• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.267-275
• /
• 2023

This paper presents the development of specialized software for annotating volume-of-interest on ¹⁸F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within ¹⁸F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding ¹⁸F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with ¹⁸F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.628-630
• /
• 2005

유비쿼터스 컴퓨팅 환경의 중요한 이슈 중 하나인 상황인식은 컴퓨팅환경(예를 들어 가용 처리장치, 사용자 입력과 표시를 위한 장치, 네트워크 수용량, 다른 기기와의 접속용이성 및 컴퓨팅비용 등), 사용자 환경(위치, 주위 사람들과의 접촉, 사회적 입장 등) 및 물리적 환경(밝기, 소음, 온도 등)이 지속적으로 변화하는 수행 환경에서 인간으로 하여금 본연의 목적을 달성하는데 집중할 수 있도록 지원하는 인간 친화적인 시스템을 제공하기 위한 필수 기술이다. 이러한 상황인식을 이용하여, 사람이나 장소 및 사물의 입장이나 처지 혹은 관계 등을 특징 지을 수 있는 신원, 위치, 상태(혹은 활동) 및 시간의 4가지 상황정보를 고려한 학습이 이루어지도록 지원함으로써 학습에 있어서의 접근용이성과 적응성을 높이기 위한 컨텐츠 전승제어 시스템을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1653-1656
• /
• 2000

필기체 서체 인식은 온라인 문자 인식 시스템에서 주로 사용되는 시스템이다. 또한 오프라인 문자 인식 시스템은 문자 인식에만 초점이 맞추어져 있는 상황이다. 본 논문에서는 오프라인 방식으로 기초의 문자 인식에만 머물던 시스템을 문자 익히기까지 행할 수 있는 시스템으로 확장하는 방법을 제안 하고자 한다. 이를 위해 신명조체 80포인트에 대한 표준문자패턴을 생성하고, 유사도함수를 정의하며 이를 통해 입력 문자 패턴과의 유사성을 계산하여 문자 익히기를 행하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.603-605
• /
• 2018

최근 대두되고 있는 딥 러닝은 학습을 통해 사물이나 데이터를 군집화하거나 분류하는 데 사용하는 기술이다. 본 논문은 딥 러닝에 활용하기 위해 개발된 오픈소스 소프트웨어인 텐서플로 Inception V3을 사용해 연구를 진행했다. 딥 러닝을 활용한 씨앗 발아 확인 시스템은 기존의 영상 처리를 활용한 시스템에서 고안했으며, 씨앗 발아 여부의 정확성이 떨어지는 단점을 개선하고, 모든 종자들의 발아 여부를 확인할 수 있도록 구현해 사용자가 효과적으로 연구를 수행할 수 있도록 하는 목적에 있다.

• Educational Technology International
• /
• v.24 no.1
• /
• pp.53-80
• /
• 2023

This study investigates faculty support for quality assurance in online education, and offers suggestions for its improvement based on feedback from Instructional Design (ID) staff working at a public university in the U.S. Qualitative research using semi-structured interviews was conducted with seven ID staff in order to examine their perceptions regarding faculty support related to quality assurance in online education. The results of the data analysis indicate that four types of faculty support-quality assurance reviews using Quality Matter (QM) standards, templates, individual consultations with ongoing support, and monitoring-were offered for faculty. Faculty support for quality assurance in online education could be improved by developing specific quality assurance standards, recruiting external experts, examining learning effects, developing a quality assurance management system, and sharing documents among ID staff. This study highlights the necessity of quality assurance in online education and provides cases of faculty support in a real higher education setting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.534-535
• /
• 2020

본 논문에서는 딥러닝과 지식베이스를 융합하여 활용한 질환 인식 및 식품 추천 시스템을 제안한다. 제안하는 시스템은 온전히 모바일 디바이스 내에서 작동하는 시스템이다. 본 시스템은 압축된 딥러닝 모델을 이용해 사용자 대화 텍스트를 분석하여 사용자의 질환을 예측한다. 그 후, 지식베이스를 기반으로 해당 질환 관리에 도움이 되는 식품을 매칭하고 사용자에게 추천한다. 이는 사용자 친화적 헬스케어 애플리케이션으로써 체크리스트 작성 등 번거로운 작업 없이도 사용자에게 유용한 건강 정보를 제공할 수 있다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.280-286
• /
• 2024

In this paper, layered UNet with warmup and dropout tricks was used to segment teeth instantly by using data labeled for each individual tooth and increase performance of the result. The layered UNet proposed before showed very good performance in tooth segmentation without distinguishing tooth number. To do instance segmentation of teeth, we labeled teeth CBCT data according to tooth numbering system which is devised by FDI World Dental Federation notation. Colors for labeled teeth are like AI-Hub teeth dataset. Simulation results show that layered UNet does also segment very well for each tooth distinguishing tooth number by color. Layered UNet model using warmup trick was the best with IoU values of 0.80 and 0.77 for training, validation data. To increase the performance of instance segmentation of teeth, we need more labeled data later. The results of this paper can be used to develop medical software that requires tooth recognition, such as orthodontic treatment, wisdom tooth extraction, and implant surgery.

• Journal of the Korean School Mathematics Society
• /
• v.17 no.4
• /
• pp.437-464
• /
• 2014

Curriculum for mathematic sis the system that selects and organizes the contents which have to be taught in school. Ultimately it can be the whole plan of school mathematical education. The study about curriculum for mathematics is the basic study field of the mathematical education, so curriculum-related studies have been continuously promoted in terms of character, organization and implement of the curriculum, learning contents contained by the curriculum, the connection between school levels, and comparison and analysis of domestic and foreign curricula. Thus, this paper investigated the 2009 Revised Curriculum for Mathematics, which is the curriculum of Korea and the CCSSM which is the curriculum of the U.S. Both have been adopted in schools recently. The purpose of this study is to understand the curricula for mathematics in elementary school of Korea and the U.S. in depth and obtain the implication for the further curriculum revision, by comparing and analyzing the curricula of two countries.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.1
• /
• pp.103-111
• /
• 2023

Accurate cost estimation in the early stages of a construction project is critical to the successful execution of the project. In this study, an ANFIS model was presented to predict construction costs in the early stages of a construction project. To increase the usability of the model, open construction cost data was used, and a model using limited information in the early stage of the project was presented. We analyzed existing studies related to ANFIS to identify recent trends, and after reviewing the basic structure of ANFIS, presented an ANFIS model for predicting conceptual construction costs. The variation in prediction performance depending on the type and number of membership functions of the ANFIS model was analyzed, the model with the best performance was presented, and the prediction accuracy of representative machine learning models was compared and analyzed. Through comparing the ANFIS model with other machine learning models, it was found to show equal or better performance, and it is concluded that it can be applied to predicting construction costs in the early stage of a project.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.423-429
• /
• 2006

The systems in the ubiquitous computing environment need to provide users with context-aware services, intelligently interacting with the surrounding environment. Therefore, the systems in the ubiquitous computing environment require context-awareness ability in order to gather and analyze context information in various situations and environments. However, existing context-aware systems lack the ability to systematically generate and handle various types of context information, and only a few systems have ability learning from environment. In this paper, a general context model is defined to describe various contexts and a context-awareness framework is implemented based in the model, which makes it straightforward to handle and generate various types of context from diverse sensor. The framework is designed to allow a system to sensed, combined, inferred, and learned context information, in order to provide users with services in dynamic environments. We have implemented the proposed framework and applied it to a u-Health management system.