인공지지체 불량 검출을 위한 딥러닝 모델 성능 비교에 관한 연구

이송연,허용정,Lee, Song-Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.2

When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.

멘토링을 통한 예비화학교사들의 Pedagogical Content Knowledge 변화

이송연 ( Song Yeon Lee ),민희정 ( Hee Jung Min ),원정애 ( Jeong Ae Won ),백성혜 ( Seoung Hey Paik ) 한국과학교육학회 2011 한국과학교육학회지 Vol.31 No.4

이 연구의 목적은 예비화학교사들의 PCK가 어떠한지 분석해보고, 교육실습 전·후의 멘토링 과정을 통해 예비화학교사의 PCK에는 어떤 변화가 있는지 알아보는 것이다. 이를 위해 화학교육을 전공하는 4명의 예비교사를 멘티로 선정하고, 화학교육과 교수 한명을 멘토로 선정하였다. 예비교사의 PCK를 분석하기 위하여 멘티의 수업과 멘토링 과정, 면담 녹음 등의 자료를 수집하였다. 연구결과, 멘토링 전 멘티들은 거의 모든 PCK요소에서 부족함을 보였다. 이는 그들이 수업을 위한 실천적 지식의 필요성을 알지 못했고, 배운 지식을 어떻게 적용하는지 몰랐기 때문이다. 그러나 대부분의 멘티들은 멘토링을 통해서 PCK를 발달시켰다. 이 연구는 예비 교사들을 위한 대학교육에서 교육 실습 전 후에 잘 구성된 멘토링을 통해 예비교사의 PCK를 효과적으로 발달시킬 수 있음을 시사한다. The purposes of this study were to analyze the PCK of pre-service chemistry teachers and to know the changes of in PCK before and after the educational practice. For this study, four pre-service teachers majoring in chemistry education were selected as proteges and one professor of chemistry education department participated as a mentor. For the analysis of pre-service teachers` PCK, proteges` instructions, mentoring process, and semi-constructed interviews were collected. According to the results, most of the elements of the PCK were lack of proteges` instructions before the mentoring, because they didn`t know the necessary practical knowledge for instructions. They also didn`t know how they could apply their knowledge to the instructions. However, most of the pre-service teachers developed their PCK through the mentoring. This study shows that pre-service teacher`s PCK could develop effectively by well-formed programs of mentoring before and after the educational practice in college education for pre-service teachers.

묽은 용액의 성질에 대한 화학전공 예비교사들의 이해 및 화학교사 양성교육에 대한 인식 사례 연구

이송연,김성혜,백성혜,Lee, Song-Yeon,Kim, Soeng-Hye,Paik, Seoung-Hey 대한화학회 2010 대한화학회지 Vol.54 No.6

이 연구에서는 화학교육을 전공하는 4명의 예비교사들과 화학을 전공한 2명의 예비교사들을 대상으로 고등학교 화학II 교과서에 제시된 "묽은 용액의 성질" 단원에 관련된 개념의 이해를 비교하였다. 연구결과, 예비교사들 중에 고등학교 화학II 교과서에 제시된 내용을 깊이 있게 이해하는 예비교사들이 많지 않았으며, 묽은 용액의 성질에 관련된 오개념을 가지고 있는 경우도 나타났다. 그리고 사범대학에서 화학교육을 전공한 예비교사들의 이해수준과 비사범대학에서 화학을 전공한 예비교사들의 이해수준은 차이가 없는 것으로 나타났다. 연구에 참여한 대부분의 예비교사들은 대학과 상관없이 그들의 예비교사 교육과정에서 실천적 지식이 부족하다고 느끼고 있었다. We compared the understanding of 4 pre-service teachers of chemistry education major and 2 pre-service teachers of chemistry major related to conceptions of "properties of dilute solutions" chapter in high school Chemistry II textbooks. As results, few pre-service teachers understood fully the concepts of high school Chemistry II textbooks. Some pre-service teachers had misconceptions related to properties of dilute solutions. We found that few differences existed between the pre-service teachers' understanding regardless of whether they took a major in chemistry education of a education college or a major in chemistry of noneducation college. Most of the pre-service teachers who attended this research recognized the lack of practical knowledge in their pre-service teacher curriculum.

