• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.120-122
• /
• 2011

과학 기술과 의학 기술의 발달로 전 세계적인 고령화 인구 비율도 해마다 증가하고 있다. 본 연구에서는 이러한 고령화 인구 증가 현상에 대한 대책 방안의 하나로 U-HealthCare 시스템에 구글맵(Google Map) 3D 기반의 실시간 위치 추적기법을 적용 시켜 노약자들이 이동하는 중간에 실시간 위치 추적을 실시하여 추후 발생 할 수 있는 위험 사태에 대비하고자 한다. 제안 방식은 구글 맵 3D 서비스 방식이기에 2D 서비스나 문자 서비스 방식보다 시각적으로 건물의 생김새나 주변의 건물에 대한 정확한 파악이 가능하여 노약자들의 위치 정보에 대한 신속한 대체가 가능하다.

• Honam Mathematical Journal
• /
• v.45 no.4
• /
• pp.585-597
• /
• 2023

We introduce the rotational hypersurface x = x(u, v, s, t) constructed by double rotation in five dimensional Euclidean space 𝔼⁵. We reveal the first and the second fundamental form matrices, Gauss map, shape operator matrix of x. Additionally, defining the i-th curvatures of any hypersurface via Cayley-Hamilton theorem, we compute the curvatures of the rotational hypersurface x. We give some relations of the mean and Gauss-Kronecker curvatures of x. In addition, we reveal Δx=𝓐x, where 𝓐 is the 5 × 5 matrix in 𝔼⁵.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.727-730
• /
• 2024

최근 딥러닝 기술이 급속히 발전하며 현대 사회의 다양한 응용분야에서 빠르게 적용되고 있다. 특히 영상 기반의 딥러닝 기술은 자연어 처리와 함께 인공지능 기술의 핵심 연구 분야로 많은 연구가 진행되고 있다. 논문에서는 최근 많은 연구가 진행되고 있는 영상의 의미적 분할 (Semantic Segmentation) 성능을 향상하기 위한 연구를 진행한다. 특히 모델에서 고정밀의 의미적 분할을 수행할 수 있도록 추가적인 정보로써 의사 깊이맵 (Pseudo Depth-Map)을 활용하는 방법을 제안하였다. 더불어, 의사 깊이맵을 모델 상에서 효과적으로 학습시키기 위하여 다중 디코더 모델과 학습 효율을 높이는 학습 스케줄링 전략을 제안한다. 의사 깊이맵과 다중 디코더 모델 기반의 제안 모델은 기존 의미적 분할 모델과 비교하여 iIoU 기준 2%의 성능 향상을 보였다.

• Communications of the Korean Mathematical Society
• /
• v.39 no.3
• /
• pp.585-593
• /
• 2024

Let 𝒦 be a ring. An additive map 𝖚^⋄ → 𝖚 is called Jordan involution on 𝒦 if (𝖚^⋄)^⋄ = 𝖚 and (𝖚𝖛+𝖛𝖚)^⋄ = 𝖚^⋄𝖛^⋄+𝖛^⋄𝖚^⋄ for all 𝖚, 𝖛 ∈ 𝒦. If Θ is a (non-zero) 𝜂-generalized derivation on 𝒦 associated with a derivation Ω on 𝒦, then it is shown that Θ(𝖚) = 𝛄𝖚 for all u ∈ 𝒦 such that 𝛄 ∈ Ξ and 𝛄² = 1, whenever Θ possesses [Θ(𝖚), Θ(𝖚^⋄)] = [𝖚, 𝖚^⋄] for all 𝖚 ∈ 𝒦.

• 한국정보교육학회:학술대회논문집
• /
• 2011.01a
• /
• pp.139-146
• /
• 2011

The present study proposes an innovative approach to develop educational contents for the field trip with creative activities. In the study, the field trip with creative activities extends students' learning spaces from not only the classroom but also social circumstances. With the use of the Creative Resource Map (CRM) for students' field trip, students can approach to rich contents whenever and wherever they want. For this, it is necessary to have a variety of curriculum-related contents. For the content development, it is important to enhance mutual cooperation between school and local community as well as to create local capacity for the development of the u-learning contents with smart devices.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.343-350
• /
• 2024

Since the release of Meta's Segment Anything Model (SAM), a large-scale vision transformer generation model with rapid image segmentation capabilities, several studies have been conducted to apply this technology in various fields. In this study, we aimed to investigate the applicability of SAM for water bodies detection and extraction using the QGIS Geo-SAM plugin, which enables the use of SAM with satellite imagery. The experimental data consisted of Compact Advanced Satellite 500 (CAS500)-1 images. The results obtained by applying SAM to these data were compared with manually digitized water objects, Open Street Map (OSM), and water body data from the National Geographic Information Institute (NGII)-based hydrological digital map. The mean Intersection over Union (mIoU) calculated for all features extracted using SAM and these three-comparison data were 0.7490, 0.5905, and 0.4921, respectively. For features commonly appeared or extracted in all datasets, the results were 0.9189, 0.8779, and 0.7715, respectively. Based on analysis of the spatial consistency between SAM results and other comparison data, SAM showed limitations in detecting small-scale or poorly defined streams but provided meaningful segmentation results for water body classification.

