• Journal of The Korean Digital Architecture Interior Association
• /
• v.12 no.4
• /
• pp.49-57
• /
• 2012

With regard to the culture in cities this study aims to essential understanding and systematic approach to the culture. The "2011 Seoul Survey"report has been used to find out causality among the related variables. In the first place 'satisfaction of cultural condition' was operationally selected as a dependent variable for regression. For the purpose of controlling confounding factors for ceteris paribus effect correlation analysis was done between the dependent variable and all other variables respectively, which resulted in two groups of variables: group (1) - 6 variables of very significant correlations(p-value<0.01) and (2) - the other 6 variables of significant correlations(p-value<0.05). Then hierarchical regression was adopted to these 2 groups to analyse $R^2$ increment, statistical significance of independent variables, and multicollinearity(VIF; variance inflation factor). At last a regression model specified by group (1) as independent variables(they are 'social trust', 'satisfaction of walking condition', 'happiness index', 'preparation against old age', 'satisfaction of traffic condition' and 'hours for internet') shows that only 'social trust' variable has statistically significant and substantially strong effect on 'satisfaction of cultural condition.' This finding should be accepted on the following understanding; (1) urban culture has a collective attribute formed between people and society, (2) culture is somewhat telling and hearing stories and the confidence between tellers and hearers is essential in the mutual response and (3) stimulus is received by relationship in company with sense, emotion, thinking and action. In spite of restrictive external validity this finding can be used as a direction for promoting culture and a basis for related policy choice in cities.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.5
• /
• pp.101-108
• /
• 2019

The domestic duck industry is the sixth-largest among the livestock industries. However, 34.3% of duck houses were the duck houses arbitrarily converted from plastic greenhouses. This type of duck house was difficult to properly manage internal air temperature and humidity environment. Humidity environment inside duck houses is an important factor that directly affects the productivity and disease occurrence of the duck. Although the humidity environments of litters (bedding materials) affect directly the inside environment of duck houses, there are only few studies related to humidity environment of litters. In this study, evaporation rates from litters were evaluated according to air temperature, relative humidity, water contents of litters, and wind speed. The experimental chamber was made to measure evaporation rates from litters. Temperature and humidity controlled chamber was utilized during the conduct of the laboratory experiments. Using the measured data, a multi linear regression analysis was carried out to derive the calculation formula of evaporation rates from litters. In order to improve the accuracy of the multi linear regression model, the partial vapor pressure directly related to evaporation was also considered. Variance inflation factors of air temperature, relative humidity, partial vapor pressure, water contents of litters, and wind speed were calculated to identify multicollinearity problem. The Multiple $R^2$ and adjusted-$R^2$ of regression model were calculated at 0.76 and 0.71, respectively. Therefore, the regression models were developed in this study can be used to estimate evaporation rates from the litter of duck houses.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.589-597
• /
• 2021

In simple and multiple regression, there is a difference in the meaning of regression coefficients, and not only are the estimates of regression coefficients different, but they also have different signs. Understanding the relative contribution of explanatory variables in a regression model is an important part of regression analysis. In a standardized regression model, the regression coefficient can be interpreted as the change in the response variable with respect to the standard deviation when the explanatory variable increases by the standard deviation in a situation where the values of the explanatory variables other than the corresponding explanatory variable are fixed. However, the size of the standardized regression coefficient is not a proper measure of the relative importance of each explanatory variable. In this paper, the estimator of the regression coefficient in multiple regression is expressed as a function of the correlation coefficient and the coefficient of determination. Furthermore, it is considered in terms of the effect of an additional explanatory variable and additional increase in the coefficient of determination. We also explore the relationship between estimates of regression coefficients and correlation coefficients in various plots. These results are specifically applied when there are two explanatory variables.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.