머신 러닝 회귀 방안을 이용한 인공지지체 기공 크기 예측모델 성능에 관한 연구

이송연,허용정,Lee, Song-Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2020 반도체디스플레이기술학회지 Vol.19 No.1

In this paper, We need to change all print factors when which print scaffold with 400 ㎛ pore using FDM 3d printer. Therefore the print quantity is 10 billion times, So we are difficult to print on workplace. To solve the problem, we used the prediction model based machine learning regression. We preprocessed and learned the securing print condition data, and we produced different kinds of prediction models. We predicted the pore size of scaffolds not securing with new print condition data using prediction models. We have derived the print conditions that satisfy the pore size of 400 ㎛ among the predicted print conditions of pore size. We printed the scaffolds 5 times on the condition. We measured the pore size of the printed scaffold and compared the average pore size with the predicted pore size. We confirmed that error was less than 1%, and we were identify the model with the highest pore size prediction performance of scaffold.

문화예술교육을 위한 행정지원책에 대한 방안 연구

이송연 ( Lee Song Yeon ) 경남대학교 교육문제연구소 2021 敎育理論과 實踐 Vol.29 No.-

본 논문은 문화예술교육을 위한 행정지원책에 대한 지원 방안 연구를 주제로 작성하였다. 논문의 연구의 목적은 문화예술에 대한 적절한 행정지원의 중요성을 밝히고 다양한 측면의 지원방법과 고려해야할 요소에 대해 알아보며 대상에 따른 지원사례와 방향성에 대한 분석을 바탕으로 문화예술계에 대한 행정지원책에 대한 방안을 강구해보는 것이다. 연구방식은 문헌연구를 중심으로 진행하였으며, 문화예술교육과 행정적 지원에 대한 선행논문, 보고서 등을 통해 이론적 배경과 행정적 지원에 대해 분석해보았다. 그 결과 문화예술교육이 가지는 역할과 그 가치에 관해서는 다수의 사람들이 그 중요성에 동의하고 있지만, 다양한 이유에서 문화예술교육은 가장 우선시 되지는 않는다. 따라서 문화예술에 대한 철학적 관점의 논의가 지속적으로 이루어져야 하며, 다양한 측면에서 행정지원에 대한 방법을 지속적으로 고민할 필요가 있다. 현장의 요구를 반영한 현실성 있는 문화예술정책과 적절한 행정지원을 바탕으로 집행 가능한 예산을 지원해야 하며, 사회문화적으로 마땅히 가치 있는 방향으로 행정적 지원이 이루어져야 함은 분명하다. 적재적소의 효율성 있는 적극적인 행정지원은 장기적인 발전을 위해서는 체계적이고 조직적인 구조, 행정시스템에 대한 특별예산 편성, 행정인력에 대한 중요성 인식과 제고를 위한 노력 등이 필요하다. This paper was prepared under the theme of research on support measures for administrative support measures for culture and arts education. The purpose of the thesis is to clarify the importance of appropriate administrative support for culture and arts, to find out various aspects of support methods and factors to be considered, and to devise administrative support measures for the culture and arts community based on analysis of support cases and directions. The research method was conducted focusing on literature research, and the theoretical background and administrative support were analyzed through prior papers and reports on culture and arts education and administrative support. As a result, many people agree with the importance of the role and value of culture and arts education, but culture and arts education is not the top priority for various reasons. Therefore, it is necessary to continuously discuss the philosophical perspective on culture and arts, and to continuously consider the method of administrative support from various aspects. It is clear that the executable budget should be supported based on realistic cultural and artistic policies reflecting the needs of the field and appropriate administrative support, and administrative support should be provided in a socially and culturally valuable direction. Efficient and active administrative support in the right place requires systematic and organizational structure, special budgeting for administrative systems, and efforts to recognize and enhance the importance of administrative personnel for long-term development.

