• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.396-398
• /
• 2022

The endoscopic pathological findings of gastrointestinal tract (GIT) are important in the early diagnosis of colorectal cancer. Deep learning based on convolutional nueral network (CNN) has been implemented to solve the subjective analysis problem and to increase the performance of early detection of pathological findings. However, the desired performance is yet to be achieved and CNNs are computationally complex. To solve these problems, in this paper, we propose a vision transformer based endoscopic pathological findings classification for the early detection of colorectal cancer. Publicly available endoscopic images with three pathological findings, including esophagitis, polyps, and ulcerative colitis, each with 1000 images were used. Using our approach, we have achieved a test accuracy of 98% in classifying the three pathological findings.

• Steel and Composite Structures
• /
• v.44 no.4
• /
• pp.587-602
• /
• 2022

In this study, the classical J₂ flow theory is explicitly proved to be inappropriate to describe the plastic behaviour of structural steels under different stress states according to the reported test results. A numerical framework of the characterization of the strain hardening and ductile fracture initiation involving the effect of stress states, i.e., stress triaxiality and Lode angle parameter, is proposed based on the mechanical response of structural steels under monotonic loading. Both effects on strain hardening are determined by correction functions, which are implemented as different modules in the numerical framework. Thus, other users can easily modify them according to their test results. Besides, the ductile fracture initiation is determined by a fracture locus in the space of stress triaxiality, Lode angle parameter, and fracture strain. The numerical implementation of the proposed model and the corresponding code are provided in this paper, which are also available on GitHub. The validity of the numerical procedure is examined through single element tests and the accuracy of the proposed model is verified by existing test results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.745-747
• /
• 2023

깃허브는 개발자의 명함이라는 말이 있듯, 많은 수의 개발자들이 깃허브를 활용해 자신의 개발 이력과 프로젝트들을 관리한다. 이를 위해 기존의 깃허브 정보 요약 서비스들이 제공되어졌으나, 정보 공유의 불편함과 많은 정보를 담지 못한다는 불편함이 존재했다. 본 논문에서는 이러한 불편함을 해소하기 위해 서버 기반의 깃허브 웹 명함 제작 및 멀티플랫폼에서의 서비스를 기반으로 한 효율적인 개발자 명함 생태계 구축을 제안한다. 본 서비스에서는 Next.js 기술을 활용한 한 명함 제작 및 웹, 앱 클라이언트를 통한 명함 관리 기능을 제공한다. Github oauth를 통해 인증된 정보를 바탕으로 Next.js를 활용해 사용자에 대한 정보를 정해진 형식으로 요약한 명함을 제작한다. 제작된 명함은 웹 / 앱 플랫폼을 기반으로 관리되며, 추가적으로 명함의 공유 및 저장 기능을 수행한다. 이를 통해, 명함 공유를 바탕으로 한 개발자 네트워크 형성을 목표로 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.860-880
• /
• 2024

Breast cancer is a major health concern affecting women and men globally. Early detection and accurate classification of breast cancer are vital for effective treatment and survival of patients. This study addresses the challenge of accurately classifying breast tumors using machine learning classifiers such as MLP, AdaBoostM1, logit Boost, Bayes Net, and the J48 decision tree. The research uses a dataset available publicly on GitHub to assess the classifiers' performance and differentiate between the occurrence and non-occurrence of breast cancer. The study compares the 10-fold and 5-fold cross-validation effectiveness, showing that 10-fold cross-validation provides superior results. Also, it examines the impact of varying split percentages, with a 66% split yielding the best performance. This shows the importance of selecting appropriate validation techniques for machine learning-based breast tumor classification. The results also indicate that the J48 decision tree method is the most accurate classifier, providing valuable insights for developing predictive models for cancer diagnosis and advancing computational medical research.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.191-197
• /
• 2024

Software reuse gives the meaning for rapid software development and the quality of the software. Most of the Java components/libraries open-source are available only in Java Archive (JAR) file format. When a software design enters into the development process, the developer needs to select necessary JAR files manually via analyzing the given software architecture and related JAR files. This paper proposes an automated approach, JarBot, to suggest all the necessary JAR files for given software architecture in the development process. All related JAR files will be downloaded from the internet based on the extracted information from the given software architecture (class diagram). Class names, method names, and attribute names will be extracted from the downloaded JAR files and matched with the information extracted from the given software architecture to identify the most relevant JAR files. For the result and evaluation of the proposed system, 05 software design was developed for 05 well-completed software project from GitHub. The proposed system suggested more than 95% of the JAR files among expected JAR files for the given 05 software design. The result indicated that the proposed system is suggesting almost all the necessary JAR files.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.53-56
• /
• 2024

