• Journal of Nutrition and Health
• /
• v.48 no.3
• /
• pp.269-276
• /
• 2015

Purpose: The aim of the current study was to compare the vegetable and fruit intake between one person households and those living with family. Methods: The 24-hour recall data of 14,914 persons over 20 years old who participated in the Korean National Health and Nutrition Examination Survey (KNHANES) from 2010 to 2012 were used for the final analysis. Consumption of non-salted vegetables and fruits (${\geq}400g/day$), fruits (${\geq}200g/day$), and kimchi (${\geq}120g/day$) was compared between one person households and those living with family. Logistic regression models were used to assess the associations between potential determinants and adequate vegetable and fruit intake. Results: After additional adjustments for age, household income, and total energy intake, no statistically significant differences in likelihood of low intake of nonsalted vegetable and fruit and kimchi were observed between one person households and those living with family. (Nonsalted vegetables and fruits: odds ratio (OR) = 1.15, 95% confidence interval (CI) = 0.79-1.68 for the men; OR = 1.25, 95% CI = 0.98-1.59 for women). However one person households have greater likelihood of low intake of kimchi than those living with family in women (OR = 1.72, 95% CI = 1.31-2.26). Conclusion: Although there were no differences in likelihood of low intake of non-salted vegetables and between individuals living alone and those living with family, women of one person households were great likelihood of low intake of kimchi compared to those living with family.

• Journal of Nutrition and Health
• /
• v.53 no.5
• /
• pp.518-531
• /
• 2020

Purpose: This study examined the association between fruit and vegetable intake and mental health in Korean adolescents. Methods: This study used the data from the 2014-2017 Korea Youth Risk Behavior Survey, a national cross-sectional survey on 137,101 boys and 130,806 girls aged 12-18. Fruit and vegetable intake was assessed based on the frequency of consumption. The outcome variables were the perceived happiness, perceived stress, depressive symptom and suicidal ideation over the previous 12 months. Logistic regression models were used after adjusting for the demographic, life style and other dietary factors. Results: Only 34% and 29% of Korean adolescents consumed fruits more than 5 times/week and vegetables more than 2 times/day, respectively; whereas 37%, 25% and 12.2% of Korean adolescents had perceived stress, depressive symptom and suicidal ideation, respectively. After adjusting for the confounding variables, the greater consumption of fruit and vegetable were all associated with a higher odds of perceived happiness; the adjusted odds ratios (AORs) (95% CI) were 1.53 (1.46-1.60) in boys and 1.82 (1.73-1.90) in girls who consumed fruit ≥ 5 times/week, and 1.65 (1.54-1.76) in boys and 1.62 (1.51-1.72) in girls who consumed vegetable ≥ 2 times/day. In contrast, the consumption of fruit or vegetable were all significantly associated with a lower odds of perceived stress, depressive symptom, and suicidal ideation; the AOR (95% CI) were 0.70 (0.67-0.73), 0.88 (0.84-0.93), and 0.78 (0.73-0.83) in boys who consumed fruit 3-4 times/week, and 0.71 (0.67-0.76), 0.88 (0.81-0.94), and 0.68 (0.62-0.74) in boys who consumed vegetable 5-7 times/week. Similar associations of fruit or vegetable consumption with perceived stress, depressive symptom, or suicidal ideation were found in girls. Conclusion: These findings provide evidence that increasing fruit and vegetable intake is important for better mental health among adolescents.

