• Journal of Periodontal and Implant Science
• /
• 제53권1호
• /
• pp.38-53
• /
• 2023

Purpose: The current Classification of Periodontal and Peri-Implant Diseases and Conditions, published and disseminated in 2018, involves some difficulties and causes diagnostic conflicts due to its criteria, especially for inexperienced clinicians. The aim of this study was to design a decision system based on machine learning algorithms by using clinical measurements and radiographic images in order to determine and facilitate the staging and grading of periodontitis. Methods: In the first part of this study, machine learning models were created using the Python programming language based on clinical data from 144 individuals who presented to the Department of Periodontology, Faculty of Dentistry, Süleyman Demirel University. In the second part, panoramic radiographic images were processed and classification was carried out with deep learning algorithms. Results: Using clinical data, the accuracy of staging with the tree algorithm reached 97.2%, while the random forest and k-nearest neighbor algorithms reached 98.6% accuracy. The best staging accuracy for processing panoramic radiographic images was provided by a hybrid network model algorithm combining the proposed ResNet50 architecture and the support vector machine algorithm. For this, the images were preprocessed, and high success was obtained, with a classification accuracy of 88.2% for staging. However, in general, it was observed that the radiographic images provided a low level of success, in terms of accuracy, for modeling the grading of periodontitis. Conclusions: The machine learning-based decision system presented herein can facilitate periodontal diagnoses despite its current limitations. Further studies are planned to optimize the algorithm and improve the results.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제23권4호
• /
• pp.1131-1148
• /
• 2009

이 논문에서는 대학에서 컴퓨터를 사용한 고급단계수학강좌의 방안 연구로서, ISETL 프로그램을 소개하고 그것을 활용한 대수학 강좌 방향을 모색하고자 한다.

• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.169-180
• /
• 2015

Recently, scheduling problems with position-dependent processing times have received considerable attention in the literature, where the processing times of jobs are dependent on the processing sequences. However, they did not consider cases in which each processed job has different learning or aging ratios. This means that the actual processing time for a job can be determined not only by the processing sequence, but also by the learning/aging ratio, which can reflect the degree of processing difficulties in subsequent jobs. Motivated by these remarks, in this paper, we consider a two-agent single-machine scheduling problem with linear job-dependent position-based learning effects, where two agents compete to use a common single machine and each job has a different learning ratio. Specifically, we take into account two different objective functions for two agents: one agent minimizes the total weighted completion time, and the other restricts the makespan to less than an upper bound. After formally defining the problem by developing a mixed integer non-linear programming formulation, we devise a branch-and-bound (B&B) algorithm to give optimal solutions by developing four dominance properties based on a pairwise interchange comparison and four properties regarding the feasibility of a considered sequence. We suggest a lower bound to speed up the search procedure in the B&B algorithm by fathoming any non-prominent nodes. As this problem is at least NP-hard, we suggest efficient genetic algorithms using different methods to generate the initial population and two crossover operations. Computational results show that the proposed algorithms are efficient to obtain near-optimal solutions.

• 정보교육학회논문지
• /
• 제26권3호
• /
• pp.153-165
• /
• 2022

본 연구는 독서와 공학을 융합한 수업 모델인 노벨 엔지니어링(이하 NE) 교육 프로그램에 관한 것이다. NE 수업의 도구로 VR 저작도구인 CospacesEdu를 이용하여 직접 가상현실을 설계하고 프로그래밍하는 과정을 포함함으로써, 해당 교육 프로그램이 학습자들의 융합인재소양과 학습몰입에 미치는 효과를 확인하였다. 교육 내용의 소재로는 독도 교육을 선정하여 진행하였다. 프로그램의 적용 결과 융합인재소양의 평균이 상승하였으며, 그 중 융합 영역에서 통계적으로 유의미한 변화를 확인하였다. 학습몰입은 총 5가지 하위 영역 중 과제와 능력의 균형 영역에서 유의미한 향상을 보였다. 반면 책 읽기로 시작하여 정보 수집, VR 설계, 이야기 바꿔쓰기까지 진행되는 차시가 긴 NE 수업 모델의 특성상 어려움을 느끼는 학생들이 있었다. 본 연구의 결과가 NE 수업 모델의 일반화에 도움을 주고, 새로운 방향을 제시하는 자료로 유용하게 활용되길 기대한다.

