• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.289-292
• /
• 2008

Recently, several satellite data analyses projects and numerical weather prediction (NWP) reanalysis projects have produced the ocean surface Latent Heat Flux (LHF) data sets in the global coverage. Comparisons of these LHF data sets showed substantial discrepancies in the LHF values. Recently, the increase of LHF in during 1970s-1990s over the global ocean is shown by the LHF data that have been developed at the Objective Analyzed Air-Sea Fluxes (OAFlux) project. It is interesting to investigate the existence of the increase of LHF over a global ocean in the other LHF products. It is interesting to investigate the existence of the increase of LHF over a global ocean in the other LHF products. In this study, we assessed the consistencies and discrepancies of the inter-annual variability and decadal trend for the period 1988-2005 among six LHF products ((J-OFURO2, HOAPS3, IFREMER, NCEP1,2 and OAFlux) over the global ocean. As results, all LHF products showed a positive trend. In particular, the positive trend in satellite-based data analyses (J-OFURO2, HOAPS3, IFREMER) is larger than that in reanalysis products (NCEP1/2). Also, the consistencies and discrepancies are shown on the spatial patterns of the LHF trends across the six data sets. The positive trend of LHF is remarkable in the regions of western boundary currents such as the Kuroshio and the Gulf Stream in all LHF data sets. But, the discrepancies are shown on the spatial patterns of the LHF trends in tropics and subtropics. These discrepancies are primarily caused by the differences of the input meteorological state variables, particularly for the air specific humidity, used to calculate LHF.

• The Korean Journal of Applied Statistics
• /
• v.32 no.6
• /
• pp.837-849
• /
• 2019

Latent class models (LCM) are useful tools to draw hidden information from categorical data. This model can also be interpreted as a mixture model with multinomial component distributions. In some cases, however, an available dataset may contain both categorical and count or continuous data. For such cases, we can extend the LCM to a mixture model with both multinomial and other component distributions such as normal and Poisson distributions. In this paper, we consider a LCM for the data containing categorical and count data to analyze the Drug Review dataset which contains categorical responses and text review. From this data analysis, we show that we can obtain more specific hidden inforamtion than those from the LCM only with categorical responses.

• Environmental and Resource Economics Review
• /
• v.26 no.3
• /
• pp.287-317
• /
• 2017

Asbestos has been actively used for various places. Since it was designated as the first grade carcinogen in the 1970s, strict regulations on using asbestos has been implemented globally. Considering long-term latent periods between asbestos exposure and environmental diseases, we analyze the time lag between asbestos consumption and the incidence of mesothelioma in Korea and estimate the long-run relationship. In addition, we conduct a comparative analysis on the effectiveness of asbestos regulations in the United Kingdom and the United States, which have accumulated long-term time-series observations. The latent period analysis indicates that the consumption of asbestos and the incidence of the disease are highly correlated in all three countries, being long-term lags of more than 30 years. Also, we find a long-run equilibrium relationship between asbestos consumption and the incidence of mesothelioma in the presence of long-term lags between the variables in all three countries. Furthermore, using a distributed lag model, asbestos consumption has statistically significant positive effects on mesothelioma with a long-term lag.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.4
• /
• pp.793-802
• /
• 2013

There are many problems to single sports talents out of test applicants. The physical activity promotion system has been performed to all elements school students of both 5 and 6 grades in order to evaluate overall health and physical activities since 2009. This system includes some variables which could measure the students' sports latent power, so that the system could be used to single out sports talents. In this work, we propose a primary screening method that element school teachers might evaluate sports talents based on the data of the physical activity promotion system. Two more sports talent indices which are sports flexibility index and sports endurance index are defined. The selection method of sports talents is developed by using sports latent indices including sports power and cardiorespiratory indices. This method is efficient from the view of time and cost aspects, since we do not need to remeasure all elements school students again.

• Journal of The Korean Association For Science Education
• /
• v.31 no.6
• /
• pp.876-886
• /
• 2011

This study was carried out to investigate the difference of gender of academic self-efficacy, external motivation, interest and science achievement for high school students of Korea and to verify the structural relationship among these variables using PISA 2006 data. The major findings of this study are as follows. According to Multi-group analysis, Latent means analysis (LMA), where boys were used as the reference group, girls showed lower latent mean values on the academic self-efficacy, extrinsic motivation and interest. Academic self-efficacy was found to have a greater effect on achievement compared to external motivation and interest. According to structural equation modeling (SEM) analysis, academic self-efficacy and extrinsic motivation affected interest. Academic selfefficacy, external motivation, and interest affected science achievement. Lastly, interest mediated academic selfefficacy and external motivation on science achievement.