• The Journal of Industrial Distribution & Business
• /
• v.2 no.2
• /
• pp.15-24
• /
• 2011

Modern enterprises should concentrate their efforts on continuous improvements in focusing their development in the core areas of business and to reduce their expenses and to enhance the quality of service for customers. The enterprises should focus on their core business while outsourcing the non-core areas of business to external specialists for the purpose of reducing cost. In South Korea, the enterprises are becoming increasingly interested in outsourcing their logistics function, especially in using IT technologies to the 3PL. The underlying reason for this trend is because the logistics costs of Korean businesses are much higher than that of other advanced countries. This higher logistic costs weakens the price competitiveness of Korean companies in the overseas export markets and even dampening the balance of international trade. Domestically, the higher logistics costs have the effect of raising prices in the local markets and thus affecting the local economy. Therefore a solution is urgently needed to save the logistics costs for the Korean companies in the interest of increasing national competitiveness. Outsourcing to the 3PL is becoming an attraction solution to this problem. Thanks to the increasing supply of professional logistics companies, many of the enterprises are switching to the Third Party Logistics. Nevertheless the enterprises do not yet utilize the integrated third-party logistics services on a full scale. This study analyzes present conditions and problems of the domestic third-party logistics market and suggests directions for future development. To solve the problems in the domestic third-party logistics market, four actions are recommended. First there should be new supporting policies in the laws and regulations and a system for small and medium sized companies to grow. Solutions to structural problems such as abnormal multilevel merchandising, illegal operation of private cars, and freight dumping should be implemented concurrently. Furthermore, standards for new companies entry into the market should be enhanced to allow only the competitive distribution companies to enter the market. Second, development of variety of educational programs is needed through establishing human-resource development system and specialized formal educational institution focused on this market. Third, the third party distribution companies, which seek long-term relationships with the owners of goods, should endeavor to strengthen their communications capability. Fourth, adoption of high-tech distribution system and the advent of U-Logistics, making use of RFID is urgent. This study has the limitation of objectivity because it does not include various comparative case studies about companies relating to the Third Party Logistics and domestic franchise companies. However, this study is significant to the extent that it analyzes the general present conditions and the problems of domestic Third Party Logistics and suggests recommendations for revitalization of Third Party Logistics. For future studies, analyzing the successful cases of international third party logistics companies' empirical data and studying the application into domestic franchise companies would improve the objectivity of the results. This would assist the domestic third party logistics companies not only to perform excellent domestic logistics function but also to enter into the global market for international logistics.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of agricultural medicine and community health
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2001

A questionnaire survey of 568 women over the age of 30 in 11 dongs of Goryeong- gun was performed to identify the practice rate of breast self- examination and its related factors. It was found that the practice rate of breast self- examination was 28.2%, with 9.7% of those surveyed performing breast self- examinations more than once a month. The practice rate of breast self- examination showed significant differences according to factors, such as age, presence of spouse, educational level, occupation, economic status, smoking, regular exercise and chronic disease. According to age, the highest practice rate of breast self-examination was between the ages of 40-49 and the lowest over the age of 60. The practice rate increased with higher the educational level and presence of spouse. According to occupation, administrative and managerial occupations presented the highest practice rate of breast self- examination. Higher economic status, regular exercise and positive family history of breast cancer each presented high practice rates of breast self- examination. The practice rate revealed higher in those who did not smoke and who had no chronic diseases than others. The greatest reason for performing breast self- examination was decided by myself for health reasons, followed by effect of mass media and promotion by health center. The most common reasons for not performing breast self- examination were don't feel the need, followed by don't know how to perform the exam and don't know about the exam itself. Multiple logistic regression analysis showed that factors, such as over the age of 60, less education, and no experience with mammography all lowered the practice rate of self-breast examination. Inconclusion, the rates of breast self- examination and regular check-ups of people in rural areas, who are characteristically older and have low educational backgrounds, were 28.2% and 9.7%. These results show the immediate need for the education of the methods for breast self- examination to be carried out by health centers in these areas. Such efforts and programs could increase the practice rate of breast self- examination and thereby improve health and enhance the quality of life of women in rural areas.