• 문화기술의 융합
• /
• 제2권2호
• /
• pp.29-35
• /
• 2016

기존의 교육용 로봇은 산업용 로봇을 사용하거나 토이 로봇을 사용하여 텍스트 기반으로 프로그램 하는 방식을 많이 사용하고 있으며 학습자들은 텍스트 기반 언어 문법으로 인해 로보틱스 학문에 대한 어려움을 겪는 경우가 많았다. 개발된 교육용 로봇은 카메라 및 컬러 트래킹 기능과 탈착 가능한 다양한 센서와 엑츄에이터 모듈, 오픈 하드웨어 지원 및 그래픽 언어기반으로 프로그램 방식을 가지고 있다. 본 연구에서는 최근 초중학교 소프트웨어 교육의 일환으로 사용되어지어 지고 있는 그래픽 모듈 조립방식의 스크래치를 기반으로 한 프로그램 방식을 사용하는 교육용 로봇을 개발하고 이를 현장 교육에 도입하는 새로운 교육 방식에 대해 언급하기로 한다. 또한 개발된 교육용 로봇을 대상으로 한 커리큘럼의 일례가 제시되었으며 실제 초등학교 학습에 적용한 결과 기존 교육에 비해 학생들의 창의성을 살린 교육의 수월성이 좋은 것으로 파악되었으며 이는 제시된 접근 방법이 타당하고 효율적이라는 것을 보여준다.

• 한국컴퓨터정보학회논문지
• /
• 제19권1호
• /
• pp.191-201
• /
• 2014

본 연구에서는 퍼즐 기반 학습에서 이루어지는 초등정보영재의 컴퓨팅적 문제 해결 접근법을 분석함으로써 퍼즐 기반 학습의 체계적 개선을 위한 시사점을 도출하고자 하였다. 이를 위해, 제약조건, 최적화, 확률, 통계, 패턴인식, 전략의 6가지 유형별 교육용 퍼즐을 구성하고 초등정보영재를 대상으로 퍼즐 기반 학습을 수행하였다. 또한 각 퍼즐 유형에 따른 학습자의 문제 해결 접근법을 확인하기 위해 사전 사후검사 결과의 정답률 및 정답자와 오답자의 문제 해결 접근법을 비교 분석하였다. 연구 결과, 각 퍼즐 유형별 빈번한 오류 발생의 원인인 몇 가지 양식 오류와 다양한 직관들을 확인하였으며, 오답자들은 '백트래킹', '동적 프로그래밍', '추상화', '모델링', '문제 축소'와 같은 컴퓨팅적 전략을 적용하지 못함으로 인해 완전한 해법에 도달하지 못한다는 것을 확인하였다. 이러한 분석 결과를 토대로 퍼즐 문제 표현 방식의 개선, 인지적 피드백의 적시 제공, 퍼즐 기반 학습 지원을 위한 웹 기반 시스템 개발 등 퍼즐 기반 학습 개선 방안을 제안하였다.

• International Journal of Advanced Culture Technology
• /
• 제6권2호
• /
• pp.107-116
• /
• 2018

In the past, design has been recognized as a means to determine colors, shapes, and functions Recently, however, it has been accepted in a wider sense, namely designing the entire service, including product and user experience design. In this way, in addition to creativity and expressive power that designers have as their main competence, according to the expansion of this design object, designers are required to have comprehensive abilities in related fields and accompanying technical professional abilities. If designing as a technology application as a direction toward this situation, design education can be carried out by approaching technology as a method of expression or design subject. It can also be an effective alternative towards improving the understanding of technology. Meanwhile, many small microcontroller board products with advanced functions and multi-functional specialized programming integrated development environments (IDEs) are becoming widespread due to their open source, low cost, and scalable features. However, students in the design department who lack the basic knowledge of science and engineering have difficulties learning, which requires considerable time and is required for practical use. From this point of view, we have made advancements in the technical understanding of design education by conducting fundamental research to the effectiveness of microcontroller-based prototyping tools as means of expression. We also conducted basic education of microcontroller boards for a certain period of time on students who majored in design in conjunction with the basic survey and investigated the obstacle factors using a questionnaire. Through these surveys, we have confirmed the necessity of designing microcontroller boards of low difficulty, which simplify the coding process that can act as a barrier in difficulty for design students to apply smoothly in design education. In addition, we intend to carry out a basic study on the guideline of microcontroller design for design education and composition of education programs.

