• Journal of the Korean Geographical Society
• /
• 제51권2호
• /
• pp.219-233
• /
• 2016

In social science fields, statistical models are used almost exclusively for causal explanation, and explanatory modeling has been a mainstream until now. In contrast, predictive modeling has been rare in the fields. Hence, we focus on constructing the predictive non-parametric model, instead of the explanatory model. Gangnam-gu, Seoul was chosen as a study area and we collected single-family house sales data sold between 2011 and 2014. We applied non-parametric models proposed in machine learning area including generalized additive model(GAM), random forest, multivariate adaptive regression splines(MARS) and support vector machines(SVM). Models developed recently such as MARS and SVM were found to be superior in predictive power for house price estimation. Finally, spatial autocorrelation was accounted for in the non-parametric models additionally, and the result showed that their predictive power was enhanced further. We hope that this study will prompt methodology for property price estimation to be extended from traditional parametric models into non-parametric ones.

• Journal of Families and Better Life
• /
• 제22권5호
• /
• pp.59-73
• /
• 2004

Since 1980s' Korea had a great change on the housing culture by the supply of multi-family housing stock both on the macro-social and micro-social aspects. The purpose of this study was to examine the changes and the characteristics of housing environments which were estimated its modernization, and to examine the personal life under the change of housing environments. So I would like to revaluation the characteristics of modernization between the 1980s' and 1990s'. Therefore references were made to various papers, reports, the statistical data, newspaper reports, advertisements and magazines during that period. As a result, this paper came to the remarks as follows: 1. The success of modernization on the housing environments since 1980s' was the Quantitative growth of housing supply by multi-family housing. In spite of this, the Quantitative growth of housing supply and the improvement in Quality like housing space per person had the characters which was 'out of valence on the division'. 2. The Qualitative improvement of modem housing life by the development of housing industries could be said the improvement owing to develop of facilities and equipments. The introduction of up-to-date facilities and equipments realized the convenience and the rationality of living in the house. Although the improvement on the physical things deteriorated the modernized spaces to uniform things by commercial strategies. 3. The life in the multi-family housing which gives protection to personal privacy was settle down on the extremely individualized life without common things within the neighbors. Multi-family housing which was a production of process of modernization came true the growth in an appearance and the variety in the inside, but for the aspect of residents' everyday life in the multi-family housing, the Korean traditional relationship was collapsed and a sense of incompatibility within the residents was created.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• 제23권8호
• /
• pp.900-908
• /
• 2012

Owing to the proliferation of smart phone users, a proactive spectrum policy is needed in order to deal with increasing data traffic. Therefore, the prediction of frequency requirements for future wireless local area network (WLAN) as well as a licensed cellular communication is necessary. In this paper, we proposed a new prediction method for WLAN spectrum requirements. This method includes both a traditional prediction method and an offloading percentage from cellular network, Also, it can consider a frequency interference between access points using a statistical approach. Based on these approaches, we can predict the spectrum requirements of future domestic WLAN services considering the frequency interference. Finally, we suggest the spectrum policy for WLAN which can prevent spectrum shortage of future WLAN services.

• Journal of Society of Preventive Korean Medicine
• /
• 제6권2호
• /
• pp.48-63
• /
• 2002

The study aims to investigate the process of professional socialization of oriental medical students, to analyze influencing factors on it, and to compare the results with those of western medical students. Professional socialization, in the context of this study, means the process through which a layperson becomes a profession equipped with professional identity and values. A survey using specially designed questionnaire was carried out in 1999. The data were collected from 11 oriental medical colleges for 2,656 students. A total of 2,597 cases was finally included in the statistical analysis. Analysis of factors related to professional value found that oriental medical students thought highly of human-oriented factors, followed by science and status, and this trend remained unchanged as they moved on to qualification. Among professionalism related items, those involved in professional regulation and dominance factors showed high scores, while showing low scores on items related to bio-ethics and autonomy factors. Unlike items of professional value, those of professionalism showed a notable difference in attitude statistically by schooling level. The average scores of factors for professionalism increased with increasing schooling years. This trend proved that oriental medical students acquired professional norms and attitudes through their educational period. Multiple regression analysis with the factors related to professional value and professionalism as dependent variables found that independent variables had some impact on science, status, and clinical autonomy, but no impact on human, policy autonomy, and professional regulation factors. In conclusion, with increasing schooling years, professional norms and attitudes of oriental medical students were also strengthened. And, in spite of the differences in general propensity, they have a base consciousness in common with western medical students. The difference of mind-set and attitudes related to professionalism in the two groups, however, considering the necessity of future cooperative relations, indicated that a common curriculum between both schools is needed, and the education of social medicine should be strengthened in oriental medical colleges.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제5권3호
• /
• pp.144-151
• /
• 2012