• Journal of Korea Water Resources Association
• /
• v.57 no.8
• /
• pp.533-548
• /
• 2024

Due to climate change with extreme weather events, occurrences of unprecedented heavy rainfall have become more frequent. Since it is difficult to perfectly predict and prevent flood damages, the limitation of traditional prevention-centered approaches has come a issue. The concept of "resilience" has therefore been developed which emphasizes the ability to swiftly recover from damages to previous states or to even better conditions. In this study, we 1) developed a total of 20 domestic flood resilience indicators based on the 4R principles (Redundancy, Robustness, Rapidity, Resourcefulness), 2) conducted applicability evaluations targeting specific disaster-prone areas, and 3) assessed the importance of each indicator through Analytic Hierarchy Process (AHP) analysis with flood-related experts. To confirm the suitability of the developed flood resilience indicators, multicollinearity analysis was performed, and the results indicated that all 20 indicators had tolerance limits above 0.1 and Variance Inflation Factors (VIF) below 10, demonstrating suitability as factors. Furthermore, evaluations of proposed indicators were carried out targeting disaster-prone areas in 2022(21 areas), and AHP analysis was utilized to determine the relative importance of each indicator. The analysis revealed that the importance of each indicator was as follows: Robustness 0.46, Rapidity 0.22, Redundancy 0.17, and Resourcefulness 0.16, with Robustness exhibiting the highest importance. Regarding the sub-indicators that had the greatest influence on each 4R component, river embankment maintenance emerged as the most influential for Robustness, healthcare services for Rapidity, fiscal autonomy of local governments for Resourcefulness, and drainage facilities for Redundancy.

• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.335-345
• /
• 2020

This paper deals with the problem of estimating the log-transformed linear regression model to fit actual battle data from the Ardennes Campaign of World War II into the Lanchester model. The problem of determining a global solution for parameters and multicollinearity problems are identified and modified by examining the results of previous studies on data. The least squares method requires attention because a local solution can be found rather than a global solution if considering a specific constraint or a limited candidate group. The method of exploring this multicollinearity problem can be confirmed by a statistic known as a variance inflation factor. Therefore, the Lanchester model is simplified to avoid these problems, and the combat power attrition rate model was proposed which is statistically significant and easy to explain. When fitting the model, the dependence problem between the data has occurred due to autocorrelation. Matters that might be underestimated or overestimated were resolved by the Cochrane-Orcutt method as well as guaranteeing independence and normality.

• The Korean Journal of Franchise Management
• /
• v.11 no.2
• /
• pp.41-51
• /
• 2020

Purpose: Fast food franchise companies are trying a variety of innovative services to increase their competitiveness in response to changes in population composition in the fast food market and rapid changes in consumption trends due to technological development. From this point of view, franchise companies that have focused on offline store operations are providing O2O (offline to online) service as a core service for customer convenience. This new attempt is a strategy to increase loyalty by applying an interaction method based on understanding the characteristics of new generation consumers. However, existing studies are focused on the relationship between O2O service and acceptance, so very little is known about how O2O service affects customer loyalty. Therefore, this study examines the impacts of customer involvement and relative advantages of fast food O2O service on customer brand engagement (cognitive and affective engagement) and store loyalty for MZ(Millennials - Z) generations. Research design, data, and methodology: In order to achieve the purposes of this research, several hypotheses were developed. The data were collected from 247 questionnaires in their 16-30s and were analyzed using SPSS 22.0 and SmartPLS 3.0 program. Measurement model analysis was carried out to assess convergent and discriminant validity. Also, common method bias was tested using the values of VIF (variance inflation factor). The hypotheses was tested using structural equation modeling. Result: First, involvement has a positive effect on cognitive and affective engagement. Second, relative advantages have has a positive effect on cognitive and affective engagement. Third, cognitive influences affective engagement. Finally, both cognitive and affective engagement affect store loyalty, but affective engagement has a stronger effect on store loyalty than cognitive engagement. Conclusions: In the process of consumer-brand interaction, it was confirmed that store loyalty was influenced by cognitive and affective engagement sequentially. However, the results show that affective engagement has a relatively stronger on store loyalty than cognitive engagement. Therefore, it is necessary to establish an O2O service strategy to maintain long-term loyal customers by inducing cognitive participation with high-involved consumer, as well as affective interaction, in order to obtain new customers and increase customer loyalty.

