• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.339-346
• /
• 2023

The uncertainties of microstructural features affect the properties of materials. Numerous pores that are randomly distributed in materials make it difficult to predict the properties of the materials. The distribution of pores in cementitious materials has a great influence on their mechanical properties. Existing studies focus on analyzing the statistical relationship between pore distribution and material responses, and the correlation between them is not yet fully determined. In this study, the mechanical response of cementitious materials is predicted through an image-based data approach using a convolutional neural network (CNN), and the correlation between pore distribution and material response is analyzed. The dataset for machine learning consists of high-resolution micro-CT images and the properties (tensile strength) of cementitious materials. The microstructures are characterized, and the mechanical properties are evaluated through 2D direct tension simulations using the phase-field fracture model. The attributes of input images are analyzed to identify the spot with the greatest influence on the prediction of material response through CNN. The correlation between pore distribution characteristics and material response is analyzed by comparing the active regions during the CNN process and the pore distribution.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.1
• /
• pp.29-38
• /
• 2010

The airborne LiDAR which was introduced in the early 2000's provides the point data. The new methods for the verification of LiDAR materials with high accuracy which is different from the existing airborne survey are needed. In accordance with the rules of airborne laser survey which were enacted in 2009, the verifications by three methods of Unmeasured Rate and point accuracy, point density have been executed, and Unmeasured Rate is to evaluate the rate for the presence of points within uniform grids except non-reflective areas such as watershed areas. For the calculation of Unmeasured Rate, non-reflective areas should be removed by all means, and in case of normal LiDAR materials, as there are scant points for watershed areas, watershed areas should be divided by additional spatial information. So, in this study, the watershed areas were extracted using domain extension technique from the high resolution CIR images of 0.3m grade. In addition, in order to compare the accuracy of Unmeasured Rate calculated, the comparative analysis of the Unmeasured Rate calculated by digital maps has been done. In conclusion, we found that 1I1e accuracy of Unmeasured Rate extracted by domain extension technique is similar to the value extracted by digitizing technique.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.267-275
• /
• 2015

Those land cover maps have widely been used in various fields, such as environmental studies, military strategies as well as in decision-makings. This study proposes a method to extract training data, automatically and classify the cover using ingle satellite images and national land cover maps, provided by the Ministry of Environment. For this purpose, as the initial training data, those three were used; the unsupervised classification, the ISODATA, and the existing land cover maps. The class was classified and named automatically using the class information in the existing land cover maps to overcome the difficulty in selecting classification by each class and in naming class by the unsupervised classification; so as achieve difficulty in selecting the training data in supervised classification. The extracted initial training data were utilized as the training data of MLC for the land cover classification of target satellite images, which increase the accuracy of unsupervised classification. Finally, the land cover maps could be extracted from updated training data that has been applied by an iterative method. Also, in order to reduce salt and pepper occurring in the pixel classification method, the MRF was applied in each repeated phase to enhance the accuracy of classification. It was verified quantitatively and visually that the proposed method could effectively generate the land cover maps.

• Korean Journal of Remote Sensing
• /
• v.23 no.6
• /
• pp.567-573
• /
• 2007

Tidal channel development is influenced by sediment type, grain size, composition and tidal current. Tidal channels are usually characterized by channel formation, density and shape. Quantitative analysis of tidal channels using remotely sensed data have rarely been studied. The objective of this study is to quantify tidal channels in terms of fractal dimension and compare different inter-tidal channel patterns and compare with DEM (Digital Elevation Model). For the fractal analysis, we used box counting method which had been successfully applied to streams, coastlines and others linear features. For a study, the southern part of Ganghwado tidal flats was selected which know for high dynamics of tidal currents and vast tidal flats. This area has different widths and lengths of tidal channels. IKONOS was used for extracting tidal channels, and the box counting method was applied to obtain fractal dimensions (D) for each tidal channel. Yeochari area where channels showed less dense development and low DEM had low fractal dimenwion near $1.00{\sim}1.20$. Area (near Donggumdo and Yeongjongdo) of dendritic channel pattern and high DEM resulted in high fractal dimension near $1.20{\sim}1.35$. The difference of fractal dimensions according to channel development in tidal flats is relatively large enough to use as an index for tidal channel classification. Therefore we could conclude that fractal dimension, channel development and DEM in tidal channel has high correlation. Using fractal dimension, channel development and DEM, it would be possible to quantify the tidal channel development in association with surface characteristics.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.29 no.2
• /
• pp.71-76
• /
• 2019

