• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.30-32
• /
• 1998

정보기술의 급속한 발전에 따라 공학 및 과학 분야에 대해서도 정보공유를 통한 연구의 효율성 증대를 위해 Web기반의 DB검색 시스템의 개발이 필요하게 되었다. 이러한 공학 및 과학 분야의 데이터베이스는 실험정보를 많이 다룬다는 분야의 특수성 때문에 데이터 모델링과 사용자 인터페이스 측면에서 이를 고려한 설계가 필요하다. 분 논문에서는 이에 대한 간단한 분석을 통해 ODBMS, CORBA, Java를 이용한 설계가 적절함을 보이고, 이를 화공 및 화학 분야에 적용한 시스템인 DICE(Database on Internet for Chemical Engineering) 검색 시스템을 소개한다. DICE 검색 시스템은 다양한 공학 분야의 실험정보를 관리하는데 유용한 데이터 구조와 사용자 인터페이스를 바탕으로 하고 있으며, 이를 이용하여 화공 및 화학 분야와 관련된 화합물의 물성정보와 실험정보를 함께 제공한다.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.670-673
• /
• 2022

설명가능한 인공지능은 딥러닝과 같은 복잡한 모델에서 어떠한 원리로 해당 결과를 도출해냈는지에 대한 설명을 함으로써 구축된 모델을 이해할 수 있도록 설명하는 기술이다. 최근 여러 분야에서 그래프 형태의 데이터들이 생성되고 있으며, 이들에 대한 분류를 위해 다양한 그래프 신경망들이 사용되고 있다. 본 논문에서는 대표적인 그래프 신경망인 그래프 합성곱 신경망(graph convolutional network, GCN)에 대한 설명 기법을 제안한다. 제안 기법은 주어진 그래프의 각 노드를 GCN을 사용하여 분류했을 때, 각 노드의 어떤 특징들이 분류에 가장 큰 영향을 미쳤는지를 수치로 알려준다. 제안 기법은 최종 분류 결과에 영향을 미친 요소들을 gradient를 통해 단계적으로 추적함으로써 각 노드의 어떤 특징들이 분류에 중요한 역할을 했는지 파악한다. 가상 데이터를 통한 실험을 통해 제안 방법은 분류에 가장 큰 영향을 주는 노드들의 특징들을 실제로 정확히 찾아냄을 확인하였다.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.1087-1090
• /
• 2008

Web 경계를 허무는 새 시대에 맞추어 라이프스타일은 급속히 변화하고 있다. 가상의 3D 복합 서비스는 현실과 다름없는 또 하나의 삶을 제공함으로써, 가상세계와 현실세계의 경계를 없애고 있고 이전 많은 사람들이 제안하고 예상했던, 현실의 정보가 가상세계에서 또한 다름 없는 데이터로 존재함으로써 가상세계와 현실세계 사이의 벽을 허물고 그 차이를 느끼리 못 하도록 하는 연구를 하고자 하였다. 우선 손쉽게 제시할 수 있는 실험을 통하여 그 가능성을 판단해 보고자 하였으며, 간단한 예로써 현실세계를 대표할 모바일 장비와 가상 현실세계의 대표적인 예인 SecondLife 두 가지 시스템의 접목을 통하여 가상현실 세계와 현실간의 데이터 공유 환경을 만들고 정보를 공유를 통하여, 얻을 수 있는 장점들과 활용방안에 대하여 찾고자 한다.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.135-143
• /
• 2022

The defense environment is rapidly changing, such as nuclear and missile threats of North Korea, changes in war patterns, and a decrease in military service resources due to low birth rate. In order to actively respond to these changes, the Korean military is promoting Defense Innovation 4.0 and is trying to foster an army armed with high technology such as artificial intelligence (AI), big data analysis, etc. In this regard, we analyze the effectiveness of the radar-based AI scientific guard system applied by high technology for guard operations using Analytic Hierarchy Process (AHP). We first select evaluation factors that can assess the effectiveness of the scientific guard system, and analyze its relative importance. Each evaluation factor was selected by deriving a significant concept from operating principle and how they work, and by consulting experts on the correlation between each factor and effectiveness of the scientific guard system. We examine the relative effects of the radar-based AI scientific guard system and existing scientific guard system based on the importance of the evaluation factors.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.2
• /
• pp.171-178
• /
• 2023

PCM data is result of air-vehicle flight test, this data is distributed for each engineers to analyze its condition. Since line-of-sight between the air-vehicle and the ground receiver cannot always be secured, remote PCM data recording system was claimed to be required. In this paper multi-function PCM data recorder has been described. This PCM data recorder was intended to place on inside of flight object. It can record about two hours in 32 GB SD card with maximum 7 Mbps data rate. RS-422/485 and RJ-45 interface enhanced accessibility for users. 5 V and 1 A power consumption and 19.5 mm × 152.5 mm × 102.3 mm allow to connect with mobile PCM devices. It acquired more than 190-minutes data in 12-times flight test. Also, it achieved military standard environmental test MIL-STD-810G to prove its stability and solidness.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.7 no.4 s.19
• /
• pp.44-52
• /
• 2004

The test and evaluation(T&E) of weapon systems is a significant activity in the decision-making process of defense acquisition program, providing the data of trade-off analysis, risk reduction and readiness to advance to next phase of development for the decision-maker. Currently, the modeling and simulation(M&S) is being a critical method in the test and evaluation of weapon systems. Therefore in this paper we review the current status of the test and evaluation for the defense acquisition program in Korea, and suggest an application of M&S in the T&E of weapon systems.

• Journal of Information Management
• /
• v.30 no.2
• /
• pp.53-68
• /
• 1999

This paper focuses on the critique of citation analysis and then attempts to prospect for the future. The development of citation analysis has been marked by the invention of new techniques and measures, the exploitation of new tools, and the needs of evaluation of scientific research. Normative theory takes the lead in this development. But critics have questioned both the assumptions and methods of citation analysis. This critics are based on the microsociological perspective.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.2 no.2
• /
• pp.157-165
• /
• 1999

Production and measurement of a super-polished few-ppm-scattering mirror substrate are investigated. In order to improve the surface roughness directly determining scattering, the super-polishing process using Bowl-Feed technique is tried. The surface quality of the super-polished substrate is estimated by the phase-measuring interferometer. For the reliable roughness measurement using the interferometer, data averaging method is applied so that the optimal data averaging condition, 30 phase-data averaging and 20 intensity-data averaging, minimizing the measurement error is experimently searched. Based on the optimal data averaging condition, surface roughness of home-made mirror substrate is measured to be less than $0.5{\AA}$ rms corresponding to 2-ppm total-integrated-scattering.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.4
• /
• pp.474-481
• /
• 2017

This paper presents a multiple target tracking system using Normalized Rayleigh likelihood of amplitude information of target. Although many studies of Radar systems using amplitude information have been studied, they are focused on single target tracking. This paper proposes the multiple target tracking using amplitude information as well as kinematic information from Radar sensor. The amplitude information are applied in generating the association probability of joint probabilistic data association(JPDA) algorithm through the normalized Rayleigh likelihood. It is verified that the proposed system can enhance the track maintenance and tracking accuracy, especially, in the target crossing case.