• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• 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.

• Journal of The Korean Association For Science Education
• /
• v.17 no.3
• /
• 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
• /
• v.18 no.4
• /
• 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
• /
• v.14 no.2
• /
• pp.157-176
• /
• 2012

Brand switching data frequently used in market structure analysis is adequate to analyze non- durable goods, because it can capture competition between specific two brands. But brand switching data sometimes can not be used to analyze goods like automobiles having long term duration because one of main assumptions that consumer preference toward brand attributes is not changed against time can be violated. Therefore a new type of data which can precisely capture competition among durable goods is needed. Another problem of using brand switching data collected from actual purchase behavior is short of explanation why consumers consider different set of brands. Considering above problems, main purpose of this study is to analyze market structure for durable goods with consideration set. The author uses exploratory approach and latent class clustering to identify market structure based on heterogeneous consideration set among consumers. Then the relationship between some factors and consideration set formation is analyzed. Some benefits and two demographic variables - age and income - are selected as factors based on consumer behavior theory. The author analyzed USA automotive market with top 11 brands using exploratory approach and latent class clustering. 2,500 respondents are randomly selected from the total sample and used for analysis. Six models concerning market structure are established to test. Model 1 means non-structured market and model 6 means market structure composed of six sub-markets. It is exploratory approach because any hypothetical market structure is not defined. The result showed that model 1 is insufficient to fit data. It implies that USA automotive market is a structured market. Model 3 with three market structures is significant and identified as the optimal market structure in USA automotive market. Three sub markets are named as USA brands, Asian Brands, and European Brands. And it implies that country of origin effect may exist in USA automotive market. Comparison between modal classification by derived market structures and probabilistic classification by research model was conducted to test how model 3 can correctly classify respondents. The model classify 97% of respondents exactly. The result of this study is different from those of previous research. Previous research used confirmatory approach. Car type and price were chosen as criteria for market structuring and car type-price structure was revealed as the optimal structure for USA automotive market. But this research used exploratory approach without hypothetical market structures. It is not concluded yet which approach is superior. For confirmatory approach, hypothetical market structures should be established exhaustively, because the optimal market structure is selected among hypothetical structures. On the other hand, exploratory approach has a potential problem that validity for derived optimal market structure is somewhat difficult to verify. There also exist market boundary difference between this research and previous research. While previous research analyzed seven car brands, this research analyzed eleven car brands. Both researches seemed to represent entire car market, because cumulative market shares for analyzed brands exceeds 50%. But market boundary difference might affect the different results. Though both researches showed different results, it is obvious that country of origin effect among brands should be considered as important criteria to analyze USA automotive market structure. This research tried to explain heterogeneity of consideration sets among consumers using benefits and two demographic factors, sex and income. Benefit works as a key variable for consumer decision process, and also works as an important criterion in market segmentation. Three factors - trust/safety, image/fun to drive, and economy - are identified among nine benefit related measure. Then the relationship between market structures and independent variables is analyzed using multinomial regression. Independent variables are three benefit factors and two demographic factors. The result showed that all independent variables can be used to explain why there exist different market structures in USA automotive market. For example, a male consumer who perceives all benefits important and has lower income tends to consider domestic brands more than European brands. And the result also showed benefits, sex, and income have an effect to consideration set formation. Though it is generally perceived that a consumer who has higher income is likely to purchase a high priced car, it is notable that American consumers perceived benefits of domestic brands much positive regardless of income. Male consumers especially showed higher loyalty for domestic brands. Managerial implications of this research are as follow. Though implication may be confined to the USA automotive market, the effect of sex on automotive buying behavior should be analyzed. The automotive market is traditionally conceived as male consumers oriented market. But the proportion of female consumers has grown over the years in the automotive market. It is natural outcome that Volvo and Hyundai motors recently developed new cars which are targeted for women market. Secondly, the model used in this research can be applied easier than that of previous researches. Exploratory approach has many advantages except difficulty to apply for practice, because it tends to accompany with complicated model and to require various types of data. The data needed for the model in this research are a few items such as purchased brands, consideration set, some benefits, and some demographic factors and easy to collect from consumers.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1998.03a
• /
• 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
• /
• v.20 no.6
• /
• 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
• /
• v.27 no.4
• /
• 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.

• Journal of Families and Better Life
• /
• v.19 no.6
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.899-910
• /
• 2023

The majority of research on lifestyle has been conducted based on a variable-centered approach. However, over the last decades, there is a growing body of research on lifestyle in terms of a person-centered approach. Hence, this study identifies senior generations' profiles based on the combination of the five realms of lifestyle. More specifically, this study utilized a Latent profile analysis(LPA) to explore both quantitatively and qualitatively distinct types of senior generation' lifestyle profiles. As a result, the five distinct types of senior lifestyle profiles were identified and these five profiles were then contrasted with traveling attitude and behavioral intention(traveling intention). In addition, this study attempted to identify similarity in the patterns of relations with theoretical antecedent, correlate and outcome variables. Results showed that even though senior generation belonging to profile groups pertaining to the high level of all five types of lifestyle were associated with a high level of attitude and behavior intention, there was no differences among the profiles. This means that regardless of the patterns of senor generation lifestyle profiles, there was no similarity. Nevertheless, it should be considered that senior generation consider a security when making a travel ling decision regardless of the patterns of lifestyle profiles. This results suggest that senior generation' traveling satisfaction is more likely obtained with the experience of safety and convenience during their travel. At last, this study discusses some implication tourism theory related to lifestyle, practices and future research on tourism profiles.