Chronic gastritis is the disease that is occuring in one in every 10 persons in Korea. In western medicine, endoscopy is needed to diagnose chronic gastritis, but it causes patients a pain and budget of expense. According to the TEM (Traditional Eastern Medicine), on the other hand, the 'Guan' position of the right wrist is related to a stomach. Thus we can diagnosis chronic gastritis by analyzing of pulse signal. However, pulse signal diagnosis is depended on oriental doctor's knowledge and experience. In this study, a systematic approach is proposed to analyze the computerized pulse signal. The pulse signals are firstly pre-processed, Gaussian model is adopted to fit the pulse signal, and then some related parameters are extracted from the model. Consequently, disease-sensitive parameters are selected by T-test and statistical difference. Finally, the selected parameters are entered into a Fuzzy C-Means (FCM) algorithm for classification. Classification results show that healthy persons and chronic gastritis patients are 95% and 87%, respectively.

• Journal of the Korean Society of Safety
• /
• 제35권5호
• /
• pp.59-65
• /
• 2020

For monitoring the status of industrial accidents, many statistical indexes have been developed and applied such as fatal rate, frequency rate, and severity rate. These accident indexes are measured by frequency and loss time according to the accidents in the individual industry level. However, it is less considered to use the index of identifying the industrial concentration of accidents in the holistic view. Thus, this study aims to suggest the accident concentration level among domestic industries through index analysis. The concentration level of industrial accidents is calculated by the accident composition of sub-industries. This concentration level shows whether an industry is comprised of a few sub-industries generating more accidents or an industry consists of sub-industries having the similar number of accidents. To this end, the concentration rate (CR) and concentration index (CI) are proposed to take a look at the industry composition of accidents by embracing the concept of market concentration indexes such as Hirschman-Herfindahl Index. As for the case study, four industries of mining, manufacturing, transportation, and other business (usually service) are analyzed in terms of indexes of accident rate, death(fatality) rate, and CR and CI of accident and death. Finally, we illustrate the positioning map that the accident concentration level is compared with the traditional accident frequency level among industries.

• The KIPS Transactions:PartB
• /
• 제10B권1호
• /
• pp.33-40
• /
• 2003

Data mining plays an important role in a knowledge discovery process and various algorithms of data mining can be selected for the specific purpose. Most of traditional hierachical clustering methode are suitable for processing small data sets, so they difficulties in handling large data sets because of limited resources and insufficient efficiency. In this study we propose a hybrid neural networks clustering technique, called PPC for Pre-Post Clustering that can be applied to large data sets and find unknown patterns. PPC combinds an artificial intelligence method, SOM and a statistical method, hierarchical clustering technique, and clusters data through two processes. In pre-clustering process, PPC digests large data sets using SOM. Then in post-clustering, PPC measures Similarity values according to cohesive distances which show inner features, and adjacent distances which show external distances between clusters. At last PPC clusters large data sets using the simularity values. Experiment with UCI repository data showed that PPC had better cohensive values than the other clustering techniques.

• Journal of Intelligence and Information Systems
• /
• 제11권2호
• /
• pp.17-29
• /
• 2005

The purpose of the study was to explore the potential of the Social Network Analysis as an analytical tool for scientific investigation of learner-learner, or learner-tutor interaction within a Computer Supported Corporative Learning (CSCL) environment. Theoretical and methodological implication of the Social Network Analysis had been discussed. Following theoretical analysis, an exploratory empirical study was conducted to test statistical correlation between traditional performance measures such as achievement and team contribution index, and the centrality measure, one of the many quantitative measures the Social Network Analysis provides. Results indicate the centrality measure was correlated with the higher order teaming performance and the peer-evaluated contribution indices. An interpretation of the results and their implication to instructional design theory and practices were provided along with some suggestions for future research.

• The Korean Journal of Applied Statistics
• /
• 제28권1호
• /
• pp.61-74
• /
• 2015

Structural equation modeling (SEM) is a widely used in social sciences such as education, business administration, and psychology. In SEM, the latent variable score is the estimate of the latent variable which cannot be observed directly. This study uses stagewise structural equation modeling(stagewise SEM; SSEM) by partitioning the whole model into several stages. The traditional estimation method minimizes the discrepancy function using the variance-covariance of all observed variables. This method can lead to inappropriate situations where exogenous latent variables may be affected by endogenous latent variables. The SSEM approach can avoid such situations and reduce the complexity of the whole SEM in estimating parameters.

• The Korean Journal of Applied Statistics
• /
• 제20권3호
• /
• pp.573-584
• /
• 2007

A well estimated probability of default is most important for constructing a good credit scoring process. The maximum expected utility (MEU) model has been suggested as an alternative of the traditional logistic regression model. Because the MEU model has been constructed using financial data arising from North America and European countries, the MEU model may not be suitable to Korean private firms. Thus, we propose a Korea-specific MEU model by estimating the parameters involved in kernel functions. This Korea-specific MEU model is illustrated using 34,057 private firms to show the performance of the MEU model relative to the usual logistic regression model.