• Journal of agricultural medicine and community health
• /
• v.26 no.2
• /
• pp.133-146
• /
• 2001

The purpose of this study was to investigate the treatment status and its related factors of the newly detected rural hypertensives through community health promotion program. A questionnaire survey and blood pressure measurement were performed to 6,977 residents of a rural area, and 282 hypertensives detected by blood pressure measurement were selected as subjects of the study. The study employed the health belief model as a hypothetical model. The major results of this study were as follows: The proportion of person experienced treatment among hypertensives was 12.0%. Treatment experience rate was significantly related with age and educational level(p<0.01). That is, if they were older, lower educational level, the treatment experience rate was higher. The major reasons of no treatment were 'they had not hypertensive symptoms ' (45.6%), 'their blood pressure was not high so much that they received treatment ' (43.2%). The chief facilities for treatment were public health institutions(57.9%) such as health center and health subcenter, and hospital/ clinics(29.8%). The treatment experience rate was higher when they had higher perceived severity for hypertension, lower perceived barrier to treatment, although statistically not significant. Treatment experience rate was significantly related with cues to action and health education experience(p<0.05). That is, if they had hypertension related symptoms such as headache previously, patients suffered from hypertension complication and health education experience for hypertension, the treatment experience rate was higher. In multiple logistic regression analysis for treatment experience, having a cerebrovascular patient in their acquaintance and the experience of health education for hypertension were significant variables. On consideration of above findings, it would to be essential to provide knowledge about hypertension and its treatment, and severity of hypertension complications through health education.

• Journal of agricultural medicine and community health
• /
• v.34 no.3
• /
• pp.279-290
• /
• 2009

Objectives: WHO insisted on that we should study about association between residential environment and health status and make 'health city' concept as practical motto. This study analyzed about that how community environment affected their health. Methods: We surveyed residential environment satisfaction and health status of a apartment complex residents. We transformed Chun's index about housing environment study and social capital index of WHO and used as community health survey. We analyzed the association between health status and related factor by using principal compound analysis and logistic regression analysis. Results: We found out that the perceived health status 1 years ago was highly related to the residential environment and also extracted five residential environment component (APT maintenance, House, APT complex, Neighbor, APT building) by principal component analysis. After residential environment component, demographic and socioeconomic variable were controlled, the high satisfaction group of APT complex and neighbor relationship was in lower risk of perceived health status 1 years ago than the low satisfaction group. Conclusions: Recently, the importance of residential environment and neighborhood is shaped as community capacity. Therefore, social relationship and residential environment should be the core variable for health promotion of community. After all, we should know the relationship of residential environment and perceived health status 1 years ago. This helps the concept of health city clearly.

• Journal of dental hygiene science
• /
• v.16 no.3
• /
• pp.225-234
• /
• 2016

The purpose of this study was to determine the oral health condition and behavioral status of Korean adults according to occupational status. The subjects were 7,676 adults, aged between 19 and 64 years, who completed both oral examination and questionnaire survey, among those who indicated that they were currently participating in economic activities, according to the data from the Fourth Korea National Health and Nutrition Examination Survey. Occupational class and employment status were selected as measures of occupational status. Complex-samples logistic regression models were used to assess the associations among oral health, behavioral, and occupational statuses. We found a significant occupational class-related difference in the oral health and behavioral statuses of both the men and women. In particular, the prevalence odds ratios of untreated dental caries in manual workers were 1.19 and 1.67 times higher than in non-manual workers, for men and women, respectively. As for oral health condition and behavioral status according to employment status, the health risk in temporary employment workers was higher than that in permanent employment workers. As for the prevalence odds ratios of the risk of dental caries, the highest values were observed for tooth brushing fewer than 3 times per day, not undergoing oral examinations, and chewing difficulty complaints. The risk of dental caries for agricultural, forestry, and fishing workers for both men and women was found to be the highest among other workers. Thus, strategies to promote workplace oral health in the microscopic and macroscopic perspectives should be developed to constantly monitor oral health problems, and to identify vulnerable social groups within occupational groups and the related factors that mediate oral health differences.