• Journal of agricultural medicine and community health
• /
• v.38 no.2
• /
• pp.116-129
• /
• 2013

Objectives: This study was performed to identify the associations of social capital with suicidal thoughts and attempts in Korean communities with poor health. Methods: We used the data from community health interviews conducted at 40 administrative sections (dong, eup, or myeon) with high mortality from August to October in 2010, 2011, and 2012 as part of the Health Plus Happiness Plus Projects in Gyeongsangnam-do Province. The 8,800 study subjects composed of 220 adults systematically sampled from each administrative section were asked if they had thought about suicide or had attempted suicide within 1 year. The social participation was measured with 'participation in formal and/or informal group' and trust using responses to three questions about trust of others. Results: The prevalence of suicidal ideation and attempt within 1 year were 10.4% and 0.8%, respectively. The logistic regression analysis revealed that those who participated in only informal groups, or had highest trust level reported less suicidal ideation, or attempt after adjusting for socio-demographic factors (sex, age, marital status, occupation, and food affordability), self-rated health, and health behaviors (smoking, alcohol drinking, and exercise). Conclusions: This study suggested social capital such as social participation and trust was associated with less suicide ideation and attempt. More studies are warranted for the association of social capital with suicidal behavior.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. 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, total misclassification cost is more affected by FNE rather than FPE. 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 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of Preventive Medicine and Public Health
• /
• v.35 no.2
• /
• pp.153-159
• /
• 2002

Objectives : To evaluate the accuracy of the registered cause of death in a county and its related factors. Methods : The data used in this study was based on 504 cases, in a county of Chonnam province, registered between January and December 1998. Study subjects consisted of 388 of the 504 cases, and their causes of death were established by an interview survey of the next of kin or neighbor and medical record surveys. We compared the registered cause of death with the confirmed cause of death, determined by surveys and medical records, and evaluated the factors associated with the accuracy of the registered cause of death. Results : 62.6% of the deaths were concordant with 19 Chapters classification of cause of death. external causes of mortality, endocrine, nutritional and metabolic diseases, neoplasms and diseases of the circulatory system showed the good agreement between the registered cause of death and the confirmed cause of death. The factors relating to the accuracy of the registered cause of death were the doctors' diagnosis for the cause of death (adjusted Odds Ratio: 2.67, 95% Confidence Interval: 1.21-5.89) and the grade of the public officials in charge of the death registry (adjusted Odds Ratio: 0.30, 95% CI=0.12-0.78). Conclusions : The accuracy of the registered cause of death was not high. It could be improved by using the doctors' diagnosis for death and improving the job specification for public officials who deal with death registration.

• Journal of Preventive Medicine and Public Health
• /
• v.28 no.4 s.51
• /
• pp.795-807
• /
• 1995

This study was carried out from 1993 to 1994 in the small industries in Incheon. The objectives of this study was in order to estimate the quitting rate, to identify its relating factors and to propose effective quitting management policy in the small industries. The results were as follows ; 1. The quitting rate of 266 study workers was 42.1%(112 workers). 2. Age, working duration, position, marrital status were significant difference between the quitting group and the non - quitting group. In the quitting group, mean age was young, working duration was short, general employees and unmarried workers were many compared with the non - quitting group. 3. In the industry characteristics, total assets, total assets, sales per person, establishment duration and occupational health and safely status were significant difference between the quitting group and the non - quitting group. In the quitting group, total assets, total sales and sales per person were little, establishment duration of company was short and occupational health and safety status were poor compared with the non - quitting group. 4. In the quitting group, worker's response to employer's disposal about health and safety was more passive and the relation to employer with employee was significantly poor compared with the non - quitting group. 5. Multiple logistic regression analysis of quitting against family income per person, working duration, relation to employer with employee, occupational health and safety status in industry, worker's response to employer's disposal about health and safety and sales per person was done. Working duration, occupational health and safety status, worker's response to employer'1 disposal about health and safety were significant explainatory variables for quitting. Above results showed that the quitting rate was high and it was significant difference between the quitting group and non : quitting group according to characteristics of workers and of industries. Especially, it suggested that working duration, occupational health and safety status and worker's response to employer's disposal about health and safety were significant quitting factor. Therefore, it should be reflected in the quitting management and the policy of steady employment.

• Journal of Nutrition and Health
• /
• v.47 no.2
• /
• pp.124-133
• /
• 2014

Purpose: The current study was designed for development of a simplified malnutrition screening tool (SMST) for hospitalized patients using readily available laboratory and patient information and for evaluation of its reliability compared to well-established tools, such as PGSGA and NRS-2002. Methods: Anthropometric and biochemical measurements, as well as a few subjective assessments, of 903 patients who were preclassified by their nutritional status according to PGSGA were analyzed. Among them, a combination of factors, including age, BMI, albumin, cholesterol, total protein, hematocrit, and changes in body weight and food intake, were statistically selected as variables for SMST. Results: According to SMST, 620 patients (68.7%) were classified as the normal group and 283 patients (31.3%) were classified as the malnutrition group. Significant differences in age, albumin, TLC, BMI, hemoglobin, hematocrit, total protein, cholesterol, and length of stay were observed between the two groups. For inter-methods reliability, the screening results by SMST were compared with those by PGSGA and NRS-2002. The comparison with PGSGA and NRS-2002 showed 'Substantial agreement' (sensitivity 94.4%, specificity 88.4%, ${\kappa}$ = 0.747) and 'Moderate agreement' (sensitivity 96.1%, specificity 79.5%, ${\kappa}$ = 0.505), respectively, indicating that SMST held high inter-methods reliability. Conclusion: In conclusion, SMST, based on readily available laboratory and patient information and simple subjective assessments on changes in food intake and body weight, may be a useful alternative tool with a simple but reliable risk index, especially in resource-limited domestic hospitals.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.2
• /
• pp.191-199
• /
• 2016

