• 한국콘텐츠학회논문지
• /
• 제12권4호
• /
• pp.40-51
• /
• 2012

한국의 온라인 토론게시판은 의견 공유뿐 아니라 여론 형성과 참여를 위한 공간으로 활발히 사용되고 있다. 토론게시판에서 어떤 글은 사회적 정치적 이슈를 몰고 다니기도 하고 어떤 글은 사용자의 관심을 끌지 못하기도 한다. 본 논문에서는 한국의 유명 토론게시판인 다음 아고라와 서프라이즈에서 수집한 글의 통계적 정보를 이용하여 글의 인기를 분석하고 인기글을 예측하기 위한 예측모델을 제안한다. 분석결과 아고라는 87.52%의 글이 게시판에 제출된 후 하루가 지나기 전에 글의 인기가 끝나고 있었지만 서프라이즈는 39%의 글이 4일 이상 인기가 지속되고 있었다. 그렇지만 글의 인기기간과 조회수의 상관관계는 낮았다. 조회수 증가가 오랫동안 지속된다고 해서 최종 조회수가 높다는 것을 의미하지는 않는다. 본 논문에서는 분류와 예측 분야에서 잘 알려진 SVM 모델과 유사매칭 모델, 그리고 새롭게 제안한 예측 모델 '베이스 라인'을 이용하여 인기글을 예측하고 평가하였다. SVM 모델이 F-measure와 정밀도에서 유사매칭과 베이스라인보다 우수하였으며, 베이스라인이 실행시간에서 가장 우수한 성능을 보였다.

• Clinical and Experimental Reproductive Medicine
• /
• 제48권2호
• /
• pp.163-173
• /
• 2021

Objective: This study aimed to characterize a validated model for predicting oocyte retrieval in controlled ovarian stimulation (COS) and to construct model-based nomograms for assistance in clinical decision-making regarding the gonadotropin protocol and dose. Methods: This observational, retrospective, cohort study included 636 women with primary unexplained infertility and a normal menstrual cycle who were attempting assisted reproductive therapy for the first time. The enrolled women were split into an index group (n=497) for model building and a validation group (n=139). The primary outcome was absolute oocyte count. The dose-response relationship was tested using modified Poisson, negative binomial, hybrid Poisson-E_max, and linear models. The validation group was similarly analyzed, and its results were compared to that of the index group. Results: The Poisson model with the log-link function demonstrated superior predictive performance and precision (Akaike information criterion, 2,704; λ=8.27; relative standard error (λ)=2.02%). The covariate analysis included women's age (p<0.001), antral follicle count (p<0.001), basal follicle-stimulating hormone level (p<0.001), gonadotropin dose (p=0.042), and protocol type (p=0.002 and p<0.001 for short and antagonist protocols, respectively). The estimates from 500 bootstrap samples were close to those of the original model. The validation group showed model assessment metrics comparable to the index model. Based on the fitted model, a static nomogram was built to improve visualization. In addition, a dynamic electronic tool was created for convenience of use. Conclusion: Based on our validated model, nomograms were constructed to help clinicians individualize the stimulation protocol and gonadotropin doses in COS cycles.

• 한국도로학회논문집
• /
• 제16권4호
• /
• pp.111-118
• /
• 2014

PURPOSES: The purposes are to analyze the pedestrian accident severity and to develop the accident models by arterial road function. METHODS: To analyze the accident, count data and ordered logit models are utilized in this study. In pursuing the above, this study uses pedestrian accident data from 2007 to 2011 in Cheongju. RESULTS : The main results are as follows. First, daytime, Tue.Wed.Thu., over-speeding, male pedestrian over 65 old are selected as the independent variables to increase pedestrian accident severity. Second, as the accident models of main and minor arterial roads, the negative binomial models are developed, which are analyzed to be statistically significant. Third, such the main variables related to pedestrian accidents as traffic and pedestrian volume, road width, number of exit/entry are adopted in the models. Finally, Such the policy guidelines as the installation of pedestrian fence, speed hump and crosswalks with pedestrian refuge area, designated pedestrian zone, and others are suggested for accident reduction. CONCLUSIONS: This study analyzed the pedestrian accident severity, and developed the negative binomial accident models. The results of this study expected to give some implications to the pedestrian safety improvement in Cheongju.

• 응용통계연구
• /
• 제21권4호
• /
• pp.603-613
• /
• 2008

셀 수 있는 이산 자료 중에서 일반적인 모형에 비하여 영의 빈도가 과도하게 많이 관측되는 자료가 있다. 이러한 경우에 포아송 또는 음이항회귀모형과 같은 일반적인 회귀모형에 의한 분석은 적절하지 못하다. 본 논문에서는 영과잉 포아송회귀모형과 영과잉 음이항회귀모형에 대하여 베이지안 분석을 하였다. 또한, 마코브 연쇄 몬테카롤로 방법으로 계산한 베이즈 요인을 이용하여 모형선택을 하였다. 실제 교통사고 자료를 분석하여 이론적인 결과들을 뒷받침하였다.