• The Journal of Engineering Geology
• /
• v.28 no.4
• /
• pp.593-603
• /
• 2018

The most of groundwater with high U-concentration occur in the Jurassic granite of Gyeonggi massif and Ogcheon belt, and some of them occur in the Cretaceous granite of Ogcheon belt. On the contrary, they do not occur in the Jurassic granite of Yeongnam massif and the Cretaceou granite of Gyeongsang basin. The Jurassic and Cretacous granite, the host rock of high U-groundwater, were resulted from parental magma with high ratio of crustal material and highly differentiated product of fractional crystalization. These petrogenetic characteristics explain the geological evidence for preferential distribution of uraniferous groundwater in each host rock. It were reported recently that high U-content, low Th/U ratio and soluble mineral occurrence of uraninite in the two-mica granite of Daejeon area which have characteristics of S-type peraluminous and highly differntiated product. It is the mineralogical-geochemical evidences supporting the fact that the two-mica granite is the effective source of uranium in groundwater. The biotite granite and two-mica granite of Jurassic age were reported as biotite granite in many geological map even though two-mica granite occur locally. This fact suggest that the influence of two-mica granite can not be ignored in uraniferous groundwater hosted by biotite granite.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.3
• /
• pp.91-102
• /
• 2019

This study explores the causes and processes of morphological transformation of apartment complexes in Busan. All apartment complexes built until the year 2016 were selected for statistical analysis, drawing/map examination, field observation, selected expert interviews based on 6 periodical groups: Period I(~1990), Period II(1991~1995), Period III(1996~2000), Period IV(2001~2005), Period V(2006~2010), and Period VI(2011~2016). The research argues for three 'arrangement' types, P1U, L1U and P2U, which have dominated the whole periods occupying 88% of the total 260 complexes. The switch of the leading type represents for morphological transformation of apartment complexes. Four aspects, density(F.A.R.), height(maximum number of floors), deformed-building-type ratio, and building-orientation, have affected the change of 'arrangement' types. Density was the major cause of the arrangement-type switch, from P1U to L1U, on Period II(1991~1995). The morphological change, from type L1U to P2U, on Period V(2006~2010) was caused by height and orientation, and is correlated with the increased number of deformed-type buildings. The first phase morphological change on Period II(1991~1995) was resulted by the supply side of apartment. However, the second phase transformation on Period V(2006~2010) had gone through the complex process including reflection of consumers' demands. The significance of research is to reveal the morphological transformation process of apartment complexes through analytical investigation of the entire apartment data in Busan. The result shows that the major change of urban paysage started to occur from Period V(2006~2010), and the superficial evaluation on apartment 'being monotonous and repetitive' may not be proper at least from the perspective of town plan.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.83-98
• /
• 2021

Urban green space is an important component for enhancing urban ecosystem health. Thus, identifying the spatial structure of urban green space is required to manage a healthy urban ecosystem. The Ministry of Environment has provided the level 3 land cover map(the highest (1m) spatial resolution map) with a total of 41 classes since 2010. However, specific urban green information such as street trees was identified just as grassland or even not classified them as a vegetated area in the map. Therefore, this study classified detailed urban green information(i.e., tree, shrub, and grass), not included in the existing level 3 land cover map, using two types of high-resolution(<1m) remote sensing data(i.e., airborne LiDAR and RGB ortho imagery) in Suwon, South Korea. U-Net, one of image segmentation deep learning approaches, was adopted to classify detailed urban green space. A total of three classification models(i.e., LRGB10, LRGB5, and RGB5) were proposed depending on the target number of classes and the types of input data. The average overall accuracies for test sites were 83.40% (LRGB10), 89.44%(LRGB5), and 74.76%(RGB5). Among three models, LRGB5, which uses both airborne LiDAR and RGB ortho imagery with 5 target classes(i.e., tree, shrub, grass, building, and the others), resulted in the best performance. The area ratio of total urban green space(based on trees, shrub, and grass information) for the entire Suwon was 45.61%(LRGB10), 43.47%(LRGB5), and 44.22%(RGB5). All models were able to provide additional 13.40% of urban tree information on average when compared to the existing level 3 land cover map. Moreover, these urban green classification results are expected to be utilized in various urban green studies or decision making processes, as it provides detailed information on urban green space.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.21-30
• /
• 2023

Accurate segmentation of the kidney tumor is necessary to identify shape, location and safety margin of tumor in abdominal CT images for surgical planning before renal partial nephrectomy. However, kidney tumor segmentation is challenging task due to the various sizes and locations of the tumor for each patient and signal intensity similarity to surrounding organs such as intestine and spleen. In this paper, we propose a semi-supervised learning-based mean teacher network that utilizes both labeled and unlabeled data using a kidney local guided map including kidney local information to segment small-sized kidney tumors occurring at various locations in the kidney, and analyze the performance according to the kidney tumor size. As a result of the study, the proposed method showed an F1-score of 75.24% by considering local information of the kidney using a kidney local guide map to locate the tumor existing around the kidney. In particular, under-segmentation of small-sized tumors which are difficult to segment was improved, and showed a 13.9%p higher F1-score even though it used a smaller amount of labeled data than nnU-Net.