• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.1-7
• /
• 2023

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.1
• /
• pp.5-19
• /
• 2010

Geo-layer information is important to determine pile length and estimate residual settlement in the construction site. An overall spatial distribution of geo-layers in the entire construction site can be predicted using drill-log information. In this study, the geo-layer distribution at Song-do area was estimated by kriging and inverse distance weighting methods, and a cross validation was adopted to verify the reliability of estimation results. The analysis results indicate that the best fitted theoretical variogram model to the experimental variogram does not always provide the most reliable estimation in the kriging method. The proper $\alpha$ value of inverse distance weighting method must be determined by types of geo-layer, because the $\alpha$ value is affected by types of geo-layer. Results of the kriging method show more reliable results than those of inverse distance weighting method, and the structure of geo-layer distribution could be evaluated by variogram in the kriging method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5B
• /
• pp.469-479
• /
• 2006

In order to investigate characteristics of the primary flow and the secondary currents in meandering channels, the laboratory experiments were conducted in S-curved channels with angle of bend, $150^{\circ}$, and sinuosity of 1.52. The experimental conditions was decided varying average depth and velocity. Under these experimental conditions, spatial variations of the secondary currents in multiple bends were observed. The experimental results revealed that the distribution of primary flow in straight section is symmetric without respect to the experimental condition and the maximum velocity line of the primary flow occurs along the shortest path in experimental channel, supporting the result of previous works. The secondary currents in second bend became more developed than those in first bend. Particularly, the outer bank cell developed distinctively and the secondary current intensity was low at the straight section and high at the bends, periodically. Also, the secondary current intensity at the bends was as twice to three times as that at the straight section, and has its maximum value at the second bend. The turbulent flow characteristics of meandering channel was investigated with turbulent intensity of the primary flow and Reynolds shear stress. It was observed that the turbulent intensity is increasing when the velocity deviation of the primary flow is large whereas Reynolds shear stress increases when both the velocity deviation of the primary flow and the secondary current are large.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

• Journal of Korea Water Resources Association
• /
• v.56 no.spc1
• /
• pp.1059-1069
• /
• 2023

Dam-break flow occurs when an elevated dam suddenly collapses, resulting in the catastrophic release of rapid and uncontrolled impounded water. This study compares laminar and turbulent closure models for simulating three-dimensional dam-break flows using OpenFOAM. The Reynolds-Averaged Navier-Stokes (RANS) model, specifically the k-ε model, is employed to capture turbulent dissipation. Two scenarios are evaluated based on a laboratory experiment and a modified multi-layered block obstacle scenario. Both models effectively represent dam-break flows, with the turbulent closure model reducing oscillations. However, excessive dissipation in turbulent models can underestimate water surface profiles. Improving numerical schemes and grid resolution enhances flow recreation, particularly near structures and during turbulence. Model stability is more significantly influenced by numerical schemes and grid refinement than the use of turbulence closure. The k-ε model's reliance on time-averaging processes poses challenges in representing dam-break profiles with pronounced discontinuities and unsteadiness. While simulating turbulence models requires extensive computational efforts, the performance improvement compared to laminar models is marginal. To achieve better representation, more advanced turbulence models like Large Eddy Simulation (LES) and Direct Numerical Simulation (DNS) are recommended, necessitating small spatial and time scales. This research provides insights into the applicability of different modeling approaches for simulating dam-break flows, emphasizing the importance of accurate representation near structures and during turbulence.

• Journal of Life Science
• /
• v.34 no.5
• /
• pp.356-364
• /
• 2024

Lymph nodes (LNs) are crucial sites where immune responses are initiated to combat invading pathogens in the body. LNs are organized into distinctive compartments by stromal cells. Stromal cell subsets constitute special niches supporting the trafficking, activation, differentiation, and crosstalk of immune cells in LNs. Fibroblastic reticular cells (FRC) are a type of stromal cell that form the three-dimensional structure networks of the T cell-rich zones in LNs, providing guidance paths for immigrating T lymphocytes. FRCs imprint immune responses by supporting LN architecture, recruiting immune cells, coordinating immune cell crosstalk, and presenting antigens. During inflammation, FRCs exert both spatial and molecular regulation on immune cells through their topological and secretory responses, thereby steering immune responses. Here, we propose a model in which FRCs regulate immune responses through a three-part scheme: setting up, supporting, or suppressing immune responses. FRCs engage in bidirectional interactions that enhance T cell biological efficiency. In addition, FRCs have profound effects on the innate immune response through phagocytosis. Thus, FRCs in LNs act as gatekeepers of immune responses. Overall, this study aims to highlight the emerging roles of FRCs in controlling both innate and adaptive immunity. This collaborative feedback loop mediated by FRCs may help maintain tissue function during inflammatory responses.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.1
• /
• pp.33-48
• /
• 2024

