• The Korean Journal of Applied Statistics
• /
• v.29 no.3
• /
• pp.487-503
• /
• 2016

Urban-to-rural migration for farming has recently emerged as a new way to vitalize rural economies in a fast-aging rural Korea. In this paper, we analyze the 2013 data of returning farmers with statistical network methods. We identify urban to rural migration hubs with centrality measures and find migration trends based on regional clusters with similar features via statistical network models. We also fit a latent distance model to investigate the role of distance in migration.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.61-68
• /
• 2015

In recent times, the median filtering (MF) detector as a forensic tool for the recovery of forgery images' processing history has concerned broad interest. For the classification of MF image, MF detector should be designed with smaller feature set and higher detection ratio. This paper presents a novel method for the detection of MF in altered images. It is transformed from BMP to several kinds of MF image by the median window size. The difference distribution values are computed according to the window sizes and then the values construct the feature set same as the MF window size. For the MF detector, the feature set transformed to the model specification which is computed using latent growth modeling (LGM). Through experiments, the test image is classified by the discriminant into two classes: the true positive (TP) and the false negative (FN). It confirms that the proposed algorithm is to be outstanding performance when the minimum distance average is 0.119 in the confusion of TP and FN for the effectivity of classification.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.211-216
• /
• 2021

This study intended to test the structure of the latent factor of a subjective happiness scale and the stability of invariance across groups of students' classifications (gender and students' status). In the large, non-clinical sample (619), students completed the subjective happiness scale. The (CFA) confirmatory factor analysis was used to investigate the factor-structure of the measure, and multiple-group confirmatory factor analysis (MGCFA) model was used to test the stability of invariance across groups of students classifications. The findings of the CFA indicated support for the original one-factor model. Additional analyses of the MGCFA method support the measurement (configural, metric and strong) invariant and practical invariant components of this model. There was an invariant across gender. There was partially invariant across groups of students' statuses. The scale exists in both groups to assess the same concepts of (single and married), excluding Items 3 and 4. Given that this study is the first investigation for the structure of the subjective happiness scale.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12
• /
• pp.149-156
• /
• 2021

This study intended to test the structure of the latent factor of an effectiveness scale and the stability of invariance across groups of students' classifications (gender and levels of education). In the large, non-clinical sample (850), students completed the effectiveness scale. The (CFA) confirmatory factor analysis was used to investigate the factor-structure of the measure, and multiple-group confirmatory factor analysis (MGCFA) model was used to test the stability of invariance across groups of students' classifications. The findings of the CFA indicated support for the original four-factor model. Additional analyses of the MGCFA method support the measurement (configural, metric and strong) invariant and practical invariant components of this model. There was an invariant across gender. There was partially invariant across groups of levels of education. The scale exists in groups of levels of education assess the same concepts of, excluding Items 15 and 10. Given that this study is the first investigation for the structure of the effectiveness scale.

• Asia-Pacific Journal of Business
• /
• v.15 no.1
• /
• pp.319-334
• /
• 2024

Purpose - The purpose of this study is to examine the gravity model commonly used for demand forecasting upon the implementation of new tourist facilities and analyze the main causation of forecasting errors to provide a suggestion on how to improve. Design/methodology/approach - This study first measured the errors in predicted values derived from past feasibility study reports by examining the cases of five national science museums. Next, to improve the predictive accuracy of the gravity model, the study identified the five most likely issues contributing to errors, applied modified values, and recalculated. The potential for improvement was then evaluated through a comparison of forecasting errors. Findings - First, among the five science museums with very similar characteristics, there was no clear indication of a decrease in the number of visitors to existing facilities due to the introduction of new facilities. Second, representing the attractiveness of tourist facilities using the facility size ratio can lead to significant prediction errors. Third, the impact of distance on demand can vary depending on the characteristics of the facility and the conditions of the area where the facility is located. Fourth, if the distance value is below 1, it is necessary to limit the range of that value to avoid having an excessively small value. Fifth, depending on the type of population data used, prediction results may vary, so it is necessary to use population data suitable for each latent market instead of simply using overall population data. Finally, if a clear trend is anticipated in a certain type of tourist behavior, incorporating this trend into the predicted values could help reduce prediction errors. Research implications or Originality - This study identified the key factors causing prediction errors by using national science museums as cases and proposed directions for improvement. Additionally, suggestions were made to apply the model more flexibly to enhance predictive accuracy. Since reducing prediction errors contributes to increased reliability of analytical results, the findings of this study are expected to contribute to policy decisions handled with more accurate information when running feasibility analyses.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.5_2
• /
• pp.151-162
• /
• 2010