Recently, the demand of labels for product management is increasing, as the automation system becomes more common. the development of functional labels which can be used in various environments has been rapidly proceeded. In the case of a printed circuit board, barcode labels with thermal and chemical stability are generally used due to a high temperature process around $300^{\circ}C$ and chemical cleaning in the manufacturing process. However, the yellowing phenomenon of labels that can lower the resolution of printed barcode image still needs to be prevented. In this study, we prepared a composite coating layer using a silica inorganic binder and a titanium dioxide white pigment, and developed a functional labels with thermal and chemical stability. The silica inorganic binder prepared by sol-gel process was confirmed to show excellent adhesion and abrasion resistance with the polyimide film. The white coating layer could be formed on the polyimide film with mixing the silica inorganic binder and titanium dioxide white pigment. The prepared coating layer showed excellent whiteness and glossiness above $400^{\circ}C$. The excellent chemical stability of the coating layer was also confirmed by the chemical treatment with acidic (pH 1.6) and basic (pH 13.6) cleaners.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1889-1900
• /
• 2022

Roads are an essential factor in the physical functioning of modern society. The spatial information of the road has much longer update cycle than the traffic situation information, and it is necessary to generate the information faster and more accurately than now. In this study, as a way to achieve that goal, the Pan-sharpening technique was applied to satellite images of Kompsat 3 and 3A to improve spatial resolution. Then, the data were used for road extraction using the semantic segmentation technique, which has been actively researched recently. The acquired Kompsat 3/3A pan-sharpened images were trained by putting it into a U-Net based segmentation model along with Massachusetts road data, and the applicability of the images were evaluated. As a result of training and verification, it was found that the model prediction performance was maintained as long as certain conditions were maintained for the input image. Therefore, it is expected that the possibility of utilizing satellite images such as Kompsat satellite will be even higher if rich training data are constructed by applying a method that minimizes the impact of surrounding environmental conditions affecting models such as shadows and surface conditions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.381-391
• /
• 2022

This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• The Journal of Engineering Geology
• /
• v.7 no.2
• /
• pp.139-149
• /
• 1997

Electrical resistivity monitoring methods were adopted to detect groundwater table change in alluvium. Numerical modelling test using finite element method(FEM) and field resisfivity monitoring were conducted in the study. The field monitoring data were acquired in the alluvium deposit site in Jeong-Dong Ri, Geum River where pumping test had been conducted continuously for 20 days to make artificial changes of groundwater table. The unit distance of the electrode array was 4m and 21 fixed electrodes were applied in numerical calculation and field data acquisition. "Modified Wenner" and dipole-dipole array configurations were used in the study. The models used in two-dimensional numerical test were designed on the basis of the simplifving geological model of the alluvium in Jeong Dong Ri, Geum River. Numerical test results show that the apparent resistivity pseudosections were changed in the vicinity of the pootion where groundwater table was changed. Furthermore, there are some apparent resistivity changes in the boundary between aquifer and crystalline basement rock which overlays the aquifer. The field monitoring data also give similar results which were observed in numerical tests. From the numerical test using FEM and field resistivity monitoring observations in alluvium site of Geum River, the electrical monitoring method is proved to be a useful tool for detecting groundwater behavior including groundwater table change. There are some limitations, however, in the application of the resistivity method only because the change of groundwater table does not give enough variations in the apparent resistivity pseudosections to estimate the amount of groundwater table change. For the improved detection of groundwater table changes, it is desirable to combine the resistivity method with other geophysical methods that reveal the underground image such as high-resolution seismic and/or ground penetrating radar surveys.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.786-792
• /
• 2013

In this study was explored minimize side effects due to the additional injection of contrast medium and maintaining a high resolution imaging applied to the inspection and analysis of the contrast medium that affect the peak time biomechanics factors. Included 48 patients using the test bolus method, after measuring a patient's biomechanics factors of inspection before and during the test, correlation between contrast medium peak time and learn, matches the regression equation calculated and measured contrast medium peak time was assessed by the Bland Altman plot. Research result, inspections of SBP, HR contrast medium peak time and a significant negative correlation was, step 1, every increase, the contrast medium peak time significantly to -0.018 and -0.159 decreased, a fairly high concordance no difference between the two method. In conclusion, the regression equation using the existing methods, while maintaining excellent image quality that contrast medium is reduced to a patient, it can conclude that the alternative to the existing methods.