• The Korean Journal of Franchise Management
• /
• v.13 no.1
• /
• pp.35-46
• /
• 2022

Purpose: With the rapid changes in the technical development and the trend of consumption trend, the convenience store industry is facing an unprecedented competitive situation in the consumption environment where the boundary between online and offline is broken due to the stagnation of offline distribution channels and the spread of online shopping. The biggest innovation strategy of the major convenience store brands in recent years are introducing the O2O (Online to Offline) platform and presenting new products and services beyond the boundaries of online and offline to transform themselves into Omni Channel stores. The study is designed to analyze the effect of innovativeness of convenience store as a stimulus in O2O platform which customers perceive on store loyalty, the final response to external stimuli, through customer engagement with convenience store brands. Specifically, the innovativeness of convenience stores was divided into types of core activities in corporate marketing and focused on innovations in services, products(proposals), promotions and experiences. Research design, data, and methodology: Various hypotheses have been developed to achieve this research purpose. The data were collected from 1,128 questionnaires the age between 15 and 60 who had experience using retail store apps and delivery apps and were analyzed using SPSS 22.0 and SmartPLS 3.3.7 program. Measurement model analysis was carried out to assess convergent and discriminant validity. Also, common method bias was tested using the values of VIF (variance inflation factor). The hypotheses were tested using structural equation modeling with SmartPLS 3.3.7 program. Results: First, service innovation has a positive effect on cognitive engagement. Second, product, promotion and experience innovation have a positive effect on cognitive and affective engagement. Third, cognitive influences affective engagement. Finally, both cognitive and affective engagement affect store loyalty, but affective engagement has a stronger effect on store loyalty than cognitive engagement. Conclusions: All four types of innovation and cognitive engagement have a positive effect on emotional engagement, which has a stronger effect on store loyalty than cognitive engagement. Thus, while innovation can build loyalty through emotional engagement, innovation strategies must be designed and pursued with caution in terms of impact through cognitive engagement may not achieve the planned goals.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.390-390
• /
• 2020

자연재해 중 홍수의 경우 단기간에 발생하며, 큰 인명 및 금전적 피해를 가져오는 재해이다. 1970년~2017년 국내 홍수 피해 분석결과 사상자(총 8,152명)는 점차 줄어드는 추세를 보이지만, 반대로 피해액(총 17조5,000억원)은 증가하는 것으로 나타났다(wamis, 국가수자원관리종합정보시스템). 이러한 국내 홍수 피해를 최소화하기 위해서는 각 유역 또는 지역별 특성을 고려한 홍수 취약성 평가가 필요하다. 홍수 취약성은 대상 지역의 기상, 지형, 인문학적 상황에 따라 상이하게 나타나며, 홍수 취약성을 평가하는 인자의 선정 또한 매우 중요하다. 따라서 본 연구에서는 홍수 피해 자료와 홍수 인자간의 인과관계를 분석하여 홍수 취약성 지표 선정 및 취약성 평가를 실시하였다. 홍수 취약성 평가를 위해 홍수 피해 자료와 대상 인자간의 상관성 분석을 통해 상관계수 값이 상대적으로 높게 나온 인자를 선정하였다. 대상 인자는 크게 기상학적 인자, 지형학적 인자, 사회·인문학적 인자로 구분하였다 선정된 인자 간 서로 높은 상관성을 보일 시 공선성이 존재함을 의미하며, 이러한 공선성을 방지하기 위해 VIF (Variance Inflation Factor, 분산팽창계수)를 통한 공선성 검토를 적용하였다. 또한 각 인자 간 에는 서로 다른 단위 및 범위를 가진다. 이러한 경우 특정 인자들의 증감을 취약성 평가에 반영하기에 어려움이 있으며, 유역별 평가 시 신뢰성이 낮아진다. 따라서 Re-scaling 방법을 통해 각 인자의 단위 및 범위를 표준화 후 동일가중치 법을 적용하였다. 본 연구에서는 전체 유역 중 홍수피해가 가장 크게 발생하는 낙동강 태화강 유역을 연구 대상 지역으로 선정하였다. 태화강은 도심지의 중심부를 흐르는 하천이며, 산지의 고도가 높은 지형적 특성을 가지고 있어 홍수에 대한 취약성이 높은 것으로 나타났다(wamis, 국가수자원관리종합정보시스템). 태화강 유역 홍수 취약성 평가결과 유역별 기상, 지형, 인문학적 특성에 따라 홍수 취약성이 높게 나타나는 결과를 보였다. 이와 같은 결과는 유역 내 도심지 비율, 인구밀도, 토지피복 특성에 의한 것으로 주로 지형학적 인자로 인해 취약성이 높게 나타났다. 본 연구에서 활용한 홍수 취약성 평가 방법은 향후 홍수피해 대책 수립에 사용될 수 있을 것으로 판단된다.