• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.19-30
• /
• 2003

Spatiotemporal statistical models are used for analyzing space-time data in many fields, such as environmental sciences, meteorology, geology, epidemiology, forestry, hydrology, fishery, and so on. It is well known that classical spatiotemporal process modeling requires the estimation of space-time variogram or covariance functions. In practice, the estimation of such variogram or covariance functions are computationally difficult and highly sensitive to data structures. We investigate a Bayesian hierarchical model which allows the specification of a more realistic series of conditional distributions instead of computationally difficult and less realistic joint covariance functions. The spatiotemporal model investigated in this study allows both spatial component and autoregressive temporal component. These two features overcome the inability of pure time series models to adequately predict changes in trends in individual sites.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.194-202
• /
• 2019

Reliability analysis of the components frequently starts with the data that manufacturer provides. If enough failure data are collected from the field operations, the reliability should be recomputed and updated on the basis of the field failure data. However, when the failure time record for a component contains only a few observations, all statistical methodologies are limited. In this case, where the failure records for multiple number of identical components are available, a valid alternative is combining all the data from each component into one data set with enough sample size and utilizing the useful information in the censored data. The ROK Navy has been operating multiple Patrol Killer Guided missiles (PKGs) for several years. The Korea Multi-Function Control Console (KMFCC) is one of key components in PKG combat system. The maintenance record for the KMFCC contains less than ten failure observations and a censored datum. This paper proposes a Bayesian approach with a Dirichlet mixture model to estimate failure time density for KMFCC. Trends test for each component record indicated that null hypothesis, that failure occurrence is renewal process, is not rejected. Since the KMFCCs have been functioning under different operating environment, the failure time distribution may be a composition of a number of unknown distributions, i.e. a mixture distribution, rather than a single distribution. The Dirichlet mixture model was coded as probabilistic programming in Python using PyMC3. Then Markov Chain Monte Carlo (MCMC) sampling technique employed in PyMC3 probabilistically estimated the parameters' posterior distribution through the Dirichlet mixture model. The simulation results revealed that the mixture models provide superior fits to the combined data set over single models.

• 한국수자원학회논문집
• /
• 제55권8호
• /
• pp.589-601
• /
• 2022

가뭄은 자연적 현상이지만, 지역의 물리적 및 사회적 요소와 결합되어 피해가 발생한다. 특히, 각종 용수 공급 및 수요과 연관되어 사회 경제적으로 큰 피해를 야기시킨다. 비슷한 심도의 기상학적 가뭄에도 지역의 특성과 용수공급체계에 따라 실제로 발생하는 가뭄 피해는 다르다. 본 연구에서는 지역의 사회·경제적 인자와 용수공급체계를 고려하여 가뭄 위험도를 평가하였다. 노출성은 용수공급 과부족량을 나타내는 결합가뭄관리지수(JDMI)를 등급화하여 평가하였다. 취약성은 가뭄에 영향을 받는 10개의 사회·경제적 인자에 엔트로피, PCA 및 GMM를 적용하여 가중평균하여 평가하였다. 대응능력은 지역의 용수능력을 나타내는 인자들을 베이지안 네트워크에 적용하여 평가하였다. 위험도는 노출성, 취약성 및 대응능력을 통합하여 결정하였다. 용수공급 실패 사상의 발생 가능성을 의미하는 가뭄 노출성을 평가한 결과, 괴산군이 0.81로 가장 높게 나타났다. 가뭄 취약성의 경우, 대전광역시가 0.61로 매우 취약한 것으로 나타났다. 지역의 용수공급체계가 고려된 가뭄 대응능력을 평가한 결과, 세종시가 가뭄 대응능력이 가장 낮은 것으로 나타났다. 마지막으로 위험도를 평가한 결과, 청주시가 가장 높게 나타났다. 이러한 결과를 통해 가뭄에 대한 위험 및 취약 원인을 파악하였으며, 향후 지역의 특성을 고려한 가뭄 피해 저감 정책 마련이 가능하다.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.591-600
• /
• 2018

