머신러닝 모델 기반의 전자결제 이용 사업자의 폐업 예측

공현정,황유진,박성혁 한국지능정보시스템학회 2023 한국지능정보시스템학회 학술대회논문집 Vol.2023 No.5

오이의 RAPD분석을 위한 PCR 최적화

공현정,최인수 밀양대학교 농업기술개발연구소 2000 農業技術開發硏究所報 Vol.4 No.1

This study was conducted to identify the best combinations of factors(template DNA concentration, MgCl2 concentration, and amount of taq polymerase) for the optimization of PCR in cucumber. 3×3×3 factorial experiment for template DNA concentration, MgCl2 concentration, and amount of taq polymerase was conducted. Another factorial experiment for denature, annealing, extension temperature on the optimal PCR condition was also conducted. The most clear and reproducible bands were appeared in 60ng(0.5unit taq polymerase and 2.5mM MgCl2, 0.5unit taq polymerase and 4.5mM MgCl2, and 1unit taq polymerase and 7.0mM MgCl2). The best MgCl2 concentration was 2.5mM(60ng template DNA and 0.5unit taq polymerase), 4.5mM(40ng template DNA and 0.5unit taq polymerase, 40ng template DNA and 1unit taq polymerase, and 60ng template DNA and 0.5unit taq polymerase), and 7.0mM(60ng template DNA and 1unit taq polymerase). The combinations which showed the best bands from the amount of taq polymerase were 0.5unit(60ng template DNA and 2.5mM MgCl2, 60ng template DNA and 4.5mM MgCl2) and 1unit(40ng template DNA and 4.5mM MgCl2, 60ng template DNA and 2.5mM MgCl2, and 60ng template DNA and 7.0mM MgCl2). When we consider results from template DNA concentration, MgCl2 concentration, and amount of taq polymerase, 3 conditions(60ng of template DNA, 2.5mM MgCl2 and 0.5unit taq polymerase; 60ng of template DNA, 4.5mM MgCl2 and 0.5unit taq polymerase; 60ng of template DNA, 7.0mM MgCl2 and 1unit taq polymerase) were best combinations for the optimal PCR condition. Reaction temperatures for the optimal PCR condition were 86℃, 35℃, 64℃; 90℃, 40℃, 72℃; and 92℃, 36℃, 72℃.

참외의 PCR 최적 조건 구명

공현정,김용철,최인수 밀양대학교 농업기술개발연구소 2000 農業技術開發硏究所報 Vol.4 No.1

This study was conducted to identify the optimized PCR condition in cucumis melo. Factorial experiments for template DNA concentration, MgCl2 concentration, amount of taq polymerase, and reaction temperature(denature, annealing, extension) were conducted. The best template DNA concentration was 40ng(0.5unit taq polymerase and 4.5mM MgCl2, and 1unit taq polymerase and 2.5mM MgCl2), 60ng(0.5unit taq polymerase and 2.5mM MgCl2, 0.5unit taq polymerase and 4.5mM MgCl2, 1unit taq polymerase and 2.5mM MgCl2, 1unit taq polymerase and 4.5mM MgCl2, and 1unit taq polymerase and 7.0mM MgCl2). The best MgCl2 concentration was 2.5mM(40ng template DNA and 1unit taq polymerase, 60ng template DNA and 0.5unit taq polymerase, and 60ng template DNA and 1unit taq polymerase)와 4.5mM(40ng template DNA and 0.5unit taq polymerase, 60ng template DNA and 0.5unit taq polymerase, and 60ng template DNA and 1unit taq polymerase), and 7.0mM(60ng template DNA and 1unit taq polymerase). The best amount of taq polymerase was 0.5unit(40ng template DNA and 4.5mM MgCl2, 60ng template DNA and 2.5mM MgCl2, and 60ng template DNA and 4.5mM MgCl2) and 1unit(40ng template DNA and 2.5mM MgCl2, 40ng template DNA and 4.5mM MgCl2, 40ng template DNA and 7.0mM MgCl2, 60ng template DNA and 2.5mM MgCl2, 60ng template DNA and 4.5mM MgCl2, and 60ng template DNA and 7.0mM MgCl2). When we consider results from template DNA concentration, MgCl2 concentration, and amount of taq polymerase, 6 conditions(60ng template DNA, 7.0mM MgCl2, 1unit taq polymerase; 60ng template DNA, 4.5mM MgCl2, 1unit taq polymerase; 60ng template DNA, 2.5mM MgCl2, 1unit taq polymerase; 60ng template DNA, 4.5mM MgCl2, 0.5unit taq polymerase; 60ng template DNA, 2.5mM MgCl2, 0.5unit taq polymerase; and 40ng template DNA, 2.5mM MgCl2, 1unit taq polymerase) were best combinations for the optimal PCR condition. Reaction temperatures for the optimal PCR condition were 90℃, 40℃, 72℃ and 92℃, 36℃, 72℃.

