• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2527-2545
• /
• 2016

Measuring the similarity of given samples is a key problem of recognition, clustering, retrieval and related applications. A number of works, e.g. kernel method and metric learning, have been contributed to this problem. The challenge of similarity learning is to find a similarity robust to intra-class variance and simultaneously selective to inter-class characteristic. We observed that, the similarity measure can be improved if the data distribution and hidden semantic information are exploited in a more sophisticated way. In this paper, we propose a similarity learning approach for retrieval and recognition. The approach, termed as LDA-FEK, derives free energy kernel (FEK) from Latent Dirichlet Allocation (LDA). First, it trains LDA and constructs kernel using the parameters and variables of the trained model. Then, the unknown kernel parameters are learned by a discriminative learning approach. The main contributions of the proposed method are twofold: (1) the method is computationally efficient and scalable since the parameters in kernel are determined in a staged way; (2) the method exploits data distribution and semantic level hidden information by means of LDA. To evaluate the performance of LDA-FEK, we apply it for image retrieval over two data sets and for text categorization on four popular data sets. The results show the competitive performance of our method.

• 한국과학교육학회지
• /
• 제17권3호
• /
• pp.301-311
• /
• 1997

The purpose of this study is to construct a structural equation model and to analyze causal relationships among variables related to attitudes to science using structural equation modeling(SEM) with LISREL VII. The sample consisted of 483 10th grade boys from a general high school in Pusan, Korea. The questionnaires (ABC-attitude scale: affection, behavioral intention, cognition scale of attitude towards science) were developed by the researcher through a pilot study. And other instruments have modified previous ones. Five instruments were used in this study: GALT(group assessment of logical thinking), MTSlS(modified test of science inquiry skill), ABC-attitude scale, MSAS(modified scientific attitude scale), CSAT(common science achievement test). Structural equation modeling with LISREL VII($J\ddot{o}reskog$ & $S\ddot{o}rbom,$ 1993) was employed to estimate the causal inferences about hypothesized relationships among observed data sets. Three competing models consisted of five latent variable(scientific thinking ability, science inquiry skill, attitude towards science, scientific attitude, science achievement) - lP(inquiry preceding) model, AP(attitude preceding) model and AM(attitude mediating) model - were developed. Among these competing models, IP model satisfied the observed data sets. The causal relationships among "attitudes to science" and other latent variables were reliably identified. According to the results of the present study, science inquiry skill was the most significant variable that can predict science achievement. But scientific thinking ability has not directly influenced science achievement. This study suggests that inquiry based teaching-learning processes should be offered to students for improvement of science achievement. At the same time, it seems to be important to develop positive attitude towards science. Understanding of relationships among variables related to attitudes to science will be helpful to the development of science curriculum and to the design of science teaching and learning process. LISREL has been recognized as a useful approach in testing a SEM. However, in this study, LISREL approach was estimated as much more useful method for research design.

• Journal of Information Technology Applications and Management
• /
• 제18권4호
• /
• pp.169-181
• /
• 2011

The study developed the ideas of innovation resistance attitude in view of innovation delay, rejection, and objection. Authors developed the idea of innovation resistance attitudes of customers in view of innovation diffusion process. The study categorized the idea of resistance such as delay, rejection, and objection. The study hired the structural equation modeling to evaluate the relationships among the consumers' subjective variables such as incongruence, uncertainty, perceived performance, peer usage, and tradition orientation those were factored out by the survey test. These measured variables were analyzed into the innovation resistance related latent variables. The study provides the basic treatment to introduce new technologies and products to the superficially resisting customers. Those resisting customers might be future late adopters. The research results provide the basic arguments for prerequisite treatment to introduce smart phone in the global market place.

• Asia Marketing Journal
• /
• 제14권2호
• /
• pp.157-176
• /
• 2012

시장구조 분석에서 흔히 사용되는 상표전환 자료는 비내구재 분석에 적절한 방법이 될 수 있으나 자동차 같이 사용연한이 장시간인 내구재의 경우에는 소비자의 상표에 대한 선호도가 변할 수 있어 상표전환 자료의 사용에 문제가 있다. 따라서 경쟁을 잘 포착할 수 있는 다른 접근이 필요하다. 본 연구는 이에 대한 대안으로 상표간 경쟁 자료로써 고려상표군을 이용하여 자동차 시장의 구조를 Latent Class 군집분석을 활용한 탐색적 검증방법으로 분석하였다. 또한 소비자 행동분석에 근거하여 상표간 경쟁의 근간을 이루는 고려상표군 형성에 영향을 미치는 인자들을 밝히는데 중점을 두었다. 미국 자동차 시장을 대상으로 분석한 결과, 시장은 상표 원산지 효과에 의해 구분되었다. 즉, 미국 상표, 유럽 상표, 그리고 아시아 상표 등으로 시장이 구분되었다. 또한 각 시장구조 내 소비자들의 고려상표군 형성에 신뢰성/안전, 이미지/즐거움, 경제성 등의 편익과 성별, 소득 등 개인적 요인이 영향을 미치는 것으로 나타났다.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1998년도 춘계학술대회논문집
• /
• pp.179-184
• /
• 1998

Semi-solid forging can be applied in industry only with enough knowledge of the effects of the forming parameters related with the process and their exact control which can be obtained by empirical or numerical methods. In the current study, the effects of process variables on semi-solid forging are discussed based on mainly numerical results. Die preheating temperature, initial solid fraction of the workpiece, and die velocity were selected as process variables, and numerical analyses using a rigid-thermoviscoplastic finite element approach that considered the release of latent heat due to phase change were carried out. In the analyses, a proposed flow stress material characterization and a solid fraction updating algorithm were employed. The obtained results from numerical analysis are discussed and are compared with some experimental observations.