The probabilistic characterization of wind field characteristics is a significant task for fatigue reliability assessment of long-span railway bridges in wind-prone regions. In consideration of the effect of wind direction, the stochastic properties of wind field should be represented by a bivariate statistical model of wind speed and direction. This paper presents the construction of the bivariate model of wind speed and direction at the site of a railway arch bridge by use of the long-term structural health monitoring (SHM) data. The wind characteristics are derived by analyzing the real-time wind monitoring data, such as the mean wind speed and direction, turbulence intensity, turbulence integral scale, and power spectral density. A sequential quadratic programming (SQP) algorithm-based finite mixture modeling method is proposed to formulate the joint distribution model of wind speed and direction. For the probability density function (PDF) of wind speed, a double-parameter Weibull distribution function is utilized, and a von Mises distribution function is applied to represent the PDF of wind direction. The SQP algorithm with multi-start points is used to estimate the parameters in the bivariate model, namely Weibull-von Mises mixture model. One-year wind monitoring data are selected to validate the effectiveness of the proposed modeling method. The optimal model is jointly evaluated by the Bayesian information criterion (BIC) and coefficient of determination, $R^2$. The obtained results indicate that the proposed SQP algorithm-based finite mixture modeling method can effectively establish the bivariate model of wind speed and direction. The established bivariate model of wind speed and direction will facilitate the wind-induced fatigue reliability assessment of long-span bridges.

• Asia Marketing Journal
• /
• 제15권1호
• /
• pp.155-168
• /
• 2013

This study describes consumers' movie choices in conjunction with other group members and attempts to reassess the effect of the online word of mouth (WOM) source in a joint decision context. The tendency of many people to go to movies in groups has been mentioned in previous literature but there is no modeling research that studies movie choice from the group decision perspective. We found that ignoring the group movie-going perspective can result in a misunderstanding, especially underestimation of genre preference and the impact of the WOM variables. Most of the studies to measure online WOM effects were done at the aggregate level, and the role of online WOM variables(volume vs valence) is mixed in the literature. We postulate that group-level analysis might offer insight to resolve these mixed understanding of WOM effects in the literature. We implemented the study via a random effect model with group-level heterogeneity. Romance, drama, and action were selected as genre variables; valence and volume were selected as online WOM variables. A choice-based conjoint survey was used for data collection and the models was estimated via Bayesian MCMC method. The empirical results show that (i) both genre and online WOM are important variables when consumers choose movies, especially as group, and (ii) the WOM valence effect are amplified more than the volume effect does as individuals are engaged in group decision. This research contributes to the literature in several ways. First, we investigate movie choice from a group movie-going perspective that is more realistic and consistent with the market behavior. Secondly, the study sheds new light on the WOM effect. At group-level, both valence and volume significantly affect movie choices, which adds to the understanding of the role of online WOM in consumers' movie choice.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.49-56
• /
• 1999

In this paper, the general formula of disparity estimation based on Bayesian Maximum A Posteriori (MAP) algorithm is derived. The generalized formula is implemented with the plane configuration model and applied to multiple baselined stereograms. The probabilistic plane configuration model consists of independence and similarity among the neighboring disparities in the configuration. The independence probabilistic model reduces the computation and guarantees the discontinuity at the object boundary region. The similarity model preserves the continuity or the high correlation of disparity distribution. In addition, we propose a hierarchical scheme of disparity compensation in the application to multiple-view stereo images. According to the experiments, the derived formula and the proposed estimation algorithm outperformed other ones. The proposed probabilistic models are reasonable and approximate the pure joint probability distribution very well with decreasing the computations to O(n(D)) from O(n(D)4) of the generalized formula. And, the hierarchical scheme of disparity compensation with multiple-view stereos improves the performance without any additional overhead to the decoder.

