• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.29-34
• /
• 2023

Recently, the rapid development of artificial intelligence technology, many studies are being conducted to predict the risk of heart disease in order to lower the mortality rate of cardiovascular diseases worldwide. This study presents exercise or dietary improvement contents in the form of a software app or web to patients with cardiovascular disease, and cardiovascular disease through digital devices such as mobile phones and PCs. LR, LDA, SVM, XGBoost for the purpose of developing "Life style Improvement Contents (Digital Therapy)" for cardiovascular disease care to help with management or treatment We compared and analyzed cardiovascular disease prediction models using machine learning algorithms. Research Results XGBoost. The algorithm model showed the best predictive model performance with overall accuracy of 80% before and after. Overall, accuracy was 80.0%, F1 Score was 0.77~0.79, and ROC-AUC was 80%~84%, resulting in predictive model performance. Therefore, it was found that the algorithm used in this study can be used as a reference model necessary to verify the validity and accuracy of cardiovascular disease prediction. A cardiovascular disease prediction analysis algorithm that can enter accurate biometric data collected in future clinical trials, add lifestyle management (exercise, eating habits, etc.) elements, and verify the effect and efficacy on cardiovascular-related bio-signals and disease risk. development, ultimately suggesting that it is possible to develop lifestyle improvement contents (Digital Therapy).

• Journal of Advanced Navigation Technology
• /
• v.18 no.5
• /
• pp.494-500
• /
• 2014

Recently the leak of personal information from in-house and contract-managed companies has been continually increasing, which leads a regular observation on outsourcing companies that perform the personal information management system to prevent dangers from the leakage, stolen and loss of personal information. However, analyzing many numbers of computers in limited time has found few difficulties in some circumstances-such as outsourcing companies that own computers that have personal information system or task continuities that being related to company's profits. For the reason, it is necessary to select an object of examination through identifying a high-risk of personal data leak. In this paper, this study will formulate a proposal for the selection of high-risk subjects, which is based on the user interface, by digital forensic. The study designs the integrated analysis tool and demonstrates the effects of the tool through the test results.

• Journal of Digital Convergence
• /
• v.9 no.6
• /
• pp.103-111
• /
• 2011

This study parent-children relationship with the youth of the Internet was to evaluate the impact on. Internet excess utility of adolescents was to influence the, and how we received its relation the influence. This study distinguished their patent-children relation according to the violence and non-interference level and Internet excess utility contains an everyday life problem, we can not do the work to plan, the excess Internet usage, and the complications of the another person. This distinguished with genernal, potent risk, high risk category. The result was as follows: First, potent risk and high risk category appeared in the parent-children relation to be the no- interference. This means that parent-children relation has an influence on internet excess utility of adolescent. Second, the role of parents is important to reduce internet utility of adolescent, and it must understand so that the development stage is careful. We need the supply for adolescent with play and experience program development which can enjoy the leisure culture. We need internet poisoning expert training and the treatment must be achieved with the counselling to be continuous to problem adolescents.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.175-183
• /
• 2018

This study analyzes determinants of bond returns in terms of systematic risk versus idiosyncratic risk by examining relationship among those factors. First we examined the cross-sectional determinants of corporate bond returns with Korean bond market data from 2001 to 2014. This paper uses term factor and default factor for systematic risk, and duration factor and credit rating factor for idiosyncratic risk. The empirical result shows that systematic risk can explain cross-sectional differences of bond returns rather than idiosyncratic risk which is the same result in advanced markets(US or Europe). This result is different from the previous Korean studies which showed that idiosyncratic risk is more important than systematic risk in Korean bond market. The reason for the different result may be the longer sample period which includes the most recent period. It is insisted that Korean bond market is getting more synchronized with the advanced bond market. In conclusion, this empirical result implies that Korean bond portfolio managers should focus on systematic risk, which is contrary to current system in Korean asset management industry.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2002.10a
• /
• pp.85-85
• /
• 2002

