Periodontal disease is a chronic but treatable condition which often does not cause pain during the initial stages of the illness. Lack of awareness of symptoms can delay initiation of treatment and worsen health. The aim of this study was to develop and compare different risk prediction models for periodontal disease using machine learning algorithms. We obtained information on risk factors for periodontal disease from the Korea National Health and Nutrition Examination Survey (KNHANES) dataset. Principal component analysis and an auto-encoder were used to extract data on risk factors for periodontal disease. A synthetic minority oversampling technique algorithm was used to solve the problem of data imbalance. We used a combination of logistic regression analysis, support vector machine (SVM) learning, random forest, and AdaBoost to classify and compare risk prediction models for periodontal disease. In cases where we used principal component analysis (PCA) to extract risk factors, the recall was higher than the feature selection method in the logistic regression and support-vector machine learning models. AdaBoost’s recall was 0.98, showing the highest performance of both feature selection and PCA. The F1 score showed relatively high performance in Ada- Boost, logistic regression, and SVM learning models. By using the risk factors extracted from the research results and the predictive model based on machine learning, it will be able to help in the prevention and diagnosis of periodontal disease, and it will be used to study the relationship with various diseases related to periodontal disease.

The purposes of this study are to analyze risks of construction step BIM(Building Information Modeling) applied project and improve it. Recently, construction industry has emphasized an importance of BIM for efficient utilization of various information. In the whole life cycle of huge construction project, there are cases introducing BIM and projects applying BIM are gradually increased to the work of construction step. However, the process of communication is not established, so the contents of BIM process of construction step are just showing rough fields and concepts of working utilization, so it's restrictive to utilize BIM actively on constructions step. Through results of case study in this research, constructor risks of BIM business should be efficiently treated with Fuzzy-FMEA that is more precise than existing danger evaluation.

The purpose of this study was to investigate the relations between HbA1c level and health risk factor. For analysis, 330 elderly women aged 65 years and over were recruited in Jeonla province, Korea. The subjects were classified into two groups according to their HbA1c level; the diabetic group (HbA1c level≥6.5%, n=68, 20.6%) and control group (HbA1c level< 6.5%, n=262, 79.4%). Demographic characteristics were collected, as well as information on physical measurements, blood tests for biochemical indicators, a health status and health-related life style, dietary behavior, favorite food groups, consumption frequency of food groups and nutrient intake. Educational level of the diabetic group was significantly lower than that of the control group. The height of the diabetic group was shorter, and percentage fat of the diabetic group was higher than those of the control group. In the diabetic group, the higher concentrations of creatinine and activity of alkaline phosphatase were found to be significantly unfavorable factors. Therefore, the diabetic group was assumed to be at risk of decreased liver and renal function. The self-rated health level of the diabetic group has a declining tendency, while the medicine intake was significantly higher than that of the control group, but there are no significant differences in visiting frequency of hospital and community health center. The distribution of physical activity showed a significant difference between the groups. Although there are no significant differences in nutrient intake, the diabetic group had relatively inferior nutrient intake of diet, especially vitamin C, as contrasted with the control group. In conclusion, the weight control and increasing physical activity may be effective in the prevention of the diabetes and continuous education and intervention by specialized nutritionists will be needed for diabetic patients. These results could be useful to plan effective strategies to increase the health-life expectancy and the prevention of the diabetes of Korean elderly people living in rural areas.

후쿠시마 원자력 발전소 사고 이후 한국 정부는 일본북부지역에서 생산되는 수산물 수입을 금지하였다. 한국과 일본 사이 수산물 분쟁은 아직 진행중이며 소비자들은 식품안전에 위협을 받고 있다. 이 연구는 소비자의 일본수산물에 대한 위험인식과 위험행동에 영향을 미치는 요인들을 밝히기 위함이다. 이를 위해 2012년 9월부터 10월까지 1,500명의 성인을 대상으로 설문조사를 수행하였다. 분석결과 일본산 수산물에 대한 위험인식에서 감정의 역할이 확인되었는데, 일본산 수산물에 대해 부정적인 감정을 느끼고 있는 개인은 해당 제품에 대한 위험 인식이 높았다. 또 부정적인 감정은 수산물 구입행동에도 영향을 미치는 것으로 나타났다. 한편 운명주의적 성향은 수산물 구입행동에 유의한 변수가 아닌 것으로 나타났다.

There are many reason for unsafety action without safety operation. The reason is no standard safety operation in company or the workers never get a enough education. Standard safety operation is prepared by paper for accurate directions and orders and operators must read the paper to prevent an error of action. Also an essential particular is safety of equipment and machine must be assumed to establish standard safety operation then safety of operations will be possible.

The purpose of this study is to examine the prevalence of musculoskeletal disorders and ergonomic risk factors for workers of printing business. A self-reporting survey and task analysis using video camera were performed to identify ergonomic risk factors associated with musculoskeletal disorders. We used the OWAS, RULA, and REBA methods to quantify the risk factors, and the results show that the printing business have high risk of work-related musculoskeletal disorders.

The purpose of this study is to analyze the determinants of risk factor model for the Jordanian banking stocks from 2006 to 2018. This study employs the Five-factor Fama and French’s (2015) methodology and uses the annual returns of all Jordanian banks including 2 Islamic and 13 commercial banks listed on the Amman Stock Exchange (ASE) over a period of 13 years. The results show that the factors of value and profitability have an important role in evaluating the expected return in Jordanian banking stocks. Moreover, the value HML and profitability RMW factors provide the highest cumulative returns among these five factors, while the investment CMA and size SMB factors are still around zero cumulative returns. For the market factor, it provides the least negative cumulative returns. The results showed that the largest correlation is between value and investment factors which means that banks with a high book to market value become banks with a conservative investment strategy. The result of the sub-periods confirmed the value and profitability results. The findings of this study suggest that the five-factor Fama and French model is the choice of building an investment portfolio, especially the factors of value and profitability.

In this study, the risk factors which derive from the ground condition of typical construction sites are put forward. In order to prioritize the risk elements, the analytical method of AHP was used. The result of using a weighting factor for each risk analysis showed that if the constituency index is less than 0.1, then reliable results and priorities for each of the risk elements can be calculated using the AHP method. From now on, if the range of measured value can be established, the risk or safety value of concrete structures for power lines can be applicable.

전 세계는 테러리스트에 의한 세계무역센터의 공격으로 인해 테러로부터의 안전과 보호를 강화하기 위해 초점이 맞추어져 있다. 본 연구는 해상테러 위험요소의 구조와 우선순위를 분석하고자 한다. 이를 위해 먼저 테러의 유형과 사례를 토대로 브레인스토밍법을 이용하여 해상테러 위험요소를 추출하였고, 퍼지구조모델법을 이용하여 위험요소를 그래프로 구조화 하였으며, 계층분석법을 이용하여 위험요소간의 우선순위를 분석하였다. 그 결과 외부영향이 가장 큰 위험요소인 것으로 나타났다.