• 한국수자원학회논문집
• /
• 제52권12호
• /
• pp.985-999
• /
• 2019

전 세계적으로 극심한 가뭄현상이 반복적으로 발생하고 있으며, 이러한 가뭄을 분석하기 위한 연구가 다수 진행되고 있다. 최근 코플라 함수를 활용한 이변량 가뭄빈도해석에 대한 연구가 다수 진행된 바 있으나, 대부분 지점빈도해석에 국한되어 진행되었으며, 통계적으로 부족한 자료의 기간을 보완하기 위한 대안으로 지역빈도해석 개념을 도입한 연구는 미진한 실정이다. 이러한 점에서 본 연구에서는 기존의 베이지안 기법과 코플라 함수를 연계한 이변량 지역빈도해석 모형을 개발하였다. 최종적으로 이변량 코플라 가뭄 지역빈도해석 모형을 한강유역에 적용하여 2013-2015년에 발생한 가뭄 사상을 평가하였으며, 기존에 개발된 이변량 지점빈도해석 결과와 비교를 통해 모형의 해석결과에 대한 신뢰성을 확보하였다. 결과적으로 이변량 지점빈도해석에 비해 가뭄사상에 대한 결합재현기간의 불확실성 구간이 약 3배 가까이 감소하였으며, DIC 통계량 산정결과 약 15 이상 개선된 것을 확인하였다. 본 연구를 통해 제안된 베이지안 코플라 기반 이변량 가뭄 지역빈도해석 모형은 가뭄자료의 분포특성 및 자료간의 상관성을 효과적으로 재현하는데 유리할 뿐만 아니라, 지역적인 가뭄특성을 효과적으로 평가할 수 있는 장점을 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제13권4호
• /
• pp.765-773
• /
• 2009

최근의 텔레매틱스 교통정보제공서비스는 지능형 교통시스템의 구축을 통한 실시간 교통정보 수집이 가능해짐에 따라 다양해지고 있다. 본 논문에서는 고품질의 다양한 교통정보제공을 위해 필요한 미래시간에 대한 단기 교통정보 예측 모델을 제안하고 개발하였다. 단기 예측 모델은 현재로부터 가까운 미래의 교통 상황을 예측하기 위한 교통 모델로 본 연구에서 제안한 예측 모델은 각 도로에 대하여 5분 이후부터 1시간 이전까지의 미래시간에 대한 차량 평균 속도를 예측 결과로 준다. 본 연구에서 제안한 예측 모델은 베이지안 네트워크에 기반을 두고 있으며 각 도로의 미래시간 교통상황에 영향을 줄 수 있는 요인들을 분석하여 베이지안 네트워크의 원인노드로 설정하였다. 설계된 베이지안 네트워크에 대하여 실시간 교통정보데이터를 이용하여 가우시안 혼합 분포를 가정한 베이지안 네트워크의 결합 확률 밀도 함수를 EM(Expectation Maximization) 알고리즘으로 구하여 미래시간의 교통정보를 예측하였다. 예측 모델의 정확도 검증을 위해 실시간 교통데이터로 다양한 실험을 수행하였다. 실험결과 제안된 모델은 현재 시간으로부터 10분 이후, 30분 이후, 60분 이후 예측 오차로 각각 4.5, 4.8, 5.2의 RMSE(Root Mean Square Error) 값을 주었다.

• 약학회지
• /
• 제39권2호
• /
• pp.103-112
• /
• 1995

Population pharmacokinetics for gentamicin were compared with 24 American patients (16 male and 8 female) and 16 Korean-American appendicitis patients(12 male and 4 female). Two to six blood specimens were collected from all patients at the following times: just before a regularly scheduled infusion and at 1/2 hour after the end of a 1/2 hour infusion. Nonparametric expected maximum(NPEM) algorithm for population modeling was used. The estimated parameters were the elimination rate constant(K), the slope of the relationship between K versus creatinine clearance(KS), the apparent volume of distribution(V), the slope of the relationship between V versus weight(VS), gentamicin clearance(CL) and the slope of the relationship between CL versus creatinine clearance and the VS(CS). The output includes a 3-dimensional plot of the joint probability density function(PDF), two marginal PDF, means, medians, modes, variance, skewness, kurtosis, and CV%. The mean K(KS) were 0.424$\pm$0.139(0.00429$\pm$0.00164) and 0.411$\pm$0.135 hr$^{-1}$ (0.00475$\pm$0.00180[hr.mL/min/1.73m$^{2}]^{-1}$) for American and Korean-American populations, respectively. The mean V(VS) were not different at 15.6$\pm$4.77(0.233$\pm$0.0526) and 15.1$\pm$3.84L(0.239$\pm$0.0492 L/kg) for American and Korean-American populations, respectively (P>0.2). The mean CL (CS) were 6.28$\pm$1.85(0.0634$\pm$0.0191) and 5.70$\pm$1.77 L/hr(0.0701$\pm$0.0215 L/kg[hr.mL/min/1.73m$^{2}$)] for American and Korean-American populations, respectively. There are no differences in gentamicin pharmacokinetics between American and Korean-American Appendicitis patients.