This research aimed at measuring Park and Green Satisfaction (PGS) using subjective indicators of 'surface, line and spot' green evaluated by citizens. Also frequency of visits to park and green measured using objective indicators (number of visits) to find the relationship with PGS. A conceptual model of PGS was developed to relate evaluation to satisfaction and finally to utilization of open spaces. A sample of 500 questionnaire survey was employed for Uijeongbu City in Korea. A Structual Equation Modeling (AMOS) techniques was used to test the hypothesized relationship among factors (construct). As a result, first, PGS was explained by three latent factors of 'urban park' (${\gamma}=0.54$), 'linear facilities' (${\gamma}=0.25$), and 'surface green' (${\gamma}=0.15$) respectively. These three exogenous construct was found very useful classification system for open spaces of cities. Second, PGS (${\gamma}=0.34$) was found as a mediating variable to utilization of open spaces and also PGS was closely related to citizens Environmental Quality Satisfaction (EQS), such concept as, 'livability' and 'aesthetic quality'. The more satisfied with park and green the more people use the space. The PGS was an important QOL indicator together with the subjective indicator of 'livability'. Third, jogging and walking trails and bike ways along the river corridor was the most important green facilities contribute to the PGS and EQS. The near the distance (within 500m) the more number of visit to river corridor (green way). The river corridor promote accessibility to nature and other parks.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.3
• /
• pp.209-219
• /
• 2013

Epidemiological models on disease spread attempt to simulate disease transmission and associated control processes and such models contribute to greater understanding of disease spatial diffusion through of individual's contacts. The objective of this study is to develop an agent-based modeling(ABM) approach that integrates geographic information systems(GIS) to simulate the spread of FMD in spatial environment. This model considered three elements: population, time and space, and assumed that the disease would be transmitted between farms via vehicle along the roads. The model is implemented using FMD outbreak data in Andong city of South Korea in 2010 as a case study. In the model, FMD is described with the mathematical model of transmission probability, the distance of the two individuals, latent period, and other parameters. The results show that the GIS-agent based model designed for this study can be easily customized to study the spread dynamics of FMD by adjusting the disease parameters. In addition, the proposed model is used to measure the effectiveness of different control strategies to intervene the FMD spread.

• Particle and aerosol research
• /
• v.8 no.4
• /
• pp.161-172
• /
• 2012

Three-dimensional numerical simulation using a computational fluid dynamics (CFD) was carried out in order to investigate the formation and dispersion of the plume discharged from the stack of a thermal power station. The simulation was based on the standard ${\kappa}{\sim}{\varepsilon}$ turbulence model and a finite-volume method. Warm and moist exhaust from a power plant stack forms a visible plume as entering the cold ambient air. In the simulation, moisture content, emission velocity and temperature of the flue gas, air temperature and wind speed were dealt with the main parameters to analyze the properties of the plume composed mainly of water vapor. As a result of the simulation, the plume could be more apparent in cold winter due to a big difference of latent heat capacity. At no wind condition, the white plume rises 120 m upward from the top of the stack, and expands to 40 m around from the stack in cold winter after flue gas heat recovery. The influencing distance of relative humidity will be about 100 m to 400 m downstream from the stack with a cross wind effect. The decrease of flue gas temperature by heat recovery of thermal energy facilitates the formation of the plume and restrains its dispersion. Wind speed with vertical distribution affects the plume dispersion as well as the density.