• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.785-796
• /
• 2019

Due to the view point, illumination, personal gait and other background situation, person re-identification across cameras has been a challenging task in video surveillance area. In order to address the problem, a novel method called Joint Bayesian across different cameras for person re-identification (JBR) is proposed. Motivated by the superior measurement ability of Joint Bayesian, a set of Joint Bayesian matrices is obtained by learning with different camera pairs. With the global Joint Bayesian matrix, the proposed method combines the characteristics of multi-camera shooting and person re-identification. Then this method can improve the calculation precision of the similarity between two individuals by learning the transition between two cameras. For investigating the proposed method, it is implemented on two compare large-scale re-ID datasets, the Market-1501 and DukeMTMC-reID. The RANK-1 accuracy significantly increases about 3% and 4%, and the maximum a posterior (MAP) improves about 1% and 4%, respectively.

• Journal of Information Processing Systems
• /
• 제12권3호
• /
• pp.381-391
• /
• 2016

The Joint Bayesian (JB) method has been used in most state-of-the-art methods for face verification. However, since the publication of the original JB method in 2012, no improved verification method has been proposed. A lot of studies on face verification have been focused on extracting good features to improve the performance in the challenging Labeled Faces in the Wild (LFW) database. In this paper, we propose an improved version of the JB method, called the two-dimensional Joint Bayesian (2D-JB) method. It is very simple but effective in both the training and test phases. We separated two symmetric terms from the three terms of the JB log likelihood ratio function. Using the two terms as a two-dimensional vector, we learned a decision line to classify same and not-same cases. Our experimental results show that the proposed 2D-JB method significantly outperforms the original JB method by more than 1% in the LFW database.

• 디지털콘텐츠학회 논문지
• /
• 제16권5호
• /
• pp.671-680
• /
• 2015

Joint Bayesian 방법론[1]은 2012년 발표된 이후 최근까지 최고 성능을 보이는 거의 모든 얼굴인식 알고리즘에서 이진 분류를 위해 사용되고 있지만, 지금까지 이를 개선한 알고리즘은 2D-JB[2] 외에 거의 발표되지 않았다. 우리는 본 논문에서 주어진 얼굴 영상과 이를 좌우 반전시킨 미러 영상을 함께 고려함으로써 Joint Bayesian 방법론의 성능을 향상시킬 수 있는 방법론을 제안한다. 일반적인 패턴인식에서 결정함수 값이 결정경계 또는 임계치에 가까운 경우 오류가 발생할 확률이 높다. 제안한 방법론은 미러 영상의 특징을 이용하여 결정함수 값을 결정경계로부터 멀어지게 함으로써 오류를 줄이는 방법이다. 우리는 LFW DB를 이용한 실험을 통해 제안한 JB 개선 방법론이 기존 JB 방법론보다 1%이상 높은 인식률을 보임을 입증하였다. LFW DB를 이용한 기존 연구들에서 성능을 1% 높이기 위해 많은 학습데이터가 필요했음을 감안할 때, 제안한 방법론은 큰 의미가 있다고 볼 수 있다.

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.239-250
• /
• 2022

In many applications, we frequently encounter correlated multiple outcomes measured on the same subject. Joint modeling of such multiple outcomes can improve efficiency of inference compared to independent modeling. For instance, in developmental toxicity studies, fetal weight and number of malformed pups are measured on the pregnant dams exposed to different levels of a toxic substance, in which the association between such outcomes should be taken into account in the model. The number of malformations may possibly have many zeros, which should be analyzed via zero-inflated count models. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint modeling framework for continuous and count outcomes with excess zeros. In our model, zero-inflated Poisson (ZIP) regression model would be used to describe count data, and a subject-specific random effects would account for the correlation across the two outcomes. We implement a Bayesian approach using MCMC procedure with data augmentation method and adaptive rejection sampling. We apply our proposed model to dose-response analysis in a developmental toxicity study to estimate the benchmark dose in a risk assessment.

• International Journal of Concrete Structures and Materials
• /
• 제5권1호
• /
• pp.57-64
• /
• 2011

An extensive database has been constructed of reinforced concrete (RC) beam-column connection tests subjected to cyclic lateral loading. All cases within the database experienced joint shear failure, either in conjunction with or without yielding of longitudinal beam reinforcement. Using the experimental database, envelope curves of joint shear stress vs. joint shear strain behavior have been created by connecting key points such as cracking, yielding, and peak loading. Various prediction approaches for RC joint shear behavior are discussed using the constructed experimental database. RC joint shear strength and deformation models are first presented using the database in conjunction with a Bayesian parameter estimation method, and then a complete model applicable to the full range of RC joint shear behavior is suggested. An RC joint shear prediction model following a U.S. standard is next summarized and evaluated. Finally, a particular joint shear prediction model using basic joint shear resistance mechanisms is described and for the first time critically assessed.

