• Journal of Korean Medical Science
• /
• 제33권43호
• /
• pp.239.1-239.12
• /
• 2018

Background: We described a novel multi-step retinal fundus image reading system for providing high-quality large data for machine learning algorithms, and assessed the grader variability in the large-scale dataset generated with this system. Methods: A 5-step retinal fundus image reading tool was developed that rates image quality, presence of abnormality, findings with location information, diagnoses, and clinical significance. Each image was evaluated by 3 different graders. Agreements among graders for each decision were evaluated. Results: The 234,242 readings of 79,458 images were collected from 55 licensed ophthalmologists during 6 months. The 34,364 images were graded as abnormal by at-least one rater. Of these, all three raters agreed in 46.6% in abnormality, while 69.9% of the images were rated as abnormal by two or more raters. Agreement rate of at-least two raters on a certain finding was 26.7%-65.2%, and complete agreement rate of all-three raters was 5.7%-43.3%. As for diagnoses, agreement of at-least two raters was 35.6%-65.6%, and complete agreement rate was 11.0%-40.0%. Agreement of findings and diagnoses were higher when restricted to images with prior complete agreement on abnormality. Retinal/glaucoma specialists showed higher agreements on findings and diagnoses of their corresponding subspecialties. Conclusion: This novel reading tool for retinal fundus images generated a large-scale dataset with high level of information, which can be utilized in future development of machine learning-based algorithms for automated identification of abnormal conditions and clinical decision supporting system. These results emphasize the importance of addressing grader variability in algorithm developments.

• 한국터널지하공간학회 논문집
• /
• 제23권6호
• /
• pp.423-438
• /
• 2021

모터 그레이더의 블레이드는 도로공사시 골재를 산포하고 평탄화하는 역할을 수행한다. 본 연구는 그레이더의 작업효율을 향상시키기 위하여 블레이드 부품의 설계개선 연구를 진행하였다. 블레이드와 골재 입자의 접촉, 절삭, 산포 과정을 모사하기 위하여 동해석 코드에 개별요소법을 도입하여 전산해석 모델을 수립하였다. 블레이드 설계인자를 4가지 선별한 후 작업 시나리오를 수립하였다. 실험계획의 직교배열을 통해 각 인자의 수준조합별 9개 모델에 대해 평탄화 작업에 대한 동해석을 수행하고, 각 설계인자의 영향도를 분석하였다. 이후 유의한 인자를 분산분석을 통해 선별하여 최적화기법으로 점진적 반응표면법을 적용하였다. 최종적으로 블레이드의 작업 효율성을 향상시킬 수 있도록 설계인자의 최적값을 제안하였다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2005년도 동계 학술대회 논문집
• /
• pp.281-285
• /
• 2005

• 한국수학교육학회지시리즈A:수학교육
• /
• 제55권4호
• /
• pp.447-465
• /
• 2016

The purpose of this study is to analyze longitudinal trends of students' mathematical affective domain by use of the data mining method. For this purpose, we used the Korea education longitudinal study(KELS 2005) which was the survey data for students' achievement test, affective domain test, teachers' evaluation, and parents' evaluation from $7^{th}$ grader in the year of 2005 to $11^{th}$ grader in the year of 2010. Subjects of this study is a total of 5040 students who answered to the mathematical affective domain survey in KELS 2005. The result findings are as follows. First, students' affective domain had changed negatively as they went up to higher grade. Second, if students' affective domain had built at a certain level in $7^{th}$ grade, the level did not change easily until $11^{th}$ grade. Third, major factors of students' affective domain were shown to be self-efficacy, intrinsic motivation, efforts and patient, and time management.

• Journal of Biosystems Engineering
• /
• 제30권3호
• /
• pp.172-178
• /
• 2005

Grading and sorting an indeterminate form of agricultural products such as sweet potatoes and potatoes are a labor intensive job because its shape and size are various and complicate. It costs a great deal to sort sweet potato in an indeterminate forms. There is a great need for an automatic grader fur the potatoes. Machine vision is the promising solution for this purpose. The optical indices for qualifying weight and appearance quality such as shape, color, defects, etc. were obtained and an on-line sorting system was developed. The results are summarized as follows. Sorting system combined with an on-line inspection device was composed of 5 sections, human inspection, feeding, illumination chamber, image processing & control, and grading & discharging. The algorithms to compute geometrical parameters related to the external guality were developed and implemented for sorting the deformed sweet potatoes. Grading accuracy by image processing was $96.4\%$ and the processing capacity was 10,800 pieces per hour.

