• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.317-330
• /
• 2021

This study aims to derive the main factors for predicting student departure of university freshmen and provide the basis for establishing policies to prevent student departure at the institutional level. For this purpose, a random forest model is developed with the data observed for 2 years at a four-year private university in Seoul. In the prediction model, 6 variables of school adjustment factors and 12 variables of institution satisfaction factors are applied. The top 6 variables presenting the highest MDA turn out to be emotional stability, financial conditions, assurance in the choice of major, satisfaction with the choice of university, educational method(systematic teaching method), educational method(effectiveness of major education). Based on the results of this study, it is suggested the necessity of institutional design supporting freshmen to adapt to university life and stably continue their studies.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.49-58
• /
• 2023

Dropouts of students not only cause financial loss to the university, but also have negative impacts on individual students and society together. To resolve this issue, various studies have been conducted to predict student dropout using machine learning. This paper presents a model implemented using DNN (Deep Neural Network) and LGBM (Light Gradient Boosting Machine) to predict dropout of university students and compares their performance. The academic record and grade data collected from 20,050 students at A University, a small and medium-sized 4-year university in Seoul, were used for learning. Among the 140 attributes of the collected data, only the attributes with a correlation coefficient of 0.1 or higher with the attribute indicating dropout were extracted and used for learning. As learning algorithms, DNN (Deep Neural Network) and LightGBM (Light Gradient Boosting Machine) were used. Our experimental results showed that the F1-scores of DNN and LGBM were 0.798 and 0.826, respectively, indicating that LGBM provided 2.5% better prediction performance than DNN.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.380-390
• /
• 2020

Cyber-university has a higher rate of dropout freshmen due to various educational factors, such as social background, economic factors, IT knowledge, and IT utilization ability than students in twenty offline-based university. These students require a different dropout prevention method and improvement method than offline-based universities. This study examined the main factors affecting dropout during the first semester of 2017 and 2018 A Cyber University. This included management and counseling factors by the 'Decision Tree Analysis Model'. The Management and counseling factors were presented as a decision-making method and weekly methods. As a result, a 'Dropout Improvement Model' was implemented and applied to cyber-university freshmen in the first semester of 2019. The dropout-rate in freshmen applying the 'Dropout Improvement Model' decreased by 4.2%, and the learning-persistence rate increased by 11.4%. This study applied a questionnaire survey, and the cyber-university students LMS (Learning Management System) learning results were analyzed objectively. On the other hand, the students' learning results were analyzed quantitatively, but qualitative analysis was not reflected. Nevertheless, further study is necessary. The 'Dropout Improvement Model' of this study will be applied to help improve the dropout rate and learning persistence rate of cyber-university.

• Korean Journal of Social Welfare
• /
• v.61 no.4
• /
• pp.191-215
• /
• 2009

The purposes of this study were to investigate the factors that influence the school drop-out of North Korean refugee youth and to generate recommendations for social work practice and the resettlement policies of the government to ameliorate the high school drop-out rate among North Korean refugee youth. This study examined the effects of the environmental factors such as the quality of parenting practice, peer attachment and the kind of school a youngster attends, and personal characteristics such as self-respect and acculturation stress level, and academic efficacy on the school drop-out intention. Gender, duration of stay in Korea, family economic status were established as control variables. The drop-out intention was used as a proxy for drop-out behavior. The study findings indicate that the personal characteristics such as gender, self-respect and acculturation stress, academic efficacy were the significant influencing factors, whereas environmental factors such as quality of parenting, peer attachment did not exert any statistically significant effect on the drop-out intention. At the conclusion, the implications of the study findings for research, social work practice and the government policies were discussed.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.37-43
• /
• 2021

This study proposed an effective automatic classification technique to identify dropout patterns of university students, and based on this, an intelligent recommender system to prevent dropouts. To this end, 1) a data processing method to improve the performance of machine learning was proposed based on actual enrollment/dropout data of university students, and 2) performance comparison experiments were conducted using five types of machine learning algorithms. 3) As a result of the experiment, the proposed method showed superior performance in all algorithms compared to the baseline method. The precision rate of discrimination of enrolled students was measured to be up to 95.6% when using a Random Forest(RF), and the recall rate of dropout students was measured to be up to 80.0% when using Naive Bayes(NB). 4) Finally, based on the experimental results, a method for using a counseling recommender system to give priority to students who are likely to drop out was suggested. It was confirmed that reasonable decision-making can be conducted through convergence research that utilizes technologies in the IT field to solve the educational issues, and we plan to apply various artificial intelligence technologies through continuous research in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.187-193
• /
• 2020

