• Journal of Korea Water Resources Association
• /
• v.52 no.9
• /
• pp.589-601
• /
• 2019

Various applications of radar rainfall data have been actively employed in the field of hydro-meteorology. Since radar rainfall is estimated by using predefined reflectivity-rainfall intensity relationships, they may not have sufficient reproducibility of observations. In this study, a generalized linear model is introduced to better capture the Z-R relationship in the context of bias correction within a Bayesian regression framework. The bias-corrected radar rainfall with the generalized linear model is more accurate than the widely used mean field bias correction method. In addition, we analyzed variability of the bias correction parameters under various geomorphological conditions such as the height of the weather station and the separation distance from the radar. The identified relationship is finally used to derive a regionalized formula which can provide bias correction factors over the entire watershed. It can be concluded that the bias correction parameters and regionalized method obtained from this study could be useful in the field of radar hydrology.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.2
• /
• pp.183-194
• /
• 1997

In accelerated life tests, the failure time of an item is observed under a high stress level and based on the time, the failure rates of items we estimated at the normal stress level. In this paper, when the mean of the prior distribution of a parameter is known in Weibull lifetime model with censored failure time data, we study various estimating methods to obtain the empirical Bayes estimator of a parameter from the empirical Bayes approach under the normal stress level by considering the fact that the Bayes estimator is the function of prior parameters and of the acceleration parameter representing the effect of acceleration. And we compare the performance of several empirical Bayes estimators of a parameter in terms of the Bayes risk.

• Journal of Convergence for Information Technology
• /
• v.10 no.9
• /
• pp.229-236
• /
• 2020

The purpose of this study was to investigate the current status of unmet medical need using data from the Korea Health Panel study from 2009 to 2013 (excluding 2010), and to analyze the trends of unmet medical need and related factors. The subjects of this study were 11,598 in 2009, 11,035 in 2011, 10,584 in 2012, 10,099 in 2013, and 7,144 people in panel data, and conducted frequency analysis, chi-square test and generalized estimating equation. As a result of the analysis by year, it was found that women, under middle school graduation, medical aid, the lowest household income and low subjective health status experienced more unmet medical need. As a result of analysis using generalized estimating equation, women, under 40 years of age, under elementary school graduation, lowest quartile household income, subjective health status of less than 20 points, and activity restrictions are more likely to experience unmet medical need. Based on these results, we intend to provide basic data for establishing policies on the use of medical services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.1
• /
• pp.25-31
• /
• 2014

Korean grammar checkers typically detect context-dependent errors by employing heuristic rules; these rules are formulated by language experts and consisted of lexical items. Such grammar checkers, unfortunately, show low recall which is detection ratio of errors in the document. In order to resolve this shortcoming, a new error-decision rule-generalization method that utilizes the existing KorLex thesaurus, the Korean version of Princeton WordNet, is proposed. The method extracts noun classes from KorLex and generalizes error-decision rules from them using the Tree Cut Model and information-theory-based MDL (minimum description length).

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.403-406
• /
• 2002

휴대폰의 일반화와 이것의 음향변환기로 사용되는 초소형 스피커 (Micro-speaker) 수요의 증가에 따라 휴대폰의 다양한 기능 및 성능의 개발에 대한 초소형 스피커의 성능개선이 절실히 요구된다. 특히, 초소형 스피커에서 발생된 음의 명료도와 음의 방사효율에 관한 특성의 개선은 당면한 문제이다. 본 연구에서는 초소형 스피커 전면에 진동판 보호를 위해 부착되어 있는 전면 덮개(Front Cover)를 스피커의 명료도와 효율에 관련된 음향적 기구로서 고려하여 일반 휴대폰에 사용되고 있는 초소형 스피커들을 대상으로 전면덮개에 가공된 기공의 면적에 따른 음파의 투과손실을 측정하였다. 또한, 전면덮개와 초소형 스피커 진동판 사이에 존재하는 체적과 전면 덮개의 기공에 대한 음향 임피던스(Acoustic Impedance)를 이론적인 방법으로 구하여 이에 따른 투과손실(Transmission Loss) 및 공명특성을 예측하고 이를 스피커들에 대한 투과손실 측정 결과와 비교하였다. 본 연구의 결과는 초소형 스피커를 제조하는 기업들이 경험적인 방법을 벗어나, 이론적 근거를 바탕으로 제품설계를 수행하는데 기여할 것으로 사료된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.491-491
• /
• 2021

