• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2001.10a
• /
• pp.71-82
• /
• 2001

인공위성을 이용한 범 지구 위치결정시스템인 GPS(Global Positioning System)는 수 밀리의 정밀도로 정적, 동적 위치측정이 가능한 시스템으로 교량, 건축물, 댐 등 각종 구조물의 미세한 변위를 측정하는데 이용되고 있다. 최근 국내에서도 대형구조물의 변위 측정에 GPS를 활용하려는 시도가 부분적으로 이루어지고 있으나 초보적인 단계이며 체계적인 연구가 이루어지지 못하고 있는 실정이다. 본 연구에서는 RTK(Real Time Kinematic) GPS로 구조물의 변위를 실시간 측정하고 모니터링 할 수 있는 시스템을 개발하였다. 먼저 예비실험으로 반송파의 차분에 의해서 증폭되는 수신기의 측정잡음 오차, 다중경로 오차, GDOP(Geometric Dilution of Precision)가 RTK GPS의 위치정확도에 미치는 영향을 분석하였다. 그리고, RTK GPS를 이용하여 마포대교를 관측한 결과, 수 센티미터 정도 발생하는 구조물의 변위를 3차원으로 정밀 관측할 수 있었으며, 본 연구에서 개발한 모니터링프로그램을 이용하여 구조물의 거동을 실시간으로 모니터링 할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.71-73
• /
• 2022

다양한 미디어 서비스의 발전으로 비디오의 방대한 데이터를 효과적으로 압축할 수 있는 비디오 부호화 표준은 지속적인 발전을 하고 있다. 압축된 데이터를 다시 영상으로 복원하는 비디오 부복호화 과정에서 영상 데이터의 손실이 일어나고 그에 따른 다양한 형태의 열화가 나타나 영상의 화질을 저하한다. 이러한 열화들을 제거하여 원본 이미지에 가깝게 만들기 위해서 인루프 필터 과정을 비디오 부호화 표준에서 포함하고 있다. 이에 최근 영상처리 및 컴퓨터 비전 분야에서는 널리 사용되는 인공 신경망을 적용하여 효과적인 필터링을 하는 방법을 제시한다. 본 논문에서는 비디오 부호화 시 인루프 필터링에서 자기 참조를 통한 화질 개선 방법에 대해 연구하였다. 이를 위하여 트랜스포머 기반의 화질 개선 네트워크를 제안하고 기존 부호화 방법과 비교하였다. 인루프 필터링을 통해 화질을 향상하여 주관적 화질을 개선할 뿐만 아니라 객관적 부호화 효율을 증가시키는 방법을 개발하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.470-472
• /
• 2023

최근 위치 기반 장소 (POI) 추천 서비스가 많이 사용되면서, 사용자의 이전 방문지들에 대한 체크인 시퀀스를 기반으로 현재 (다음으로) 방문할 법한 POI 를 찾아 사용자에게 추천하는, next POI 추천 시스템에 관한 연구가 활발히 진행되고 있다. 하지만, 기존 연구들의 경우 next POI 추천을 위한 모델 학습 시, 사용자의 네거티브 POIs 에 관한 정교한 샘플링 없이 사용자 선호도를 추론해왔다. 본 연구에서는, 사전 학습된 별도의 사용자 선호도 추론 모델을 통해 사용자의 네거티브 POI로서 쉽게 분류되기 어려운 하드 네거티브 POIs 를 찾고, 이들을 위주로 수행되는 하드 네거티브 샘플링 방법을 새롭게 제안한다. 우리는 실 세계 데이터셋을 이용한 실험을 통해, 제안 방안이 기존 연구들에서 사용되어 온 랜덤 네거티브 샘플링 방법 대비 recall@5 기준, 최대 16.4%까지 추천 정확도를 향상시킬 수 있음을 확인하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.99-105
• /
• 2021

In addition to the OTT video production service represented by Nexflix and YouTube, a personalized recommendation system for content with artificial intelligence has become common. YouTube's personalized recommendation service system consists of two neural networks, one neural network consisting of a recommendation candidate generation model and the other consisting of a ranking network. Netflix's video recommendation system consists of two data classification systems, divided into content-based filtering and collaborative filtering. As the online platform-led content production is activated by the Corona Pandemic, the field of virtual influencers using artificial intelligence is emerging. Virtual influencers are produced with GAN (Generative Adversarial Networks) artificial intelligence, and are unsupervised learning algorithms in which two opposing systems compete with each other. This study also researched the possibility of developing AI platform based on individual recommendation and virtual influencer (metabus) as a core content of OTT in the future.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.885-890
• /
• 2023

As satellite technology progresses, a growing number of satellites-like CubeSat and radar satellites-are available with a higher spectral and spatial resolutions than previous. National initiatives used to be the main force behind satellite development, but current trendsindicate that private enterprises are also actively exploring and developing new satellite technologies. This special issue examines the recent research results and advanced technology in remote sensing approaches for Earth environment analysis. These results provide important information for the development of satellite sensors in the future and are of great interest to researchers working with artificial intelligence in thisfield. The special issue introduces the latest advances in remote sensing technology and highlights studies that make use of data to monitor and forecast Earth's environment. The objective is to provide direction for the future of remote sensing research.

