• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.153-154
• /
• 2021

본 논문에서는 ROS(Robot Operating System)를 기반으로 한 로봇(Robot)에 LiDAR 센서를 설치하여 SLAM(Simultaneous Localization and Mapping) 기술인 동시적 위치 추적 지도 작성 기법을 이용하여 실내 맵 정보를 습득하고, 이를 기반으로 장애물과 건물 실내를 안전하고 정확하게 이동할 수 있도록 하였다. 또한 로봇에 자바에서 제공하는 개발 툴킷 Swing 및 AWT 라이브러리를 이용하여 GUI(Graphical User Interface)를 구현하였고 터치스크린을 장착하여 사용자가 원하는 제품을 선택하고 선택한 제품의 목적지를 습득한 맵을 토대로 좌표 값을 설정하여 ROS에서 지원하는 이동 프로세스를 실행시켜 목적지까지 경로를 설정하고 자율 주행하게 된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.89-90
• /
• 2021

본 논문에서는 Python과 Selenium 라이브러리 기반의 재난 문자 크롤링 및 데이터 시각화 애플리케이션을 설계하고 구현한다. 이 애플리케이션의 특징은 웹상에서 재난 문자 데이터를 크롤링(Crawling)하여 그 빈도수에 따라 시각화하는 것이다. 이 애플리케이션을 활용하여 국민재난안전포털에 접속하여 재난 문자 데이터를 크롤링하고, 그 데이터를 Word Cloud를 활용하여 지역별 재난 문자 빈도수를 시각화한다. 지역별 재난 문자 빈도수를 한눈에 보기 쉽게 시각화함으로써 재난문자를 잘 확인하지 않는 사람들에게 해당 지역의 재난 정보를 쉽게 전달하는 기능을 제공한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.321-322
• /
• 2022

본 논문에서는 ROS(Robot Operating System) 기반으로 한 로봇(Robot)에 레이저 거리 센서(LiDAR)를 설치하여 SLAM(Simultaneous Localization And Mapping) 기법으로 지도 정보를 습득 및 저장하고, 이를 기반으로 맵핑된 환경과 환경 내 장애물을 회피하여 안전하고 정확하게 이동할 수 있도록 하였다. ROS는 하드웨어 추상화, 장치 드라이버, 시각화 도구, 패키지 관리 등 로봇 애플리케이션을 개발할 수 있도록 라이브러리와 도구를 제공한다. 또한 로봇 동작에 사용되는 프로세스 간 TCP-IP 통신을 통해 연동할 수 있도록 한다[1]. Ubuntu 18.04 버전의 OS에 ROS Melodic 버전을 설치해서 앱으로 선택된 목적지로 이동하는 물류 이송 로봇을 구현하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.283-284
• /
• 2023

본 논문에서는 데이터 수집 자동화를 기반으로 한 자연재해 피해 통계 사이트를 구현한다. 자연재해 피해액 데이터는 국민 재난 안전 포털 사이트[1]에 자연재난 상황 통계 데이터를 사용하였다. Python 라이브러리인 Selenium을 활용하여 웹 브라우저를 제어해 자연재해 데이터를 쿼리문으로 변환 후 데이터베이스에 저장하는 자동화 프로그램을 사용한다. 또한 nncron을 활용해 6개월마다 한 번씩 자동으로 프로그램이 실행되도록 한다. 자연재해 종류에 따른 연도별, 시도 구역 자연재해 피해액을 웹사이트로 시각화하여 보여준다. 웹사이트 구현은 React.js와 Node.js를 활용하여 구현하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.457-458
• /
• 2023

본 논문에서는 실시간 영상처리 라이브러리인 OpenCV와 YOLO를 활용하여 사용자가 횡단보도 보행 시 안전을 제공해 주는 시스템을 개발하였다. 객체 인식 알고리즘인 YOLOv4-tiny를 이용하여 Ubuntu 환경에서 구현하였다. 데이터 셋은 인도 보행 영상 데이터 셋을 이용하였고 하드웨어는 Jetson Nano를 이용하여 구현하였다. 신호등의 색에 따른 보행 가능 여부를 카메라를 이용하여 전방의 장애물을 음성신호를 이용하여 사용자에게 전달한다. 제안된 시스템은 횡단보도와 신호등, 자동차와 같은 도로 위의 객체들로 설계된 알고리즘을 이용해 다양한 곳에서 사용이 가능하여 활용도가 높을 것으로 예상된다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1520-1531
• /
• 1999

In this paper, we present a first step for developing a method of verifying both safety and correctness of object-oriented design specification. As first, we analyze the discrepancies, which can occur between requirements specification and design specification, to make clear target faults. Then, we propose a new design verification method which aims at detecting faults in the design specification. The key idea of the proposed framework is that all elements to be verified can be extracted based on the requirements specification, safety standards, and design specification given for the target product These elements are expressed using three kinds of tables for verification, and thus, the verification steps can be greatly simplified. Here, we assume that component library, standards for safety and design specification obtained from the Booch's object-oriented design method are given. At the beginning, the designers construct a design table based on a design specification, and the verifiers construct a correctness table and a safety table from component library and standards for safety Then, by comparing the items on three tables, the verifiers verification a given design specification and detect faults in it. Finally, using an example of object-oriented design specification, we show that faults concerning safety or correctness can be detected by the new design verification method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.85-91
• /
• 2020