This study aims to establish the scope and statistics of the K-address information industry in Korea, estimating its size and prospects and estimates the economic effects through K-address information industry based on Input-Output analysis. Considering the characteristics and sectoral structure of the K-address information industry, the study delineates the scope and specific sectors, constructing sectoral statistics linked to the KSIC and the Bank of Korea's industrial classification. The study estimates the sectoral industry size, taking into account potential markets. Furthermore, it analyzes the economic impact of each sector within the K-address information industry. To figure out the economic effects, the study conducts Input-Output analysis by setting the K-address information industry as an exogenous sector in the input-output table. The results indicate that the overall size of the K-address information industry is estimated to grow from 406.1 billion KRW in 2021 to 3.65 trillion KRW in 2030. The economic effects of the K-address information industry vary by sector, emphasizing the importance of synergies and integration with related sectors, particularly those with significant inducement effects in high value-added manufacturing and service sectors. Furthermore, the industry's sensitivity to economic fluctuations is evident through the input-output analysis of inter-industry chain effects.

• Korean Journal of Clinical Laboratory Science
• /
• v.55 no.4
• /
• pp.253-260
• /
• 2023

The germanium-68/gallium-68 (⁶⁸Ge/⁶⁸Ga) generator has high spatial utilization and requires little maintenance, making it economical and easy to produce. Thus, the frequency of use of ⁶⁸Ga radiopharmaceuticals is rapidly increasing worldwide. Therefore, this study attempted to develop an automated synthesizer for the routine clinical application of ⁶⁸Ga radiopharmaceuticals. The automated synthesizer was based on a fixed tubing system and the structure was designed after adjusting the position of the parts to reflect the synthesis method. Using various components that can be supplied in Korea, the automated synthesizer was manufactured at a much lower price cost than that of a commercialized automated synthesizer sold by companies. ⁶⁸Ga-DOTA-[Tyr3]-octreotide (⁶⁸Ga-DOTATOC) was synthesized to evaluate the performance of the automated synthesizer. ⁶⁸Ga-DOTATOC could be synthesized with about 65% of non-decay corrected yield, and the synthesized ⁶⁸Ga-DOTATOC met all quality control standards. We have synthesized ⁶⁸Ga-DOTATOC more than 100 times, and only faced a few problems caused by mechanical errors. In this study, we successfully developed a simple automated synthesizer for ⁶⁸Ga radiopharmaceuticals with high reproducibility. As various ⁶⁸Ga radiopharmaceuticals have recently been developed, it is expected that the automated synthesizer developed in this study will be useful for routine clinical use.

• Journal of the Economic Geographical Society of Korea
• /
• v.27 no.1
• /
• pp.38-52
• /
• 2024

Digital transformation industry contributes to the improvement of productivity in overall industrial production, the smart green industry for carbon neutrality and sustainable growth is growing as a future industry. The purpose of this paper is to explore the status and role of the industry in the future industry innovation ecosystem through the analysis of the growth drivers and location pattern changes of the smart green industry. The industry is on the rise in both metropolitan and non-metropolitan areas, and the growth of the industry can be seen in non-metropolitan and non-urban areas. In particular, due to the smart green industrial complex pilot project, the creation of Gwangju Jeonnam Innovation City, and the promotion of new and renewable energy policies, the emergence of core aggregation areas (HH type) in the coastal areas of Honam and Chungcheongnam-do, and the formation of isolated centers (HL type) in the Gyeongsang region, new and renewable energy production companies are being accumulated in non-metropolitan areas. Therefore, the smart green industry is expected to promote the formation of various specialized spokes in non-urban areas in the future industrial innovation ecosystem that forms a multipolar hub-spoke network structure, where policy factors are the triggers for growth.