• Journal of Sensor Science and Technology
• /
• v.24 no.5
• /
• pp.291-298
• /
• 2015

There are many landslides occurred by typhoons and intense rainfall during the summer seasons in Korea. To predict a landslide triggering it is important to understand mechanisms and potential areas of landslides by the geological approaches. However, recent climate changes make difficult to predict landslide based on only conventional prediction methods. Therefore, the importance of a real-time monitoring of landslide using various sensors is emphasized in recent. Many researchers have studied monitoring techniques of landslides and suggested several monitoring systems which can be applicable to the natural terrain. Most sensors of landslide monitoring measure slope displacement, hydrogeologic properties of soils and rocks, changes of stress in soil and rock fractures, and rainfall amount and intensity. The measured values of each sensor are transmitted to a monitoring server in real-time. The ultimate goal of landslide monitoring is to warn landslide occurrence in advance and to reduce damages induced by landslides. This study introduces the current situation of landslide monitoring techniques in each country.

• Journal of Wetlands Research
• /
• v.19 no.1
• /
• pp.80-89
• /
• 2017

Researches about NPS(Non-point Pollution Source) reduction have been widely carried out in recent years. A pilot channel-type constructed wetland (wet swale) was constructed in Rongyin area to treat stormwater generated from a green house agro-land of 22.7 ha. From 2006 to 2008, monitoring was conducted to evaluate its performance on the removal effect for organic pollutants as well as nutrients. Totally, sampling trips of 17 rainfall events were made and they covered most types of storm events in Korea. The channel-type constructed wetland have average removal efficiencies of 78.3~92.0%, 56.4~66.1%, 28.2~45.5% and 50.6~66.4% for SS, COD, TN and TP, respectively. According to four methods for estimating the removal efficiency, the average efficiencies of TSS, COD, TN and TP are 86.0%, 60.1%, 30.1% and 53.5%, respectively. From 2006 to 2008, annual efficiency improved due to infiltration potential increase. It was found that most of the pollutants removed in this channel type of wetland was particulate solids bound pollutants, which is assumed fact that it lacks of physico-chemical treatment conditions which are commonly observed in the retention type of constructed wetlands.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.3
• /
• pp.141-147
• /
• 2013

An artificila fish-reef is a artificail structure installed at marine ranching under the littoral sea. The artificial fish-reefs provide the function of fish spawning ground, habitation, nursery ground, and enhance the productivity of fising industry devastated by environmental pollution. After the installation of artificila fish-reef, continuous monitoring is demanded to check the validity of artificila fish-reef plan. However, the support of follow-up management is impossible because of the lack of a huge budget and professional manpower. Therefore, the artificial fish-reef combined with IT devices can be controled IT devices through the IT artificial fish-reef management system, and collect the marine environment information for the fair management. This paper shows the example of systematization for the management of artificial fish-reef based on the marine rancing management system.

• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.573-584
• /
• 2020

This study is about the development of AI algorithm education program using cognition modeling to positively improve students' image on AI. First, we analyzed the concept of user-based collaborative filtering and developed the education program using the cognition modeling method. We checked the adequacy of program through the expert validity test. Both CVR values for the content development method of cognitive modeling and the developed program showed validity above .80. We applied the developed program to elementary school students in class. The test was conducted using a semantic discrimination to examine changes in students' perception of artificial intelligence before and after. We were able to confirm that the students' AI images were significant positive change in 12 of the 23 words in the adjective pair.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.62-72
• /
• 2023

Recently, the importance of monitoring and management measures for bicycle road related facilities has been increasing. However, research on the monitoring and evaluation of users' safety and convenience in walking spaces including bicycle path is insufficient. In this study, we would like to construct health monitoring data for cylists-pedestrians mixed road using a mobile mapping system, and propose a plan to calculate the level of service of the mixed roads from the perspective of pedestrians and cyclists using artificial intelligence based object detection techniques. The monitoring and level of service calculation method of cylists-pedestrians mixed roads proposed in this study is expected to be used as basic information for planning and management such as maintenance and reconstruction of walking spaces in preparation for the increase of electric bicycles and personal mobility in the future.