댐·보 운영은 과거부터 많은 양의 데이터를 근간으로 분석 및 의사결정을 진행하였으나, 자연 현상의 복잡성 및 다양한 영향 관계로 인해 기술개발은 답보 상태에 머물러 있다. 또한 댐·보 운영의 기술개발은 개별적인 일부 요소기술에 국한되어 있는 실정으로 댐·보 운영의 전체 의사결정체계에 대한 미래의 방향성에 대한 전략이 부재한 상황이다. 이에 기후변화, 물관리일원화, 환경대응용수의 활용, 복합적 제약사항 도출 등 최적 댐·보 운영을 위한 의사결정지원 고도화에 대한 사회적 니즈가 증가를 반영하고, 기존의 재래적 의사결정지원 시스템 및 홍수분석기술에서 탈피하여 AI, Big Data 등 혁신 기술적용 및 최신기술 트렌드를 반영한 미래 물관리 로드맵의 제시가 필요한 상황이다. 본 연구의 목적은 홍수기 댐운영을 위해 기존 반복 분석하는 일련의 절차 자동화와 운영자의 경험에 따라 달라지는 운영방법의 일반화를 위한 AI의 도입에 있다. 기존 홍수분석체계를 살펴보면 저수지 홍수분석, 저수지 수위계산, 방류량 결정, 분석결과와 제약사항의 비교 같은 일련의 절차에 대해서 합리적인 결과가 도출될 때까지 반복 분석을 수행하여야 한다. 분석모형간 연계와 재래적 방법의 자동화를 도입하면 홍수분석에 소요되는 시간을 줄일 수 있어, 사전에 대비할 수 있는 시간을 추가적으로 확보할 수 있게 된다. 또한 홍수기 댐운영 방법이 운영자의 경험에 의존하다 보니 운영자마다 다른 운영방법을 도출하게 되는데, 과거사례의 최적 운영방안을 학습시킨 AI를 도입하게 되면 일관성있는 최적 댐운영이 가능할 것으로 판단된다. 이에 본 연구에서는 홍수분석 절차의 자동화, DB 및 통계모형 구축, 분석결과 및 제약사항의 직관적인 표출화, AI 도입을 통한 운영방안의 일반화 등 기존 재래기술의 개선을 통해 최적 댐운영 의사결정지원시스템의 고도화를 추진하고자 한다.

• Journal for History of Mathematics
• /
• v.25 no.2
• /
• pp.57-70
• /
• 2012

In this study, a teaching unit for mathematically gifted students is designed, based on Lakatos's perspective. First, students appreciated the exceptions of Desargue theorem and introduced the point at infinity to remove the exceptions. Finally students were guided to realize that the exceptions and the general case of Desargue theorem have equal status. Exploring Desargue theorem with other viewpoints, gifted students experienced the growth of mathematical knowledge due to exceptions of the theorem.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.401-409
• /
• 2020

The purpose of this study is to develop a convergence inpatient medical service patient experience management model(IMSPEMM) that can help in the management strategy of a medical institution to create a patient-centered medical culture. Using the original data from the 2018 Medical Service Experience Survey, 593 people with medical services inpatient(MSI) over the age of 15 were analyzed. By using the decision tree model, we developed a prediction model for overall satisfaction(OS) with the inpatient medical service experience(IMSE) and the intention to recommend patient experience(RI), and were classified into 4 and 7 types. The accuracy of the model was 68.9% and 78.3%. The OS level of IMSE was the nurse area and the hospital room noise management area, and the RI decision factor was the nurse area. It is significant that the IMSPEMM for MSI was presented and confirmed that the nurse area and the noise management area of the hospital room are important factors for the inpatient experience. It is considered that further research is needed to generalize the IMSPEMM.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.326-338
• /
• 2003

The objective of a neural network design and model selection is to construct an optimal network with a good generalization performance. However, training data include noises, and the number of training data is not sufficient, which results in the difference between the true probability distribution and the empirical one. The difference makes the teaming parameters to over-fit only to training data and to deviate from the true distribution of data, which is called the overfitting phenomenon. The overfilled neural network shows good approximations for the training data, but gives bad predictions to untrained new data. As the complexity of the neural network increases, this overfitting phenomenon also becomes more severe. In this paper, by taking statistical viewpoint, we proposed an integrative process for neural network design and model selection method in order to improve generalization performance. At first, by using the natural gradient learning with adaptive regularization, we try to obtain optimal parameters that are not overfilled to training data with fast convergence. By adopting the natural pruning to the obtained optimal parameters, we generate several candidates of network model with different sizes. Finally, we select an optimal model among candidate models based on the Bayesian Information Criteria. Through the computer simulation on benchmark problems, we confirm the generalization and structure optimization performance of the proposed integrative process of teaming and model selection.

• The Journal of the Convergence on Culture Technology
• /
• v.1 no.2
• /
• pp.53-64
• /
• 2015

The purpose of this study was to analyze the smoking experience and attitude including affect factors to smoking for elementary schoolers. The cross-sectional descriptive study design was used. We selected 810 students from 14 elementary school located in Chungchung-do and Gangwon-do by convenience random sampling and received IRB from Y Univ. 810 students were included in the final analysis using generalized linear model. Among 810 students, 7.3% of students reported to have smoking experience. The result of analyzing the smoking affect factors for smoking students who were having friends who had smoking experience, unable to smoking suggestion and those who were male, had significantly more smoking experience. According to the results of this study, there should be an intensive tailed smoking related program development for male elementary students, especially for smokers who have smoking friend and including smoking refusing program. And the school system services of elementary school should be strengthened to protect the elementary students from further the critical situation caused by smoking experience.