• 한국소프트웨어감정평가학회 논문지
• /
• 제16권2호
• /
• pp.63-68
• /
• 2020

본 논문에서는 딥러닝 프레임워크 기반의 얼굴인증 시스템에 대하여 제안한다. 제안 시스템은 딥러닝 알고리즘을 활용하여 얼굴영역 검출과 얼굴 특징 추출을 수행하고, 결합베이시안 학습 모델을 이용하여 얼굴인증을 수행한다. 제안 얼굴인증 알고리즘에 대한 성능 평가는 다양한 얼굴 사진들로 구성된 데이터베이스를 이용하여 수행하였으며, 한 명에 대한 얼굴 영상은 2장으로 구성하였다. 또한 얼굴인증 실험은 딥 뉴럴 네트워크를 통한 2048차원의 특징과 그 유사성을 측정하기 위해 결합베이시안 알고리즘을 적용하였으며, 얼굴인증에 실패한 동일오율을 계산함으로써 성능평가를 수행하였다. 실험 결과, 딥러닝 특징과 결합베이시안 알고리즘을 사용한 제안 방법은 1.2%의 동일오율을 보였다.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2002년도 춘계 학술발표회 논문집
• /
• pp.67-72
• /
• 2002

A Bayesian testing procedure is proposed for assessment of bioequivalence in both mean and variance which ensures population bioequivalence under normality assumption. We derive the joint posterior distribution of the means and variances in a standard 2 ${\times}$ 2 crossover experimental design and propose a Bayesian testing procedure for bioequivalence based on a Markov chain Monte Carlo methods. The proposed method is applied to a real data set.

• Structural Engineering and Mechanics
• /
• 제27권4호
• /
• pp.439-456
• /
• 2007

Reinforced concrete (RC) joint shear strength models are constructed using an experimental database in conjunction with a Bayesian parameter estimation method. The experimental database consists of RC beam-column connection test subassemblies that maintained proper confinement within the joint panel. All included test subassemblies were subjected to quasi-static cyclic lateral loading and eventually experienced joint shear failure (either in conjunction with or without yielding of beam reinforcement); subassemblies with out-of-plane members and/or eccentricity between the beam(s) and the column are not included in this study. Three types of joint shear strength models are developed. The first model considers all possible influence parameters on joint shear strength. The second model contains those parameters left after a step-wise process that systematically identifies and removes the least important parameters affecting RC joint shear strength. The third model simplifies the second model for convenient application in practical design. All three models are unbiased and show similar levels of scatter. Finally, the improved performance of the simplified model for design is identified by comparison with the current ACI 352R-02 RC joint shear strength model.

• 한국경영과학회지
• /
• 제24권1호
• /
• pp.49-58
• /
• 1999

A new channel access function is proposed to enhance the performance of the Joint CDMA/PRMA. It is obtained in consideration of the number of terminals in reservation mode and the number of terminals in contention mode whose probability distribution is estimated by applying pseudo Bayesian approach. Simulation results show that the performance of the Joint CDMA/PRMA can be improved by applying new channel access function under voice-only traffic and mixed voice/random-data traffic.

• 한국산학기술학회논문지
• /
• 제15권5호
• /
• pp.2603-2609
• /
• 2014

기계시스템의 신뢰성 해석을 위해서는 기계시스템에 성능을 미치는 변수의 확률 분포와 파라미터를 결정하는 통계적 모델링은 반드시 필요하다. 하지만, 신뢰성 해석에서 상당수의 변수는 상관관계가 있음에도 불구하고 독립변수로 취급되거나 실험데이터 수가 부족하다는 이유로 통계 모델에 대한 잘못된 가정을 하는 경우가 많다. 본 연구에서는 베이지안 방법을 이용하여 상관관계를 갖는 데이터의 결합분포함수를 copula를 이용하여 모델링함으로써 적은 수의 데이터로부터 정확한 입력모델을 산정하는 방법을 제안하였으며, 방법의 검증을 위해 다양한 상관계수와 데이터 수에 대해 통계 시뮬레이션을 수행하였다. 그 결과 Bayesian방법은 상관계수가 낮아 후보함수가 유사하거나 샘플수가 적어 정확한 모델을 산정하기 어려운 경우에도 후보 copula 중 실제 copula와 가장 근사한 후보 copula를 선정하였다. 이러한 근사 후보 copula는 신뢰성 해석결과 역시 실제 copula 함수를 이용한 신뢰성 해석 결과와 유사한 결과를 가짐을 확인할 수 있으므로 베이지안 방법은 신뢰성 해석을 위해 정확한 통계모델링을 제공함을 알 수 있다.