복숭아의 PCR 최적 조건 구명

공현정,박진철,김성만,김용철,이충열,박현철,최인수 밀양대학교 농업기술개발연구소 2000 農業技術開發硏究所報 Vol.4 No.1

To optimize PCR condition is the most important and fundamental step for experiments using PCR. The purpose of this study was to optimize PCR condition for RAPD analysis in peach. 3×3×3 factorial experiment for template DNA concentration, MgCl2 concentration, and amount of taq polymerase was conducted. Another factorial experiment for denature, annealing, extension temperature on the optimal PCR condition was also conducted. The best template DNA concentration was 20ng(0.5unit taq polymerase and 2.5mM MgCl2), 40ng(0.5unit taq polymerase and 4.5mM MgCl2, and 1unit taq polymerase and 2.5mM MgCl2), and 60ng(0.5unit taq polymerase and 2.5mM MgCl2, 0.5unit taq polymerase and 4.5mM MgCl2, 1unit taq polymerase and 2.5mM MgCl2, 1unit taq polymerase and 4.5mM MgCl2, and 1unit taq polymerase and 7.0mM MgCl2). The best MgCl2 concentration was 2.5mM(40ng template DNA and 1unit taq polymerase, 60ng template DNA and 0.5unit taq polymerase, and 60ng template DNA and 1unit taq Folymerase), and 4.5mM(40ng template DNA and 0.5unit taq polymerase, 40ng template DNA and 1unit taq polymerase, 60ng template DNA and 0.5unit taq polymerase, and 60ng template DNA and 1unit taq polymerase), and 7.0mM (60ng template DNA and 1unit taq polymerase). The best taq polymerase concentration was 0.5unit(20ng template DNA and 2.5mM MgCl2, 40ng template DNA and 4.5mM MgCl2, 60ng template DNA and 2.5mM MgCl2, and 60ng template DNA and 4.5mM MgCl2), and 1unit(40ng template DNA and 2.5mM MgCl2, 60ng template DNA and 2.5mM MgCl2, 60ng template DNA and 4.5mM MgCl2, and 60ng template DNA and 7.0mM MgCl2). When we consider results from template DNA concentration, MgCl2 concentration, and amount of taq polymerase, 5 conditions(60ng of template DNA, 7.0mM MgCl2 and 1unit taq polymerase; 60ng of template DNA, 4.5mM MgCl2 and 1unit taq polymerase; 60ng of template DNA, 2.5mM MgCl2 and 0.5unit taq polymerase; 40ng of template DNA, 2.5mM MgCl2 and 1unit taq polymerase; and 40ng of template DNA, 4.5mM MgCl2 and 0.5unit taq polymerase;) were best combinations for the optimal PCR condition. Reaction temperatures for the optimal PCR condition were 90℃, 40℃, 72℃ and 92℃, 36℃, 72℃.

전자결제서비스 이용 사업자 폐업 예측에서 비재무정보 활용을 통한 머신러닝 모델의 정확도 향상에 관한 연구

공현정,황유진,박성혁 한국지능정보시스템학회 2023 지능정보연구 Vol.29 No.3

Research on corporate bankruptcy prediction has been focused on financial information. Since the company’s financial information is updated quarterly, there is a problem that timeliness is insufficient in predicting the possibility of a company’s business closure in real time. Evaluated companies that want to improve this need a method of judging the soundness of a company that uses information other than financial information to judge the soundness of a target company. To this end, as information technology has made it easier to collect non-financial information about companies, research has been conducted to apply additional variables and various methodologies other than financial information to predict corporate bankruptcy. It has become an important research task to determine whether it has an effect. In this study, we examined the impact of electronic payment-related information, which constitutes non-financial information, when predicting the closure of business operators using electronic payment service and examined the difference in closure prediction accuracy according to the combination of financial and non-financial information. Specifically, three research models consisting of a financial information model, a non-financial information model, and a combined model were designed, and the closure prediction accuracy was confirmed with six algorithms including the Multi Layer Perceptron (MLP) algorithm. The model combining financial and non-financial information showed the highest prediction accuracy, followed by the non-financial information model and the financial information model in order. As for the prediction accuracy of business closure by algorithm, XGBoost showed the highest prediction accuracy among the six algorithms. As a result of examining the relative importance of a total of 87 variables used to predict business closure, it was confirmed that more than 70% of the top 20 variables that had a significant impact on the prediction of business closure were non-financial information. Through this, it was confirmed that electronic payment-related information of non-financial information is an important variable in predicting business closure, and the possibility of using non-financial information as an alternative to financial information was also examined. Based on this study, the importance of collecting and utilizing non-financial information as information that can predict business closure is recognized, and a plan to utilize it for corporate decision-making is also proposed.