• 한국대기환경학회지
• /
• 제15권6호
• /
• pp.757-765
• /
• 1999

Lagrangian particle dispersion model(LPDM) is an effective tool to calculate the dispersion from a point source since it dose not induce numerical diffusion errors in solving the pollutant dispersion equation. Fictitious particles are released to the atmosphere from the emission source and they are then transported by the mean velocity and diffused by the turbulent eddy motion in the LPDM. The concentration distribution from the dispersed particles in the calculation domain are finally estimated by applying a particle count method or a Gaussian kernel method. The two methods for calculating concentration profiles were compared each other and tested against the analytic solution and the tracer experiment to find the strength and weakness of each method and to choose computationally time saving method for the LPDM. The calculated concentrations from the particle count method was heavily dependent on the number of the particles released at the emission source. It requires lots fo particle emission to reach the converged concentration field. And resulting concentrations were also dependent on the size of numerical grid. The concentration field by the Gaussian kernel method, however, converged with a low particle emission rate at the source and was in good agreement with the analytic solution and the tracer experiment. The results showed that Gaussian kernel method was more effective method to calculate the concentrations in the LPDM.

• 디지털융복합연구
• /
• 제10권7호
• /
• pp.161-166
• /
• 2012

고속도로에서 교통사고가 발생하면 연쇄 추돌 사고를 예방하기 위해 주변 차량에게 안전 메시지를 브로드캐스트 해야 한다. 또한, 표본 개수의 증가는 메모리의 한계 때문에 추정치의 정확도가 낮은 문제점을 가진다. 본 논문에서는 가우시안 모델에 백오프 알고리즘을 적용한 RVC 시스템을 제안한다. 그리고 이웃 노드 개수의 수집 채널, 데이터 채널, RSU 통신 채널로 분리하여 통신 지연을 예방하는 MAC 프로토콜을 제안한다. 결과적으로, 기존 기법보다 제안된 프로토콜이 프레임 수신율의 약 10% 정도 개선되었음을 확인하였다.

• 대한산업공학회지
• /
• 제40권1호
• /
• pp.43-51
• /
• 2014

Statistical process control (SPC) is an important technique for monitoring and managing the manufacturing process. In spite of its easiness and effectiveness, some problematic sides of application exist such that the SPC techniques are hardly reflect the changes of the process conditions. Especially, update of control limits at the right time plays an important role in acquiring a reasonable performance of control charts. Therefore, we propose the control chart performance evaluation index (CPEI) based on count data model to monitor and manage the performance of control charts. The CPEI could indicate the degree of control chart performance and be helpful to detect the proper update cycle of control limits in real time. Experiments using real manufacturing data show that the proper update intervals are made by proposed method.

• Nuclear Engineering and Technology
• /
• 제50권7호
• /
• pp.1006-1016
• /
• 2018

Since the early forties, researchers from around the world have been studying the phenomenon of deadtime in radiation detectors. Many have attempted to develop models to represent this phenomenon. Two highly idealized models; paralyzable and non-paralyzable are commonly used by most individuals involved in radiation measurements. Most put little thought about the operating conditions and applicability of these ideal models for their experimental conditions. So far, there is no general agreement on the applicability of any given model for a specific detector under specific operating conditions, let alone a universal model for all detectors and all operating conditions. Further the related problem of pile-up is often confused with the deadtime phenomenon. Much work, is needed to devise a generalized and practical solution to these related problems. Many methods have been developed to measure and compensate for the detector deadtime count loss, and many researchers have addressed deadtime and pulse pile-up. The goal of this article is to summarize the state of science of deadtime; measurement and compensation techniques as proposed by some of the most significant work on these topics and to review the deadtime correction models applicable to present day radiation detection systems.

• Journal of the Korean Data and Information Science Society
• /
• 제26권2호
• /
• pp.387-397
• /
• 2015

본 연구에서는 청년인턴 DB와 고용보험 DB를 사용하여 중소기업 청년인턴의 이직횟수에 영향을 미치는 요인을 분석하였다. 이직횟수는 음수가 아닌 정수 값만 가지는 계수 데이터 (count data)이므로 일반적인 선형회귀모형을 적용하는 것은 문제가 있다. 따라서 계수 데이터에 적합한 회귀모형으로 포아송 회귀모형, 영과잉 포아송 회귀모형, 음이항 회귀모형, 영과잉 음이항 회귀모형 등 4개의 회귀모형을 적용하였다. 분석결과 최적모형으로 영과잉 음이항 회귀모형이 선택되었다. 주요 분석결과를 정리하면 다음과 같다. 첫째, 통제집단 (비인턴집단)에 비해서 처리집단 (인턴집단)이 통계적으로 유의하게 이직경험이 낮게 나타났다. 둘째, 연령이 작을수록 통계적으로 유의하게 이직경험이 낮게 나타났다. 셋째, 여자에 비해서 남자가 유의하게 이직횟수가 높게 나타났다. 마지막으로 기업규모가 클수록 이직횟수가 유의하게 감소하는 것으로 나타났다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권4호
• /
• pp.895-900
• /
• 2013

In this research, we propose a simple bivariate zero inflated negative binomial regression model with different dispersion for bivariate count data with excess zeros. An application to the demand for health services shows that the proposed model is better than existing models in terms of log-likelihood and AIC.