Recently, video-taping equipment such as CCTV have been seeing more use for crime prevention and general safety concerns. Since these video-taping equipment operates all throughout the day, the need for security personnel is lessened, and naturally costs incurred from managing such manpower should also decrease. However, technology currently used predominantly lacks self-sufficiency when given the task of searching for a specific object in the recorded video such as a person, and has to be done manually; current security-based video equipment is insufficient in an environment where real-time information retrieval is required. In this paper, we propose a technology that uses the latest deep-learning technology and OpenCV library to quickly search for a specific person in a video; the search is based on the clothing information that is inputted by the user and transmits the result in real time. We implemented our system to automatically recognize specific human objects in real time by using the YOLO library, whilst deep learning technology is used to classify human clothes into top/bottom clothes. Colors are also detected through the OpenCV library which are then all combined to identify the requested object. The system presented in this paper not only accurately and quickly recognizes a person object with a specific clothing, but also has a potential extensibility that can be used for other types of object recognition in a video surveillance system for various purposes.

• Korean Journal of Microbiology
• /
• v.46 no.1
• /
• pp.21-26
• /
• 2010

As the causative agent of Anthrax, Bacillus anthracis causes an acute fatal disease in herbivores such as cattle, sheep, and horses as well as humans. The therapeutics and prevention of anthrax currently available are based on antibiotics and the live attenuated vaccine strains, which may be problematic due to the emergency of antibiotic resistant strains or residual virulence in those vaccine strains. Therefore, it has been required to develop novel therapeutics and vaccines which are safer and applicable to humans. Recently, the development of the multivalent vaccine targeting both spores and vegetative cells of B. anthracis along with anthrax toxin has been reported. In our attempts to screen potential candidates for those multivalent vaccines, the whole genomic expression library of B. anthracis was constructed in this study. To the end, the partial digests of the genomic DNA from B. anthracis (ATCC 14578) with Sau3AI were ligated with the inducible pET30abc expression vectors, resulting in approximately $1{\times}10^5$ clones in E. coli BL21(DE3). The redundancy test by DNA nucleotide sequencing was performed for the randomly selected 111 clones and found 56 (50.5%) B. anthracis genes, 17 (15.3%) vector sequences, and 38 (34.2%) unknown genes with no sequence homology by BLAST. An inducible expression of the recombinant proteins was confirmed by Western blot. Interestingly, some clones could react with the antiserum against B. anthracis. These results imply that the whole genomic library constructed in this study can be applied for analyzing the immunomes of B. anthracis.

• Journal of the Korean earth science society
• /
• v.42 no.6
• /
• pp.623-631
• /
• 2021

The increased transport of marine hazardous and noxious substances (HNS) has resulted in frequent HNS spill accidents domestically and internationally. There are about 6,000 species of HNS internationally, and most of them have toxic properties. When an accidental HNS spill occurs, it can destroys the marine ecosystem and can damage life and property due to explosion and fire. Constructing a spectral library of HNS according to wavelength and developing a detection algorithm would help prepare for accidents. In this study, a ground HNS spill experiment was conducted in France. The toluene spectrum was determined through hyperspectral sensor measurements. HNS present in the hyperspectral images were detected by applying the spectral mixture algorithm. Preprocessing principal component analysis (PCA) removed noise and performed dimensional compression. The endmember spectra of toluene and seawater were extracted through the N-FINDR technique. By calculating the abundance fraction of toluene and seawater based on the spectrum, the detection accuracy of HNS in all pixels was presented as a probability. The probability was compared with radiance images at a wavelength of 418.15 nm to select abundance fractions with maximum detection accuracy. The accuracy exceeded 99% at a ratio of approximately 42%. Response to marine spills of HNS are presently impeded by the restricted access to the site because of high risk of exposure to toxic compounds. The present experimental and detection results could help estimate the area of contamination with HNS based on hyperspectral remote sensing.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.5
• /
• pp.558-565
• /
• 2017

Accurate prediction of wave-structure interactions is important in the safety and design cost effectiveness of fixed and floating offshore structures exposed to extreme environmental conditions. In this study, regular waves and circular column structure interactions for four circular columns in regular waves are analyzed. To simulate 3D two-phase flow, open source computational fluid dynamics libraries, called OpenFOAM, were used. When the four circular columns are arranged in a square array, the interactions according to the incident slopes of the regular waves are analyzed. The wave run-up in the circular column surface was compared according to the slope of the incident wave. It was confirmed that high amplitude waves are generated between the circular columns due to the interaction between the circular column and the incident wave. It is expected that this analytical result will be used as the basic data of the study on the air gap due to the interaction between the structure and incident wave.