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.771-777
• /
• 2018

This study proposes a big data based risk analysis framework to analyze more comprehensive disaster risk and vulnerability. We introduce a distributed and parallel framework that allows large volumes of data to be processed in a short time by using open-source disaster risk assessment tool. A performance analysis of the proposed system presents that it achieves a more faster processing time than that of the existing system and it will be possible to respond promptly to precise prediction and contribute to providing guideline to disaster countermeasures. Proposed system is able to support accurate risk prediction and mitigate severe damage, therefore will be crucial to giving decision makers or experts to prepare for emergency or disaster situation, and minimizing large scale damage to a region.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.533-539
• /
• 2015

The purpose of this study was to investigate the effects of 12weeks complexed lower body muscle-strengthening exercise program on fall risk in elderly women. Twenty subjects volunteered to participate who use a welfare center in W city For the study we divided into two groups: exercise group (EC, n=10, mean age:$69.6{\pm}2.2$), comparative group(CG, n=10, mean age:$71.3{\pm}4.6$). In order to investigate the effect of lower body muscle-strengthening program on the degree of risk of fall. It reached a conclusion as follows after having applied BBS (Berg Balance Scale) and OLST (One-Leg Stance Test) to examine the degree of risk of fall. As a result of changes in BBS and OLST, there were significant differences between EG and CG for each test(p<.00). Therefore, it confirmed that the application of complexed lower body muscle-strengthening program to the elderly who have a high risk of fall influences the risk of fall positively.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.119-127
• /
• 2014

As the disclosure of privacy information has grown steadily, concerns about mobile services based on the personal information also increased. We aspired to reveal factors influencing the use of Location-Based services(LBS) App and analyse how the perceived risk affected between these factors and the use of LBS App. Results showed that usefulness and social influence influenced on the use of LBS App. We also found that the group who highly recognized the perceived risk was highly affected by usefulness and the group who lowly recognized the perceived risk was highly affected by social influence. Findings show that the company's strategy should be different depending on the level of consumers' perceived risk.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.193-199
• /
• 2017

The objective of this research is to investigate how consumers react differently to financial and social risk/return, referred to as an 'asymmetric effect'. A lab-based experiment using a counterfeit but real-branded product examined the robustness of the statement that priming the interdependent versus independent self can result in differences in financial and social risk taking behavior in the context of counterfeit product purchase choice. Three hundred fifty-eight participants took part in the experiment. They were primed with different self-construal and evaluated purchase intention to the counterfeit product. As predicted, when evaluate in the context of loss claim of counterfeit product, risks were more activated, however, there was an asymmetric effect that self-construal priming had on financial and social risks. Interdependence primed participants were more likely to take a financial risk thus perform more purchase intention of counterfeit product and less likely to take a social risk than their independence primed counterparts, which led to lower purchase intention. The results of this research shed light on the various directions of future studies on the responses toward counterfeit product.

• Journal of Digital Convergence
• /
• v.14 no.12
• /
• pp.267-281
• /
• 2016

This study analyzed the contents of articles on GMO in Chosun Ilbo and Hankyoreh from 1994 through 2015 to check the trend of reporting on GMO as a science and technology risk issue. As a result, 'risk' and 'anxiety/concern' were continuously treated as important subjects, and there was a lack of depth and journalist's professionalism in all three periods: 'Introduction of GMO technology (1994-2000)', 'Development of GMO technology (2001-2010)' and 'Social acceptance of GMO (2011-2015).' In a comparison between the media with different ideological goals, the Chosun Ilbo had a stronger new-technological inclination to GMO than the Hankyoreh in reporting topics and tones of arguments. As a result of checking the relation of the tones in reporting with the 'risk-benefit' of GMO, reports in negative tones underlined 'risk' while those in positive tones, 'benefit.' This study could suggest improvements of subject bias and unprofessionalism in the domestic science journalism, the barometer of public awareness of disputes over science and technology risk.