• 한국정보과학회논문지:시스템및이론
• /
• 제33권12호
• /
• pp.894-906
• /
• 2006

모바일 기기의 성능 및 화면, 무선 네트워크의 속도 등의 제약으로 모바일 컨텐츠 개발에는 많은 어려움이 있다. 단순히 유선 웹상에서 기존에 서비스 되던 컨텐츠의 가시적인 축소만으로는 양질의 컨텐츠 제작이 어렵다. 빠르게 변화하는 모바일 컨텐츠 시장에 적응하기 위해서는 컨텐츠 특성에 최적화된 데이타 표현 기법 및 저작 도구의 개발이 이루어져야 한다. 본 논문에서는 모바일 기기 상에서의 한자 학습을 위한 적은 용량의 모바일 컨텐츠 및 저작 도구를 개발하였다. 본 연구에서 개발한 모바일 컨텐츠는 단순히 한자 이미지와 설명 정보를 보여주는 것이 아니라, 한자 획순으로 붓으로 쓰는 것과 같은 애니메이션 효과를 줄 수 있다. 또한 저작 도구는 사용자가 그래픽이나 한자, 모바일 프로그래밍에 관한 전문가가 아니더라도 쉽고 빠르게 컨텐츠를 생성할 수 있는 개발 환경을 제공한다. 본 논문은 트루타입 폰트로부터 글자 모양을 획득하여, 간단한 사용자 입력으로 획 분할 및 획 순서 정보를 얻고, 자동으로 획의 방향을 추출, 각 획마다 붓으로 쓰는 효과의 애니메이션을 생성한다. 다음으로 모바일 기기에서의 효율적인 글자 애니메이션을 위해 애니메이션 데이타를 압축한다. 본 논문은 한자뿐 아니라, 한글 또는 다른 형태의 그래픽에도 이용될 수 있으며, 향후 획 분할 및 획 순서 결정을 자동화하는 방법을 연구하고자 한다.

• 한국학교보건학회지
• /
• 제12권2호
• /
• pp.207-215
• /
• 1999

The objectives of this study are to explain the use of media materials in school health education with other related factors in elementary, middle, and high schools in Korea. The data were collected by questionnaires from June to September in 1998. The number of subjects were 294 school nurses. The PC-SAS program was used for statistical analysis such as percent distribution, chi-squared test, spearman correlation test, and logistic regression. The use of media materials in health education has become extremely common. Unfortunately, much of the early materials were of poor production quality, reflected low levels of interest, and generally did little to enhance health education programming. A recent trend in media materials is a move away from the fact filled production to a more affective, process-oriented approach. There is an obvious need for health educators to use high-quality, polished productions in order to counteract the same levels of quality used by commercial agencies that often promote "unhealthy" lifestyles. Health educators need to be aware of the advantages and disadvantages of the various forms of media. Selecting media materials should be based on more than cost, availability, and personal preference. Selection should be based on the goal of achieving behavioral objectives formulated before the review process begins. The decision to use no media materials rather than something of dubious quality usually be the right decision. Poor-quality, outdated, or boring materials will usually have a detrimental effect on the presentation. Media materials should be viewed as vehicles to enhance learning, not products that will stand in isolation. Process of materials is an essential part of the educational process. The major results were as follows : 1. The elementary schools used the materials more frequently. But the production rate of media materials was not enough. The budget was too small for a wide use of media materials in school health education. These findings suggest that all schools have to increase the budget of health education programs. 2. Computers offer an incredibly diverse set of possibilities for use in health education, ranging from complicated statistical analysis to elementary-school-level health education games. But the use rate of this material was not high. The development of related software is essential. Health educators would be well advised to develop a basic operating knowledge of media equipment. 3. In this study, the most effective materials were films in elementary school and videotapes in middle and high school. Film tends to be a more emotive medium than videotape. The difficulties of media selection involved the small amount of extant educational materials. Media selection is a multifaceted process and should be based on a combination of sound principles. 4. The review of material use following student levels showed that the more the contents were various, the more the use rate was high. 5. Health education videotapes and overhead projectors proved the most plentiful and widest media tools. The information depicted was more likely to be current. As a means to display both text and graphic information, this instructional medium has proven to be both effective and enduring. 6. An analysis of how effective the quality of school nurse and school use of media materials shows a result that is not complete (p=0.1113). But, the budget of health education is a significant variable. The increase of the budget therefore is essential to effective use of media materials. From these results it is recommended that various media materials be developed and be wide used.