• 보건교육건강증진학회지
• /
• 제1권1호
• /
• pp.12-20
• /
• 1983

Primary responsibility for the health of the school-age child rests with the parents, but the school should assist the parents in establishing and maintaining the highest possible level of health in each child. The important part of school health program is health education. All kinds of testbooks for elementary school were newly developed from 1982 for the 1st to 3rd grader and from 1983 for the 4th to 6th grader. The purposes of this study were to analyse the newly developed health curriculum in elementary school and to point out the errors in contents or terminology. Data were collected from all kinds of textbooks for elementary school which have been using in 1983. On the bases of these data, the following findings were observed: 1) 22.4 percents of total pages which related to health were from athletic subject. 2) Almost 29 percents of learning experiences suggested from textbooks were explanation and teach-centered. 3) The main subjects of health related contents were preventional management and environmental health. 4) 22 errors were found out, they were 12 for contents itself correction, 6 for terminology correction, 3 for lack of explanation and 1 for expurgation.

• 한국과학교육학회지
• /
• 제24권1호
• /
• pp.146-156
• /
• 2004

The purpose of this study is to look at the use of heuristics when a sixth grader solves a problem. Two research questions have been formulated: The similarities and differences in the use of heuristics when a student solves two problems that are science-knowledge-based and not science-knowledge-based, and the different types of prompts. A male sixth grade student participated in this study. All of the information for the study was collected in three interviews. The interviews began with observing the student's solving problems. The student was asked how and why he solved problem that way. There were some interactions between the researcher and the student during the interview procedures. As results of this study, eight general heuristics were used in both solutions: Check examples for support of an idea: check examples for exceptions to an idea: restate the problem: compare to known examples or patterns: make a hypothesis; check the relevance of other information present; use analogy: and recognize patterns/similarity. There seemed to be more similarities than differences in the type of general heuristic that were used in the two problem solutions. The student was systematic and consistent in his use of the general use of heuristics. Five types of interviewer prompts were detected in the two problem solutions, directional cues, modeling, clarity, problem posing, metacognition and validation.

• 한국기계가공학회지
• /
• 제20권1호
• /
• pp.88-94
• /
• 2021

Currently, the Busan cooperative fish market follows a traditional market style. This study first investigates the current conditions and environment of the market, and to modernize the market, it proposes a new automatic unloading system based on the benchmark of Namhae Suhyup. In this system, a Korean-type suction fish vacuum pump is employed to increase the loading time. An automatic grader with an adjusting device for inclined angles and a weighing machine with an automatic alignment device are proposed. In addition, a folding machine is employed to prepare boxes. The specifications for each subsystem are provided. By implementing this system, the freshness of fish can be maintained and the sellers can earn more. This system can also be applied to the cooling system of the fish reservoir of littoral sea fishing boats.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.405-406
• /
• 2017

Everycoding은 인텔리전트 코딩 교육 시스템으로, 코딩 교육을 위한 다양한 콘텐츠 및 코딩 보조 도구를 제공한다. 특히, 코드 자동 평가 기능을 교육적 목적으로 활용함으로써, 비전공자들이 쉽게 코딩을 익힐 수 있게 도움을 주고 있다. 본 논문에서는 Everycoding에서 제공하는 코드 자동 평가 기능에 대하여 소개한다.

• 한국콘텐츠학회논문지
• /
• 제14권8호
• /
• pp.185-196
• /
• 2014

본 연구는 청소년의 결손가정요인이 공동체의식에 미치는 영향에서 부모관계, 친구관계, 교사관계, 이웃관계 등 관계적 요인의 매개효과를 검증하고자 하였다. 이를 위해 한국 아동 청소년패널조사 2012년 3차년도 자료 중에서 초등학교6학년과 중학교 3학년 4,362명의 데이터를 사용하였다. 분석결과 분석대상자들의 일반적 특성에 따른 공동체 의식의 차이에서는 여학생이, 중학교 3학년이, 건강하다고 인식하는 경우, 결손이 없는 가정인 경우가 공동체 의식에 미치는 영향에 유의미한 차이가 있는 것으로 나타났다. 또한 청소년의 결손가정 요인이 공동체의식에 미치는 영향에서는 부모관계, 교사관계, 친구관계, 이웃관계의 관계적 요인이 유의미한 매개효과를 보여주면서 부모구성에 따른 결손가정요인의 영향력이 유의미하지 않게 감소된 것을 확인할 수 있었다. 결론적으로 청소년에게 있어서 관계적 요인을 강화할 수 있는 다양한 프로그램의 개발과 제도적 장치의 마련이 필요할 것이다.