• 대한통합의학회지
• /
• 제12권2호
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• 한국의류학회지
• /
• 제19권3호
• /
• pp.434-447
• /
• 1995

This research was intended to identify variables influencing on risk perception and risk reduction behavior in clothing purchase situations. Responses from 631 female adults living in Seoul area were collected and analyzed. Towner for social occasions or working in office was used as clothing stimulus. The analysis included three product variables(price, style, type of clothing), 4 personality variables(generalized self-confidence, specific self-confidence, generalized informativeness, fashion informativeness), 2 clothing attitude variables(clothing importance, clothing interest), 4 demographic variables(age, educational level, occupation, income), and 3 situational variables(purchase planning, time pressure, effects of shopping company). Multiple regression revealed the fact that each type of clothing risk and each type of risk reduction behavior was influenced by the set of different variables. Generalized self- confidence and age and time pressure had more effects on clothing risk perception, while clothing risk reduction behavior was more influenced by clothing risk type, clothing interest, price of clothing and fashion informativeness. Implications for marketing strategies planning were also provided.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.39-40
• /
• 2015

As international construction market increases, the importance of risk management in international construction project is emphasized. Unfortunately, current risk management practice does not sufficiently deal with project risks. Although a lot of risk analysis techniques have been introduced, most of them focus on project's external unexpected risks such as country conditions and owner's financial standing. However, because those external risks are difficult to manage and take preemptive action, we need to concentrate on project inherent risks. Based on this premise, this paper proposes a project-oriented risk mining approach which could detect and extract project risk factors automatically before they are materialized. This study presents a methodology regarding how to extract potential risks which exist in owner's project requirements and project tender documents using state of the art data analysis method such as text mining. The project-oriented risk mining approach is expected to effectively reflect project characteristics to the project risk management and could provide construction firms with valuable business intelligence.

• Journal of Radiation Protection and Research
• /
• 제4권1호
• /
• pp.29-35
• /
• 1979

Comparison of the risk of death due to radiation exposure with the same risk due to occupational hazards in other safe industries underlines the importance of the ALARA principle. The outlined responsibilities and listed examples presented here can serve as a basis for expanding and developing the concepts necessary for its successful application.

• Parasites, Hosts and Diseases
• /
• 제59권1호
• /
• pp.61-65
• /
• 2021

Diarrheal disease is the second leading cause of mortality and morbidity in children under 5 years old worldwide, and is the most common cause of malnutrition in sub-Saharan Africa. In Rwanda, diarrhea is the third leading cause of death in children under 5 years old. This study examined the association between sociodemographic factors and diarrhea in children under 5 years using the data of 7,474 households in the 2014-2015 Rwanda Demographic and Health Survey. Overall prevalence of diarrhea in this study was 12.7% in children. An increased risk for diarrhea was found for children aged 12-23 months (odds ratio (OR)=4.514), those with a low economic status (OR=1.64), those from the Western province (OR=1.439), those with poorly-educated mothers (OR=5.163), and those with families engaged in agricultural activities (OR=1.624). In conclusion, sociodemographic factors significantly affect the risk of developing diarrhea in children under 5 years in Rwanda. Designing and implementing health education promoting awareness of early interventions and rotavirus vaccination are essential to reduce diarrheal diseases for the Rwandan community.

• 대한의생명과학회지
• /
• 제23권3호
• /
• pp.155-160
• /
• 2017

Biomedical laboratory is full of risks. Risk could be biological, chemical, radioactive, mechanical, physical, fire and electrical. All possible risks need to be identified, evaluated and controlled. A risk management system must be in place to prevent accident or loss of lives and to improve overall workplace safety and productivity. Safety in laboratory is a combination of appropriate risk management system, engineering controls and technical facilities, administrative controls and safety procedures and practices. Laboratory safety culture must be developed so that exposure to hazards for laboratory personnel, community and environment will be minimized or eliminated. In this review, importance of safety in a biomedical laboratory and risk management will be discussed.

• Journal of Information Technology Applications and Management
• /
• 제14권3호
• /
• pp.79-94
• /
• 2007

Cases of botched information systems implementation have been surfaced due to poor IS project management and control. One major source of such failures is the perceptual difference between the participants of IS projects who should define potential risk factors well before considered IS projects are launched. Based on risk factors cited from prior works, this paper empirically examines the risk factors associated with IS service project management to analyze perceptual differences between the IS service providers and customers in Korea. Data analyses found significant differences in the area of scheduling/resource, technological newness, communications, and sponsorship/ownership while statistically significant differences were observed in eleven individual factors out of forty six risk factors. Risk factors are also ordered in terms of perceived importance to highlight the critical differences.

• Asia pacific journal of information systems
• /
• 제17권1호
• /
• pp.77-93
• /
• 2007

Risk has been considered as one of very important topics in traditional consumer behavior theoretically and practically since its tendency of minimizing errors rather than maximizing utilization in addition to its intuitive appealing with very high explaining power. In addition to a traditional view of risk, importance of risk in online transactions such as Internet banking is due to technical instability in security of the Internet as well as temporal and spatial separation of transaction partners. Therefore, risk in online transactions should be analyzed by a very comprehensive way since it is very inherent in the Internet. The objective of this study is to suggest a research model for explaining the use of online transactions in some risk related variables including risk results, security result, perceived security, and social influence and show its validity by applying it to Internet banking users. In result, hypotheses suggested by our research model are shown to be valid ones.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.4-5
• /
• 2015

Owning to rapid infrastructure development, Asia is experiencing dramatic economic growth. There are not a few cases in which, however, economic growth is achieved by increasing the external diseconomy. Pursuit of sustainable development is one of the most important issues for mankind. Under the post-industrial capitalism society, however, there seems a big risk of increase in the external diseconomy worldwide. The objectives of this manuscript are to discuss importance of risk management of construction practice in present and future. Regarding the latter, a particular attempt is made to discuss how project risk communication should be done to reduce the external diseconomy. Presently, one of the important issues in implementation of infrastructure projects is practice of risk management to properly manage time, cost, quality, and safety: mainly maximization of internal economy. Multi-party risk and uncertainty management process (MRUMP) is one of tolls to assist it. The idea on MRUMP can be used to reduce the external diseconomy through identifying, sharing, and tuning people's rhythms.

• Earthquakes and Structures
• /
• 제9권4호
• /
• pp.719-733
• /
• 2015

Seismic risk management of the built environment is integrated by two main stages, the assessment and the remedial measures to attain its reduction, representing both stages a complex task. The seismic risk of a certain structure located in a seismic zone is determined by the conjunct of the seismic hazard and its structural vulnerability. The hazard level mainly depends on the proximity of the site to a seismic source. On the other hand, the ground shaking depends on the seismic source, geology and topography of the site, but definitely on the inherent earthquake characteristics. Seismic hazard characterization of a site under study is suggested to be estimated by a combination of studies with the history of earthquakes. In this Paper, the most important methods of seismic vulnerability evaluation of buildings and their application are described. The selection of the most suitable method depends on different factors such as number of buildings, importance, available data and aim of the study. These approaches are classified in empirical, analytical, experimental and hybrid. For obtaining more reliable results, it is recommends applying a hybrid approach, which consists of a combination between methods depending on the case. Finally, a recommended approach depending on the building importance and aim of the study is described.