• Genomics & Informatics
• /
• v.11 no.2
• /
• pp.83-92
• /
• 2013

Genetic studies on facial morphology targeting healthy populations are fundamental in understanding the specific genetic influences involved; yet, most studies to date, if not all, have been focused on congenital diseases accompanied by facial anomalies. To study the specific genetic cues determining facial morphology, we estimated familial correlations and heritabilities of 14 facial measurements and 3 latent factors inferred from a factor analysis in a subset of the Korean population. The study included a total of 229 individuals from 38 families. We evaluated a total of 14 facial measurements using 2D digital photographs. We performed factor analysis to infer common latent variables. The heritabilities of 13 facial measurements were statistically significant (p < 0.05) and ranged from 0.25 to 0.61. Of these, the heritability of intercanthal width in the orbital region was found to be the highest ($h^2$ = 0.61, SE = 0.14). Three factors (lower face portion, orbital region, and vertical length) were obtained through factor analysis, where the heritability values ranged from 0.45 to 0.55. The heritability values for each factor were higher than the mean heritability value of individual original measurements. We have confirmed the genetic influence on facial anthropometric traits and suggest a potential way to categorize and analyze the facial portions into different groups.

• Journal of the Korean Regional Science Association
• /
• v.37 no.1
• /
• pp.15-27
• /
• 2021

This study investigates the difference in income trajectories of the working poor and the non-working poor and explains the effects of socio-demographic (marriage, education) and regional (living in large cities) factors on intergroup differences. We use Seoul Survey data collected between 2009-2018 and the latent growth modeling approach. It was found that the trajectory difference between groups was statistically significant. Since 2016, the income gap widened as the income of the working poor stagnated. The three variables included in this model better explained the income trajectory of the working poor compared to the working non-poor. In particular, the change in income growth rate was positively related to whether they live in large cities. This suggests the possibility that living in a large city would act as an economic premium for the working poor. It is necessary to conduct follow-up studies on urban premiums for the working poor.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.18 no.4
• /
• pp.127-140
• /
• 1991

The Primary purpose of this study is to investigate factors and variables which have significant effects on user satisfaction with recreational facilities in Taejong-Dae recreational complex, thereby establishing indices of planning and development of urban parks and open space. To test the causal models of this research, the date were gathered by self-administered questionnaires from 967 households in Pusan City which were selected by the multi-stage probability sampling methood. The analysis of the multi-stage primarily consists of two phase : The first analysis dealt exploratory factor analysis which identified major factors involved in satisfaction with recreational activities and facilities in Taejong-Dae recreational complex and the second analysis tested the fit of the causal models of this research by employing LISREL methodology. There are three advantages of using LISREL over other multivariate analysis methods : First, measurement error is allowed and calculated in LISREL, otherwise there is a risk of seriously misleading estimates of coefficients ; Second, LISREL deals with latent variables or unmeasured variables ; Third, it enables to test causal relations among variables. The factors analysis identified that five factors are involved in satisfaction with recreational facilities. The five factors of satisfaction with recreational facilities are space for repose and relaxation, active recreation facilities such as pool and zoo, physical exercise facility, convenience and maintenance facility, and linear facility, and linear facility for walking. The second phase analysis tested the fit of the causal models for satisfaction with recreational facilities to the data and identified statistically significant causal linkage among overall satisfaction with Taejong-Dae recreational complex, other endogenous factors and exogenous variables. Overall fits of both causal models were very good. Among endogenous factors, facility for repose and relaxation. linear facility for walking, active recreation facility, facility for convenience and maintenance were identified as having significant effects on overall satisfaction. Exogenous variables which have significant effects on endogenous variables wer also identified. These significant relationships indicate important factors and variables that should be considered in planning and development of the recreational complex. On the basis of these significant causal relationships, implications for planning and the delovepment of Taejong-Dae recreational complex were suggested.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.4
• /
• pp.1424-1440
• /
• 2015

It is a challenging problem to search the intended images from a large number of candidates. Content based image retrieval (CBIR) is the most promising way to tackle this problem, where the most important topic is to measure the similarity of images so as to cover the variance of shape, color, pose, illumination etc. While previous works made significant progresses, their adaption ability to dataset is not fully explored. In this paper, we propose a similarity learning method on the basis of probabilistic generative model, i.e., probabilistic latent semantic analysis (PLSA). It first derives Fisher kernel, a function over the parameters and variables, based on PLSA. Then, the parameters are determined through simultaneously maximizing the log likelihood function of PLSA and the retrieval performance over the training dataset. The main advantages of this work are twofold: (1) deriving similarity measure based on PLSA which fully exploits the data distribution and Bayes inference; (2) learning model parameters by maximizing the fitting of model to data and the retrieval performance simultaneously. The proposed method (PLSA-FK) is empirically evaluated over three datasets, and the results exhibit promising performance.