In this study, we wanted to analyze the factors at the national university level that affect college students ' elimination. In addition, national universities, private universities, universities in Seoul and universities outside of Seoul were divided into more college-specific characteristics. Except for leave of absence and departure from school, it was defined as a middle school dropout among changes of students. The data were used for analysis by receiving raw data from "University Alerts," which are operated by the Ministry of Education and the Korean Council for Educational Universities. At the university notification, 222 universities out of the schools classified as "Universities" were utilized for final analysis, and jobs, credits, scholarships, tuition fees, students, independent students, and full-time teachers were secured through multiple education. Overall, the higher the average graduate level and employee-rate the lower the rate of elimination from the middle of college students, the analysis showed. Second, the higher the average tuition fees at private universities, the more negatively affects the rate of elimination of university students. Third, higher tuition fees at universities outside the Seoul metropolitan area have a negative impact on the rate of elimination of students.

• Journal of Digital Convergence
• /
• v.14 no.1
• /
• pp.453-463
• /
• 2016

This study examined the relationship among dropout, organizational trust, and intention to transfer in the department affiliated with Physical Education. Data were collected from 480 students in the department affiliated with Physical Education from 6 institutions of a 4-year university located in Seoul, Gyeonggi-do, Incheon, and ChungChong-do. For the research model analysis, a structural equation model and bootstrapping were conducted. Results indicated that the academic domain, the social domain, and the environmental domain of dropout had a positive effect on organizational trust. But the only the academic domain in the relationship between dropout and intention to transfer affected intention to transfer positively. The social domain and the environmental domain were not statistically significant on intention to transfer. Moreover, organizational trust had a positive effect on intention to transfer. Finally, organizational trust partially mediated the path between the academic domain and intention to transfer. It fully mediated the paths between the social domain and the environmental domain and intention to transfer.

• Journal of the Korean Society of Radiology
• /
• v.83 no.5
• /
• pp.1121-1127
• /
• 2022

Endometriosis-related symptoms are believed to be alleviated during pregnancy. However, pregnancy complications, such as pseudoaneurysm of the uterine artery, rupture of ovarian or uterine vessels, and intraabdominal bleeding from decidualized deep infiltrating endometriosis (DIE) lesion have been rarely reported. Owing to the potential risk of rupture and resultant life-threatening complications, proper diagnosis and close monitoring of decidualized endometriotic lesion are very important despite its low relative risk. Till date, massive vaginal bleeding from decidualized rectovaginal DIE during pregnancy has not been in English literatures. Here, we present the first case of spontaneous massive vaginal bleeding due to decidualized rectovaginal DIE that occurred in the late third trimester of pregnancy.

• The korean journal of orthodontics
• /
• v.35 no.3 s.110
• /
• pp.207-215
• /
• 2005

This study was performed to evaluate clinical practicality of the rebonding method with flowable resin without the removal of the residual resin on the debonded theeth and debonded bracket base after debonding. The samples of the control group (group I) were rebonded with Transbond XT using the usual rebonding method after the residual resin was removed. At experimental group, the brackets were rebonded with Transbond XT(group II) and CharmFil Flow (group III) without removal of residual resin which is the possibility becoming the index (or rebonding to similar position With initial bonding. The Shear bond Strength of the each group was measured. Patterns of bonding failure were evaluated with modified ARI score. and the shear bond strength according to patterns of bonding failure at experimental group was compared. Between the control group $(6.51\pm1.21MPa)$ and the group II rebonded with Transbond XT $(6.30\pm1.01MPa)$ did not have significantly difference in the shear bond strength (p=0.534), and the shear bond strength of group II was Significantly lower 4han the group III rebonded With CharmFil Flow $(7.29\pm1.54 MPa)$ (P=0.009). At control group, there was not large difference if distribution of bending failure pattern. But at experimental group, bond failure did not occur in interface between the resin-enamel. and bond failure between the resin-bracket, within the resin was distributed similarly. There was not significantly difference in the shear bond strength according to patterns of bonding failure at experimental group (P>0.05) The result of this study showed that the method suggested in this study aid flowable resin as rebonding adhesive could be useful in clinically.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.358-360
• /
• 2003

원자력과 같은 대용량 발전기의 갑작스런 탈락이나 하루 중 아침시간이나 점심시간과 같이 급격한 부하변동이 발생하는 특수 시간대에는 계통의 발전량과 부하량간에 심한 불균형이 발생하게 된다. 이 경우 계통 주파수가 변하여 발전량과 부하량이 자동으로 조절되어 수급의 균형이 이루어지게 되므로 계통이 안정하게 유지된다. 본 논문에서는 실계통 사고사례를 통하여 우리나라 계통에서 대용량 발전기 탈락시 주파수변동에 따른 발전량 및 부하량의 조절특성과 고장당시 계통 발전기들의 응동특성을 소개한다.