• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.289-294
• /
• 2019

As social network service platforms grow and one-person media market expands, people upload their own photos and/or videos through multiple open platforms. However, it can be illegal to upload the digital contents containing the faces of others on the public sites without their permission. Therefore, many people are spending much time and effort in editing such digital contents so that the faces of others should not be exposed to the public. In this paper, we propose an automatic face hiding system called 'autoblur', which detects all the unregistered faces and mosaic them automatically. The system has been implemented using the GitHub MIT open-source 'Face Recognition' which is based on deep learning technology. In this system, two dozens of face images of the user are taken from different angles to register his/her own face. Once the face of the user is learned and registered, the system detects all the other faces for the given photo or video and then blurs them out. Our experiments show that it produces quick and correct results for the sample photos.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.908-928
• /
• 2022

Multiple target tracking mainly focuses on tracking unknown number of targets in the complex environment of clutter and missed detection. The generalized labeled multi-Bernoulli (GLMB) filter has been shown to be an effective approach and attracted extensive attention. However, in the scenarios where the clutter rate is high or measurement-outliers often occur, the performance of the GLMB filter will significantly decline due to the Gaussian-based likelihood function is sensitive to clutter. To solve this problem, this paper presents a robust GLMB filter and smoother to improve the tracking performance in the scenarios with high clutter rate, low detection probability, and measurement-outliers. Firstly, a Student-T distribution variational Bayesian (TDVB) filtering technology is employed to update targets' states. Then, The likelihood weight in the tracking process is deduced again. Finally, a trajectory smoothing method is proposed to improve the integrative tracking performance. The proposed method are compared with recent multiple target tracking filters, and the simulation results show that the proposed method can effectively improve tracking accuracy in the scenarios with high clutter rate, low detection rate and measurement-outliers. Code is published on GitHub.

• 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 Water Resources Association Conference
• /
• 2019.05a
• /
• pp.372-372
• /
• 2019

본 논문에서는 격자 기반의 2차원 침수해석 모형인 G2D(Grid based 2-Dimensional land surface flood model)의 GUI 개발에 대해서 기술하였다. G2D 모형은 ASCII 래스터 포맷의 DEM을 이용하여 정형 사각격자로 구성되는 침수모의 도메인을 설정하고, 수위, 수심, 유량 등의 경계조건과 강우와 유량을 연속방정식의 생성항으로 사용하여 2차원 침수모의를 한다. 주요한 침수모의 결과는 ASCII 래스터 포맷을 가지는 수심과 수위 등이다. 이와 같이 G2D 모형은 ASCII 래스터 파일을 주로 이용하고 있다. 본 연구에서는 우선 래스터 파일의 전후처리와 침수모의 결과의 가시화에 대한 편의성을 높이기 위해서 GIS 소프트웨어를 이용하여 GUI를 개발하고자 하였다. 이와 더불어 사용자들이 소프트웨어 구매 비용에 대한 부담을 없애고, 편리하게 사용할 수 있는 오픈소스 소프트웨어를 이용하고자 하였으며, 이 두 가지 조건을 만족할 수 있는 QGIS를 이용해서 G2D 모형의 GUI인 QGIS-G2D를 개발하였다. QGIS-G2D는 QGIS의 plug-in으로 실행된다. QGIS-G2D는 G2D 모형의 실행에 필요한 프로젝트 파일(.g2p)을 GUI를 이용해서 만들 수 있으며, 모의결과를 애니매이션 등으로 가시화 할 수 있는 후처리 기능을 포함하고 있다. 또한 QGIS-G2D는 DEM 수정 기능과 같이 G2D 모형의 입력자료 전처리를 위해서 QGIS plug-in으로 제공되는 여러 가지 기능을 함께 이용할 수 있다. 또한 물리적 분포형 강우-유출 모형인 GRM(Grid based Rainfall-runoff Model)의 QGIS plug-in인 QGIS-GRM과 연계하여, 유역 유출모의와 침수모의를 QGIS 환경에서 함께 수행할 수도 있다. 개발된 소프트웨어는 오픈소스 플랫폼인 GitHub(https://github.com/floodmodel/)를 통해서 제공된다. 본 연구를 통해서 홍수해석에 필요한 강우-유출 모의와 침수모의를 위한 모형을 제공하고, 이를 편리하게 활용할 수 있는 오픈소스 소프트웨어를 제공할 수 있었다. 이러한 연구들은 홍수 분야의 전문가들에 의해서 다양한 분야의 홍수해석에 사용될 수 있을 것으로 기대한다.

• Korean Journal of Radiology
• /
• v.22 no.12
• /
• pp.2073-2081
• /
• 2021

Deep learning-based applications have great potential to enhance the quality of medical services. The power of deep learning depends on open databases and innovation. Radiologists can act as important mediators between deep learning and medicine by simultaneously playing pioneering and gatekeeping roles. The application of deep learning technology in medicine is sometimes restricted by ethical or legal issues, including patient privacy and confidentiality, data ownership, and limitations in patient agreement. In this paper, we present an open platform, MI2RLNet, for sharing source code and various pre-trained weights for models to use in downstream tasks, including education, application, and transfer learning, to encourage deep learning research in radiology. In addition, we describe how to use this open platform in the GitHub environment. Our source code and models may contribute to further deep learning research in radiology, which may facilitate applications in medicine and healthcare, especially in medical imaging, in the near future. All code is available at https://github.com/mi2rl/MI2RLNet.

• Journal of Digital Convergence
• /
• v.15 no.5
• /
• pp.37-48
• /
• 2017

Recently, the importance of software education is growing because computational thinking of software education is recognized as a key means of future economic development. Also human resources who will lead the 4th industrial revolution need convergence and creativity, computational thinking based on critical thinking, communication, and collaborative learning is known to be effective in creativity education. Software education is also a time needed to reflect social issues such as collaboration with developers sharing interests and open source development methods. Github is a leading social coding site that facilitates collaborative work among developers and supports community activities in open software development. In this study, we apply operational cases of basic learning of social coding sites, learning for storage server with sources and outputs of lectures, and open collaborative learning by using Github. And we propose educational model consisted of four stages: Introduction to Github, Using Repository, Applying Social Coding, Making personal portfolio and Assessment. The proposal of this paper is very effective for software education by attracting interest and leading to pride in the student.

• Journal of The Korean Association of Information Education
• /
• v.22 no.5
• /
• pp.519-533
• /
• 2018

This study aims to classify the types of instructional expertise development activities of teachers who teach subjects related to software education in primary schools. To this end, the study analyzes their participation in expertise development activities over the recent three years, outcomes from these activities, and forms and characteristics of expertise development activities. In the questionnaire survey conducted for this study, 276 primary school teachers participated. According to the survey, the same largest proportion of them participated in collective job training (96%) and distant job training (96%), followed by consulting, instruction supervision, mentoring, and peer observation (82%), lectures, workshops, and seminars held by related government ministries and the provincial and municipal offices of education (69%), and teachers' study communities (66%). Among informal activities, reading accounted for the highest portion of the activities (88%), followed by the use of information on Websites including YouTude and GitHub (80%), and teachers' expertise development networks (76%). The reasons for their participation in the activities were mostly to improve their instructional expertise (80%). Their participation in the activities had an impact on usefulness to enhance instructional expertise, improvement of job competencies, application to current jobs, sense of instructional efficacy, and positive effect. These results of the study are expected to provide a foundation for preparing continued expertise development plans that can promote the educational value of primary school teachers' instructional expertise development activities for teaching subjects related to software education.