Though lots of approaches to develop mobile apps are suggested up to now, developers have difficulties selecting a right one. This study compares native and cross-platform application development approaches, particularly focusing on the shift in preference from Java to Kotlin and the increasing use of Flutter. This research offers practical insights into factors influencing developers' choice of programming languages and frameworks in mobile application development by creating identical applications using Java, Kotlin, and Dart (Flutter). Furthermore, this study explores the best practices for development by examining the quality of code in 45 open-source GitHub repositories. The study evaluates LOC and code smells using semi-automated SonarQube assessments to determine the effects of selecting a specific language or framework on code maintainability and development efficiency. Preliminary findings show differences in the quality of the code produced by the two approaches, offering developers useful information on how to best optimize language and framework selection to reduce code smells and improve project maintainability.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.86-95
• /
• 2011

Sensor nodes in wireless sensor networks are vulnerable to security than wired network due to using limited hardware performance and wireless communications that network topology changes frequently. Among techniques to enhance the security, the node authentication mechanism is used to defend against data forgery attacks using the ID of the node or to interfere with the routing of the network routing. In this paper, we proposed the AM-E mechanism that makes authentication key by using the energy value of node requesting authentication and performs the communication procedures for data transfer between different nodes. Because the energy value of node is changed depending on time, every time the authentication request is, an authentication key is changed. These features enhance the security of sensor networks and will help to configure the more secure WSN.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.1
• /
• pp.441-448
• /
• 2014

USN(Ubiquitous Sensor Network) application software has a characteristic that it controls a variety of sensor nodes based on the various target operating systems. Accordingly, many researches for efficient development of USN application software are being performed. In this paper, the attributes design technique to support attribute-based development of USN node software for multi-platform is proposed. In the proposed technique, the method to design attributes for modeling Platform Independent Model and Platform Specific Model is presented. When using the proposed technique, productivity of software development will be increased because node software design for multi-platform is easily performed by selecting values of attributes. Also, maintainability of software will be increased because node software is easily regenerated by changing attributes according to the changes of operating systems.

• Fashion & Textile Research Journal
• /
• v.14 no.4
• /
• pp.607-613
• /
• 2012

This study develops a Hanbok Jeogori pattern for middle-aged women with a 3D virtual-twin and virtual-garment simulation system. The including criteria for subjects in this study was a focus on women in their 50s, and a total of 345 females satisfying them were enrolled for 3D virtual model. Comparative Jeogori pattern, Baik & Choi's(2004) pattern, was selected for the development of Jeogori pattern. The results were: first, a new Jeogori pattern considerate of middle-aged women was developed. The basic numerical formula were: Front and back bust girth B/4+1.5, armhole depth B/4, sleeve width B/4, goedae width B/10-1.5 and git width 5.5. Second, according to the results of the new Jeogori patterns appearance evaluation, the new Jeogori pattern scored higher than the existing pattern in silhouette and ease amount, this confirmed that the new Jeogori pattern is appropriate for middle-aged women. Virtual models of production through data from 3D body scan, pattern draft, and virtual garment digital program were applied to a prototypic design method to enhance the fitness of ready-made Hanbok garments. This study serves as important basic data for ensuing studies that may utilize 3D Virtual Garment Simulation System with 2D patterns and for the future 3D Pattern Production Program development of Hanbok patterns.

• Human Ecology Research
• /
• v.52 no.4
• /
• pp.347-354
• /
• 2014

'Heongbu and Nolbu 1' is a series of the on-line game 'Tales Runner.' It is based on a traditional Korean fairy tale. However, the game characters in Heongbu and Nolbu 1 wear casual clothes even though the game is set in the Joseon Dynasty. Therefore, this paper presents proposed game characters clothes based on traditional Korean costumes from the Joseon Dynasty. This work should help inspire gamers and game designers with the beauty of Korean traditional costumes and familiarize them with an aspect of Korean people's identity. A literature review of online games and game characters was carried out, and game characters' clothes were analyzed. The design motifs of historical relics of the Joseon era were evaluated. Three styles, one traditional and two "fusion" styles integrating traditional and modern elements were proposed for each of the 4 characters: Chowon, Ruff, Bada and Abell. The chulrik and jurip were used as design motifs for Chowon. A traditional chulrik, short chulriks and pants are suggested. Second, the dongari and jeonrip were used as design motifs for Ruff. A traditional dongdari, sapok pants, deck pants and a vest are suggested. Third, the jeogori and chima were used as design motifs for Bada. A traditional female hanbok, arm warmers, short-sleeved jeogori and dress are suggested. Fourth, the dang-ui and daeran-chima were used as design motifs for Abell. A traditional dang-ui and daeran-chima, blouse, skirt, jumper and tight Bermuda shorts are suggested. The length, shape and color were converted into new styles, but some traditional elements such as the git and goreum were retained.