인슐린 요법을 받는 당뇨 환자의 우울, 가족지지, 자가간호 행위와 삶의 질

공현정(Hyun Jung Kong),최은정(Eun Joung Choi) 고신대학교 전인간호과학연구소 2022 전인간호과학학술지 Vol.15 No.-

Purpose: This study was to identify the relationship between depression, family support, self-care behavior and quality of life for diabetic patients in Insulin Therapy. Methods: The study design was a descriptive research study, and the participants of the study were 130 diabetic patients of 1university hospital in B metopolitan city. Data were collected by structured questionnaires from July 22 to August 31, 2016 after receiving approval from IBR. Data were analyzed using descriptive statistics, t-test, ANOVA and Pearson correlation. Results: The subject’s quality of life was significantly correlated with depression, family support, self-care behavior. Conclusion: To improve the quality of life of diabetics, it is necessary to develop an intervention program to reduce depression and increase family support and self-care behavior.

벼의 PCR 적정 조건 연구

김보경,공현정,최인수 밀양대학교 농업기술개발연구소 2001 農業技術開發硏究所報 Vol.5 No.1

The most fundamental step for the experiments such as RAPD is to optimize the PCR condition. The purpose of this study was to optimize PCR condition in tomato. 3×3×3 factorial experiment for template DNA concentration, MgCl2 concentration, and amount of taq polymerase was conducted. Another factorial experiment for reaction temperature(denature, annealing, extension) was also conducted. The most clear and reproducible bands were observed from 60ng(0.5unit taq polymerase and 2.5mM MgCl2, 0.5unit taq polymerascb and 4.5mM MgCl2. The best MgCl2 concentration was 2.5mM(60ng template DNA and 0.5unit tape polymerase, 60ng template DNA and lunit taq polymerase), and 4.5mM(40ng template DNA and lunit tape polymerase and 60ng template DNA and 0.5unit taq polymerase). And, the amount of taq polymerase for the optimal PCR condition was 0.5unit(60ng template DNA and 2.5mM MgCl2, 60ng template DNA and 4.5mM MgCl2, and lunit(40ng template DNA and 2.5mM MgCl2, 40ng template DNA and 4.5mM Mg Cl2, 40ng template DNA and 7.0mM MgCl2, and 60ng template DNA and 2.5mM MCl2). When we consider results from template DNA concentration, MgCl2 concentration, and amount of tape polymerase, 4 conditions(60ng of template DNA, 2.5mM MgCl2 and 0.5unit taq polymerase; 60ng of template DNA, 4.5mM MgCl2 and 0.5unit taq polymerase; and 60ng of template DNA, 2.5mM MgCl2 and lunit tape polymerase; and 40ng of template DNA, 4.5mM MgCl2 and lunit taq polymerase) were best combinations for the optimal PCR condition Reaction temperature for the optimal PCR condition was 92℃, 36℃, 72℃

