• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1035-1037
• /
• 2005

The analysis of magnetic fields(2-D) induced by line currents, such as Overhead Trolley Lines or Transmission Lines, is not so easy by using the standard Finite Element Method(FEM). Mesh generation is one of the most important processes in the standard FEM. Because, the current region is relatively small compared with whole region, and actually is a line without thickness, the mesh refinement around the source lines yields many demerits. A way of supplement such a defect, we proposed the coupling scheme of analytical solution and FEM. In this study, the analytical solution is adopted around the region of line currents and FE solution is a lied to the rest of source region. And the two types of solution are coupled at the artificial boundary. To verify the usefulness of proposed algorithm, simplified model with magnetic material in FE region is chosen and analyzed. The results are compared with those of standard FEM. And the errors between them can be reduced by increasing harmonic orders.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2345-2358
• /
• 2022

This paper presents a method to generate stained-glass animation from video inputs. The method initially segments an input video volume into several regions considered as fragments of glass by mean-shift segmentation. However, the segmentation predominantly results in over-segmentation, causing several tiny segments in a highly textured area. In practice, assembling significantly tiny or large glass fragments is avoided to ensure architectural stability in stained glass manufacturing. Therefore, we use low-frequency components in the segmentation to prevent over-segmentation and subdivide segmented regions that are oversized. The subdividing must be coherent between adjacent frames to prevent temporal artefacts, such as flickering and the shower door effect. To temporally subdivide regions coherently, we obtain a panoramic image from the segmented regions in input frames, subdivide it using a weighted Voronoi diagram, and thereafter project the subdivided regions onto the input frames. To render stained glass fragment for each coherent region, we determine the optimal match glass fragment for the region from a dataset consisting of real stained-glass fragment images and transfer its color and texture to the region. Finally, applying lead came at the boundary of the regions in each frame yields temporally coherent stained-glass animation.

• Journal of the Korean Wood Science and Technology
• /
• v.50 no.6
• /
• pp.490-498
• /
• 2022

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10-15 ㎛ were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.300-306
• /
• 2022

Currently, Korea is building traffic infrastructure using Intelligent Transport Systems (ITS), but the pedestrian traffic accident rate is very high. The purpose of this paper is to prevent the risk of traffic accidents by jaywalking pedestrians. The development of this study aims to detect pedestrians who trespass using the public data set provided by the Artificial Intelligence Hub (AIHub). The data set uses training data: 673,150 pieces and validation data: 131,385 pieces, and the types include snow, rain, fog, etc., and there is a total of 7 types including passenger cars, small buses, large buses, trucks, large trailers, motorcycles, and pedestrians. has a class format of Learning is carried out using YOLOv5 as an implementation model, and as an object detection and edge detection method of an input image, a canny edge model is applied to classify and visualize human objects within the detected road boundary range. In this study, it was designed and implemented to detect pedestrians using the deep learning-based YOLOv5 model. As the final result, the mAP 0.5 showed a real-time detection rate of 61% and 114.9 fps at 338 epochs using the YOLOv5 model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3A
• /
• pp.439-445
• /
• 2006

Analysis problems of tunnels whose geometrical dimensions are very small compared with surrounding media can be treated as infinite region problems. In such cases, even if finite element models can be applied, excessive number of elements is required to obtain satisfactory accuracy. However, inaccurate results may be produced due to assumed artificial boundary conditions. To solve these problems, a hybrid model, which models the region of interest with finite elements and the surrounding infinite media with infinite elements, is introduced for the analysis of infinite region. Three-dimensional isoparametric infinite elements with various decay characteristics are formulated in this paper and the corresponding parameters are presented by means of parametric studies. Three-dimensional tunnel analysis performed on a representative example verifies the applicability of hybrid model using infinite elements.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.7 no.4
• /
• pp.207-215
• /
• 2004

Recently, securing a vast land in the land region becomes more difficult and efforts to seek its alternation in the sea area have been increased. As a consequence, the coastal region has been faced to extensive beach erosion problems. In planning offshore structures such as artificial islands, it is necessary to forecast the influence of the structure construction exerting on the beach erosion of the adjacent coast. In the present study, the sediment movement pattern behind offshore structure was examined through a series of three dimensional movable bed experiments, so as to develop the numerical model which forecasts morphological change including beach erosions. The experimental results reveal that the sediment movement patterns of the beach line side and the depth region are separated at a certain boundary line. In details, at the beach side including swash zone the sediment movement becomes dominant, which is governed by a relation between depth contours and incident wave directions, while at the depth region the bed load and suspended load due to the orbit motion of waves are carried by nearshore currents, and both movements are clearly separated at a specified boundary that is related to partial standing wave from the beach. It is expected that these results can be effectively used for verification of a numerical model on morphological change of the coast.