재난심리 지원에 대한 국민 인식도 조사

이송은(Song-Eun Lee),이나빈(Nabin Lee),유선영(Seonyoung Yoo),박도원(Dowon Park),전경선(Kyoungsun Jeon),황태연(Tae-Yeon Hwang),이정현(Jung Hyun Lee) 대한신경정신의학회 2021 신경정신의학 Vol.60 No.1

Objectives This study examined post-disaster mental health problems and related public perception of disaster-related mental health services. The differences of these perceptions according to the disaster experience and disaster type were also investigated. Methods Data were collected via telephone and online surveys, and information from 2928 respondents was analyzed. The participants were allocated across age, sex, and residence area. Results Those who had experienced disasters showed a more negative perception of post-disaster mental health services than those who had not. While natural disaster survivors most often reported financial problems as secondary stressors after a disaster, social disaster survivors were more likely to report mental health problems. Regarding national mental health support for disaster, disaster-experiencing respondents more often tended to prefer mental health services than non-disaster-experiencing respondents. Conclusion The current study can help understand the public perception of disaster-related mental health and the needs of mental health services. These findings could suggest directions and grounds for policies of a national support system for disaster-related mental health.

다중 선형 회귀 기반 기계 학습을 이용한 인공지지체의 사각 기공 형태 진단 모델에 관한 연구

이송연,허용정,Lee, Song-Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2020 반도체디스플레이기술학회지 Vol.19 No.4

In this paper, we found the solution using data based machine learning regression method to check the pore shape, to solve the problem of the experiment quantity occurring when producing scaffold with the 3d printer. Through experiments, we learned secured each print condition and pore shape. We have produced the scaffold from scaffold pore shape defect prediction model using multiple linear regression method. We predicted scaffold pore shapes of unsecured print condition using the manufactured scaffold pore shape defect prediction model. We randomly selected 20 print conditions from various predicted print conditions. We print scaffold five times under same print condition. We measured the pore shape of scaffold. We compared printed average pore shape with predicted pore shape. We have confirmed the prediction model precision is 99 %.

CNN 알고리즘을 이용한 인공지지체의 3D프린터 출력 시 실시간 출력 불량 탐지 시스템에 관한 연구

이송연,허용정,Lee, Song Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.3

Scaffold is used to produce bio sensor. Scaffold is required high dimensional accuracy. 3D printer is used to manufacture scaffold. 3D printer can't detect defect during printing. Defect detection is very important in scaffold printing. Real-time defect detection is very necessary on industry. In this paper, we proposed the method for real-time scaffold defect detection. Real-time defect detection model is produced using CNN(Convolution Neural Network) algorithm. Performance of the proposed model has been verified through evaluation. Real-time defect detection system are manufactured on hardware. Experiments were conducted to detect scaffold defects in real-time. As result of verification, the defect detection system detected scaffold defect well in real-time.

CNN 기반 딥러닝을 이용한 인공지지체의 외형 변형 불량 검출 모델에 관한 연구

이송연,허용정,Lee, Song-Yeon,Huh, Yong Jeong 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.1

Warpage defect detecting of scaffold is very important in biosensor production. Because warpaged scaffold cause problem in cell culture. Currently, there is no detection equipment to warpaged scaffold. In this paper, we produced detection model for shape warpage detection using deep learning based CNN. We confirmed the shape of the scaffold that is widely used in cell culture. We produced scaffold specimens, which are widely used in biosensor fabrications. Then, the scaffold specimens were photographed to collect image data necessary for model manufacturing. We produced the detecting model of scaffold warpage defect using Densenet among CNN models. We evaluated the accuracy of the defect detection model with mAP, which evaluates the detection accuracy of deep learning. As a result of model evaluating, it was confirmed that the defect detection accuracy of the scaffold was more than 95%.

All-in-one 센서 디바이스 보드를 위한 전용 프로토콜 설계

이송연(Song-Yeon Lee),이현진(Hyun-Jin Lee),홍선영(Sun-Young Hong),이상석(Sang-Suk Lee),김영훈(Young-Hoon Kim),백종호(Jong-Ho Paik) 한국정보과학회 2016 한국정보과학회 학술발표논문집 Vol.2016 No.6