Objectives : Despite the increased popularity of highly caffeinated beverages, there is little research examining psychiatric adverse effects. The purpose of this study was to investigate the relationships among pattern of highly caffeinated beverage intake and depressive symptom, suicidal ideation, suicidal plan, suicidal attempt in Korean adolescents. Methods : The data was obtained from the 2014 Korean Youth's Risk Behavior Web-based Study by Korea Centers for Disease Control & Prevention. All participants conducted web-based questionnaire survey. Chisquare test and multiple logistic regression analysis were performed to determine the association among highly caffeinated beverage intake pattern, depressive symptom, suicidal ideation, suicidal plan and suicidal attempt adjusting for differences in age, gender, academic achievement, socioeconomic status. Results : A total of 71,638 participants were enrolled in this study. Depressive symptom, suicidal ideation, suicidal plan and suicidal attempt were significantly more frequent in the group with presence of highly caffeinated beverage intake within 1 week than in non-drinker group(p<0.01). Highly caffeinated beverage intake was significantly associated with suicidal attempt(OR=1.99 ; 95% CI, 1.77-2.22). In addition, depressive symptom, suicidal ideation, suicidal plan and suicidal attempt were significantly more common in the group with heavy-drinker who exceed recommended daily intake dose of caffeine than in the group with light-drinker(p<0.01). Heavy drinking of caffeinated beverage was significantly associated with suicidal attempt(OR=4.05 ; 95% CI, 3.02-5.43). Conclusions : We found that highly caffeinated beverage intake was related to more frequent depressive symptom, suicidal ideation, plan, attempt in adolescents. Also, caffeine intake which exceed recommended daily intake dose identified the predictor of suicidal attempt. Our result suggested that clinicians need to be aware of the possible psychiatric adverse effects of highly caffeinated beverage in vulnerable population including young adolescents.

• Journal of agricultural medicine and community health
• /
• v.46 no.3
• /
• pp.162-170
• /
• 2021

Objectives: This study was carried out to understand the seroprevalence and risk factors for severe fever with thrombocytopenia syndrome (SFTS) among the Korea National Park Service (KNPS) workers. Methods: We used the stored serum samples (763) and survey results collected from the previous investigation on scrub typhus and Lyme disease among the KNPS workers during 2016-2017. The serum samples were analyzed by double-antigen sandwich enzyme-linked immunosorbent assay, which was used to test the total antibody including IgG and IgM. Results: The SFTS seroprevalence among the KNPS worrkers was 1.4%. In multivariate logistic analysis, the national park exploration programs (odds ratio, 3.48; 95% confidence interval, 1.01-12.01) was significantly associated with the seroprevalence of SFTS. Conclusion: This study was the first serological study of SFTS among forestry workers in South Korea. Although the KNPS workers are at a high-risk group of SFTS, the prevention activities related to the working environment and habit was insufficient. Thus, systematic prevention education and training for the KNPS workers need to be strengthened.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.392-402
• /
• 2019

The purpose of this study is to determine the factors that predict happiness among aged males and females who live alone, and we focused on their satisfaction with their socio-physical environment, their social network, regular participation in social activities, their subjective health status and if they suffer from depression. A total of 2,76 people were the subjects of this study, their average age was 65 years old, they lived alone and all of them were selected from the '2017 Community Health Survey' data. The data was analyzed utilizing the Chi-square test, the Mann-Whitney test and multivariate logistic regression analysis. The subjects were 605 males (21.86%) and 2,163 females (78.14%). For the result of this study, the significant predictive factors of happiness for aged males living alone were monthly income (OR=2.363, 95% CI=1.473-3.791), basic livelihood rights (OR=1.903, 95% CI=1.144-3.167), trusting their neighbors (OR=2.018, 95% CI=1.263-3.225), religious activities (OR=2.098, 95% CI=1.314-3.349), subjective health (OR=2.753, 95% CI=1.217-6.228), and depression (OR=0.852, 95% CI=0.803-0.905). The significant predictive factors of happiness for aged females living alone were income (OR=2.407 95% CI=1.362-4.253), basic livelihood rights (OR=1.350, 95% CI=1.019-1.788), contact with friends (OR=1.879, 95% CI=1.323-2.669), religious activities (OR=1.372, 95% CI=1.124-1.676), recreation/leisure activities (OR=1.608, 95% CI=1.161-2.228), subjective health (OR=5.327, 95% CI=1.347-21.070), and depression (OR=0.864, 95% CI=0.840-0.890). In conclusion, programs to enhance happiness should be developed with considering the characteristics affecting the happiness of aged Korean males and females who live alone.

• 한국노년학
• /
• v.37 no.2
• /
• pp.281-291
• /
• 2017

The present study aimed to investigate the rate of unmet healthcare needs for elderly over the age of 65 years, as well as analyze the relevance between employment status and unmet healthcare needs due to financial reasons. With regard to the study method, a logistic regression analysis was performed to investigate the correlation between employment status and unmet healthcare needs due to financial reasons, targeting 5,528 subjects over the age of 65 years. The results showed that the rate of unmet healthcare needs was 18.9%, in which the rate of unmet healthcare needs due to financial reason was 8.1%. The rate of unmet health needs was higher for temporary workers(ORs=1.75) than for retirement workers. However, the rate of unmet healthcare needs caused by financial reasons was higher among day workers(ORs=1.92). In conclusion, in order to prevent unmet healthcare needs for senior Korean patients, it is necessary to not only improve the income security system for the elderly, but also improve the occupational form and level of income of these economically active citizens, considering the increase in average life expectancy. Moreover, it is also necessary to reinforce health insurance coverage systems for settling medical expenses.