일-가정 갈등 및 일-가정 향상 관련 변인 메타분석: 사회적 지지를 중심으로

윤민지,공현정,윤수란 한국문화및사회문제심리학회 2021 한국심리학회지: 문화 및 사회문제 Vol.27 No.1

본 연구는 일-가정 갈등 및 일-가정 향상과 사회적 지지와의 관계를 파악하기 위해 2000년부터 2020년까지 국내에서 이루어진 연구 총 34편(학술지 논문 14편, 학위논문 20편)에 대해 메타분석을 실시하였다(N=17,530). 일-가정 갈등과 향상은 방향에 따라 일→가정, 가정→일, 구분하지 않음으로, 사회적 지지의 지지자원은 가정, 배우자, 조직, 상사, 동료, 구분하지 않음으로, 지지유형은 정서적, 도구적, 정보적, 평가적 지지로 나누어 하위집단분석을 실시하였다. 분석 결과, 지지자원과 지지유형 모두 일-가정 갈등 및 향상과 유의한 관계를 보였으며, 지지자원에 따라 일→가정에서는 갈등과 향상 모두 상사가, 가정→일에서는 갈등에는 가정이, 향상에는 배우자가 가장 유의하였고, 지지유형은 일-가정 갈등에서 일→가정은 평가적, 정서적 순으로, 가정→일은 평가적 정보적 순으로 유의하였다. 이상의 연구결과를 바탕으로 본 연구의 시사점과 한계를 제시하고 추후 연구를 위한 방향을 제언하였다. In this study, a meta-analysis was conducted on a total of 34 studies (14 academic papers, 20 dissertations in academic journals) conducted in Korea from 2000 to 2020 in order to understand the relationship between work-family conflict, work-family enhancement and social support. (N=17,530). Work-family conflict and work-family enhancement were used for analysis by dividing the direction into the case where the direction was not distinguished, the direction from work to home, and from home to work. The social support was divided into family, spouse, organization, supervisor, coworker, and not classified according to support resource, and a subgroup analysis was conducted. Depending on the type of support, a subgroup analysis was conducted by dividing into emotional, instrumental, informational, and appraisal support. As a result of the analysis, both support resources and types showed a significant relationship with work-family conflict and work-family enhancement. It was confirmed that the most significant relationship was changed according to each sub-factor and the direction of conflict and enhancement. Based on the above research results, the implications and limitations of this study were presented and directions for future research were suggested.

일-가정 갈등 예측요인에 대한 관련변인 메타분석

윤민지 ( Minjee Yoon ),공현정 ( Hyunjung Kong ),윤수란 ( Sooran Yoon ) 사단법인 아시아문화학술원 2021 인문사회 21 Vol.12 No.1

본 연구의 목적은 일-가정 갈등을 예측하는 관련변인들의 관계를 파악하는 것이다. 이를 위해 1999년부터 2020년까지 국내에서 이루어진 연구 총 31편(학술지 논문 13편, 학위논문 18편)에 대한 메타분석을 실시하였다(N=12,559). 본 연구에서는 일-가정 갈등 관련변인을 개인, 가정, 조직으로 구분하여 무선효과모형을 적용하고, 각 영역과 일-가정 갈등 간의 관계의 평균 효과크기를 구하였다. 그 결과 개인(r=.045), 가정(r=-275), 조직(r=.-173) 영역 순으로 일-가정 갈등을 예측하는 것으로 나타났다. 연구결과를 바탕으로 가정, 조직, 개인의 영역에서 일-가정 갈등을 완화할 수 있는 방안에 대해 논의하고 연구의 사례 수 등 연구가 갖는 한계를 밝혔으며, 추후 일-가정 양립 관련 메타분석에 대한 연구 방향을 제언하였다. A meta-analysis was conducted on a total of 31 studies conducted from 1999 to 2020 in order to understand the relationship between the related variables predicting work-family conflict(N=12,559). In this meta-analysis, to check the heterogeneity of the data and to analyze which variables these differences depend on, the average effect size of the relationship between each domain and the work-family conflict is determined by applying a random effect model divided into individual, family, and organization. As a result, it was found that individual (r=.045), family (r=-.275) and organization (r=-.173) predicted work-family conflict in order. Based on the above research results, the implications and limitations of this study were presented and directions for future research were suggested.

자연어 처리 기법을 활용한 판례 기반 모욕성 문장 분석 시스템

김가영(Ga-Young Kim),공현정(Hyeon-Jeong Kong),유석종(Seok-Jong Yu) 한국정보기술학회 2023 한국정보기술학회논문지 Vol.21 No.7

With the advent of social media, there has been a significant rise in the number of individuals openly engaging in online insults, thereby emerging as a notable social issue. In order to protect users from unpleasant experiences, online portal sites employ database-driven profanity filters to render offensive content invisible. However, these filters often fall short in preventing instances where individuals insult others by judging certain words, not classified as profanity, as offensive within a specific context. Therefore, this paper aims to propose a precedent-based insult sentence analysis system, utilizing advanced natural language processing techniques. The system leverages a deep learning model, rooted in precedents, to infer the likelihood of guilt associated with an insult sentence. Furthermore, the system presents users with comparable precedents through similarity analysis. The ultimate model was chosen based on the accuracy of the test dataset and the training dataset while ensuring enhanced accessibility by deploying it on the web.