms, multiple subjective symptoms (I), respiratory (A), eye and skin (B), and digestive organs (C) were the highest in the correlation analysis with regular physical activity (p<.01), and of mental health, impulsiveness (H), mental instability (J), and depression (K) showed highest results in correlation analysis with regular physical activity (p<.01, p<.05), lie scale (L) and irregular and life (G) with eat breakfast (p<.01), and aggressiveness (F) with BMI (p<.01), showed highest results in correlation analysis. Fourthly of the Dental technology students' bodily self-reported symptoms, life-style factors which had a statistically significant effect appeared to be regular physical activity (p<.001) and BMI (p<.05), and of the mental self-reported symptoms, causes that did not have statistically significant effect appeared to be regular physical activity (p<.05) and eat breakfast (p<.05). Conclusion: This research concludes that in order to develop correct life-style habits for health promotion and reduce self-reported symptoms related to the Dental Technology students' diseases, education for the recognition of the necessity of self health promotion must be conducted, and a education programme scheme for the Dental technology curriculum for practicing the correct life-style habits in daily life is required.

• 유통과학연구
• /
• 제14권7호
• /
• pp.91-100
• /
• 2016

Purpose - Recently actively growing franchise systems distribution channel system in which franchise headquarter compared with franchise occupies an important place in distribution channel. Due to this, franchise and franchise headquarter are interdependent on task and in this situation the goal they go after, motivation and objective are probably inconsistent. If so, possibility to participate goal setting process or operating activity of opposite side is becoming bigger and in the end conflict may generate. The purpose of this study is to examine the role of the supervisor's attitude and expertise as moderating factors in the relationship between goal-incongruity/coercive power/role-incongruity and the conflict perceived by franchisee. Research design, data and methodology - This study was intended to verify how the supervisor's attitude and expertise as moderating factors in the relationship between goal-incongruity/coercive power/role-incongruity and the conflict perceived by franchisee. In order to achieve the purpose of this study, some study models and hypotheses have been established through theoretical examinations. Then, using these scales, the researcher completed the questionnaire survey. To test our hypotheses, the survey was conducted from March 9, 2016 for 20 days by random sampling, The study was implemented through a descriptive survey method using a self-administered questionnaire. A survey of 124 restaurant franchisee across Seoul and Gyeonggi Province was performed. A total of 124 completed responses were analyzed. In this study, I used SPSS 22.0 to analyze data and did frequency analysis to see demographic, and general features of the respondents; also did exploratory factor analysis to examine the validity of the items of measurement. Factor analysis was first calculated at a minimum, the number of factors, principal component analysis used when variables are committed to maximising the information with (principle component analysis) and the rotation of factors were angry about the great variable factors than 1.0 by applying Varimax rotation. In addition, I used the value of Cronbach's (Alpha) to examine the reliance of questionnaire items, final analysis the reliability factor can be found both high reliability hayeoteumeuro exceeds over 0.6 and did Multiple regression analysis to test hypothesis and also did hierarchical regression analysis to examine moderating effect. Results - To analyze the proposed model, according to the analysis result, it was found that the influence of goal-incongruity, coercive power, and role-incongruity on the perceived conflict of franchisee is moderated by the supervisor's attitude and expertise. That is, the more the supervisor's attitude and expertise were positive, the more the conflicts of the goal-incongruity, coercive power, and role-incongruity were decreased. It also confirmed previous research's finding that goal-incongruity, coercive power, and role-incongruity positively influence on the conflict. Conclusions - According to the results of this research which reduces the conflict of franchise from the in consistent goal; coercive power, and inconsistent role of superiors, it provides very important implications for franchise headquarter which has franchise system and also give them some suggestion about how to recruit superiors and what kind of training may be fit for the superiors.