• Communications for Statistical Applications and Methods
• /
• 제20권6호
• /
• pp.439-454
• /
• 2013

This study presents a Bayesian multiple change-point detection approach to segment and classify the observations that no longer come from an initial population after a certain time. Inferences are based on the multiple change-points in a sequence of random variables where the probability distribution changes. Bayesian multiple change-point estimation is classifies each observation into a segment. We use a truncated Poisson distribution for the number of change-points and conjugate prior for the exponential family distributions. The Bayesian method can lead the unsupervised classification of discrete, continuous variables and multivariate vectors based on latent class models; therefore, the solution for change-points corresponds to the stochastic partitions of observed data. We demonstrate segmentation with real data.

• Journal of the Korean Statistical Society
• /
• 제27권4호
• /
• pp.407-420
• /
• 1998

This paper is concerned with selecting covariates to be included in building linear random effects models designed to analyze clustered response normal data. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting premising subsets of covariates. The approach reformulates the linear random effects model in a hierarchical normal and point mass mixture model by introducing a set of latent variables that will be used to identify subset choices. The hierarchical model is flexible to easily accommodate sign constraints in the number of regression coefficients. Utilizing Gibbs sampler, the appropriate posterior probability of each subset of covariates is obtained. Thus, In this procedure, the most promising subset of covariates can be identified as that with highest posterior probability. The procedure is illustrated through a simulation study.

• 가정과삶의질연구
• /
• 제19권6호
• /
• pp.145-155
• /
• 2001

The purposes of this study were first to construct statistical and econometric models based on Amemiya\`s Type I Tobit mainly addressing the issue of statistical efficiency; second to explore income, price, and curvilinear age effects on the explained variable in order to illustrates its statistical marginal effects related to econometric issues; finally to provide invaluable insight for graphical simulations as a new interpretation approach using Tobit analysis. Results indicated that interpretation for the mean marginal effects of three possible cases of dependent variable was more likely to be evident to understand Tobit results compared to conventional analysis only using latent variable, beta. Results also revealed that prediction value of dependent variable can be possibly and easily projected by the independent variable changed whereas only beta value can not illustrate its projection as independent variables'changes.

• 산업경영시스템학회지
• /
• 제36권4호
• /
• pp.64-70
• /
• 2013

Estimation approaches for casual relation model with high-order factors have strict restrictions or limits. In the case of ML (Maximum Likelihood), a strong assumption which data must show a normal distribution is required and factors of exponentiation is impossible due to the uncertainty of factors. To overcome this limitation many PLS (Partial Least Squares) approaches are introduced to estimate the structural equation model including high-order factors. However, it is possible to yield biased estimates if there are some differences in the number of measurement variables connected to each latent variable. In addition, any approach does not exist to deal with general cases not having any measurement variable of high-order factors. This study compare several approaches including the repeated measures approach which are used to estimate the casual relation model including high-order factors by using PLS (Partial Least Squares), and suggest the best estimation approach. In other words, the study proposes the best approach through the research on the existing studies related to the casual relation model including high-order factors by using PLS and approach comparison using a virtual model.

• 문화기술의 융합
• /
• 제9권6호
• /
• pp.899-910
• /
• 2023

전 세계를 비롯해 우리나라에서도 시니어세대는 지속적으로 증가하고 있으며, 여가활동에 대한 희망도 동시에 증가하여 지속적으로 관광을 희망하고 있는 것으로 나타나고 있다. 시니어세대는 관광 산업이 지속적으로 성장할 수 있는 원동력의 역할을 담당할 것이다. 본 연구는 시니어세대의 라이프스타일에 따른 관광 태도 및 관광 행동의향을 파악하기 위해 사람중심접근법(person-centered approach)을 토대로 잠재프로파일분석(LPA)을 실행하여 시니어세대의 라이프스타일 프로파일 유형을 탐색하고, 라이프스타일 프로파일 유형별 관광 태도 및 관광 행동의향의 차이점이 있는지를 실증 분석하였다. 시니어세대의 라이프스타일은 안전추구, 문화활동추구, 지식추구, 건강추구, 사회활동추구의 5개 요인으로 분류되었고, 안전추구를 비롯한 모든 요인에서 다른 프로파일들에 비해 높은 값을 나타낸 프로파일 3 집단에서 관광태도와 관광행동의향이 가장 높은 것으로 나타났다. 본 연구는 시니어세대의 관광행동 차이의 관계적 특성을 다면적으로 파악하였고, 관광업계에서 중요하게 세분시장으로 형성되고 있는 시니어세대의 이해를 통해 관광소비행동 마케팅 전략 수립에 유용한 시사점을 제공하였다는 점에서 의의가 있다.