• Journal of the Korean Institute of Gas
• /
• v.17 no.2
• /
• pp.59-69
• /
• 2013

This study presents development of the ANN simulator for well placement of infill drilling in gas fields. The input data of the ANN simulator includes the production time, well location, all inter well distances, boundary inter well distance, infill well position, productivity potential, functional links, reservoir pressure. The output data includes the bottomhole pressure in addition to the production rate. Thus, it is possible to calculate the productivity and bottomhole pressure during production period simultaneously, and it is expected that this model could replace conventional simulators. Training for the 20 well placement scenarios was conducted. As a result, it was found that accuracy of ANN simulator was high as the coefficient of correlation for production rate was 0.99 and the bottomhole pressure 0.98 respectively. From the resultes, the validity of the ANN simulator has been verified. The term, which could produce Maximum Daily Quantity (MDQ) at the gas field and the productivity according to the well location was analyzed. As a result, the MDQ could be maintained for a short time in scenario C-1, which has the three infill wells nearby aquifer boundary, and a long time in scenario A-1. In conclusion, it was found that scenario A maintained the MDQ up to 21% more than those of scenarios B and C which include parameters that might affect the productivity. Thus, the production rate can be maximized by selecting the location of production wells in comprehensive consideration of parameters that may affect the productivity. Also, because the developed ANN simulator could calculate both production rate and bottomhole pressure, respectively, it could be used as the forward simulator in a various inverse model.

• Korean Journal of Environment and Ecology
• /
• v.22 no.4
• /
• pp.396-408
• /
• 2008

Gwangtan-myeon, Paju-si, Gyeonggi-do was classified as a 4 grade age-class deciduous tree forest, however as a result of vegetation survey, this site was found to consist of natural forest with deciduous trees, thus causing difficulty in judging which age class it belongs to. Subsequently, the necessity of drawing up a detailed stock map plan was raised. For this reason, this research was designed to propose a mapping method for a detailed stock map plan based on a detailed survey on actual vegetation, vegetation structure, and analysis data on tree rings. The detailed analysis of actual vegetation pattern showed that there exist 22 patterns of vegetation, in which the natural forest has 11 patterns, such as Quercus mongolica forest and Q. variabilis forest, etc. while the artificial forest was found to have 6 patterns including Castanea crenata, etc. In order to verify their age-class, this research measured a tree age by collecting 42 quadrats and 89 specimen tree cores on the basis of a detailed actual vegetation map; as a result, an artificial forest and oak trees with small diameters located at low-lying areas, was categorized as 2-grade age class(covering 29.8%), and other areas were judged to be available for land use as 3-grade age-class(covering 57.6%) while the areas judged to be 4-or-more grade age-class (covering 8.8%) was impossible for land use because they are located on a steep slope ridge line on a boundary. In case a proposed site for a small-scale development is judged as a natural forest with deciduous trees as mentioned above, it is necessary that a detailed stock map plan should be drawn up through a detailed investigation into actual vegetation and analysis of plant gathering structure & specimen trees. A detailed stock map plan includes the data that makes it possible to comprehensively judge natural property, scarcity, and diversity of vegetation; thus, it is considered that a detailed stock map plan will be useful in judging the development propriety of a small-scale site.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.

• Fire Science and Engineering
• /
• v.27 no.2
• /
• pp.80-88
• /
• 2013

The validation of Fire Dynamics Simulator (FDS) was conducted for the under-ventilated fire in well-confined multi-compartments representative of nuclear power plant. Numerical results were compared with experimental data obtained by the OECD/NEA PRISME project. The effects of the numerical boundary conditions (B.C.) in ventilated system and the flame suppression model applied within FDS on the thermal and chemical environments inside the compartment were discussed in details. It was found that numerical B.C. on the vent flow resulting from over-pressure at ignition and under-pressure at extinction should be considered carefully in order to predict accurately the species concentrations rather than temperatures and heat fluxes inside the multi-compartment. The default information of suppression model applied within FDS resulted in artificial phenomena such as flame extinction and re-ignition, and thus the FDS results on the under-ventilated fire showed good agreement with the experimental results as the modified suppression criteria of the fuel used was adopted.