• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.4
• /
• pp.183-191
• /
• 2024

Accurate seismic vulnerability assessment requires high quality and large amounts of ground motion data. Ground motion data generated from time series contains not only the seismic waves but also the background noise. Therefore, it is crucial to determine the high-pass cut-off frequency to reduce the background noise. Traditional methods for determining the high-pass filter frequency are based on human inspection, such as comparing the noise and the signal Fourier Amplitude Spectrum (FAS), f² trend line fitting, and inspection of the displacement curve after filtering. However, these methods are subject to human error and unsuitable for automating the process. This study used a deep learning approach to determine the high-pass filter frequency. We used the Mel-spectrogram for feature extraction and mixup technique to overcome the lack of data. We selected convolutional neural network (CNN) models such as ResNet, DenseNet, and EfficientNet for transfer learning. Additionally, we chose ViT and DeiT for transformer-based models. The results showed that ResNet had the highest performance with R² (the coefficient of determination) at 0.977 and the lowest mean absolute error (MAE) and RMSE (root mean square error) at 0.006 and 0.074, respectively. When applied to a seismic event and compared to the traditional methods, the determination of the high-pass filter frequency through the deep learning method showed a difference of 0.1 Hz, which demonstrates that it can be used as a replacement for traditional methods. We anticipate that this study will pave the way for automating ground motion processing, which could be applied to the system to handle large amounts of data efficiently.

• Geophysics and Geophysical Exploration
• /
• v.11 no.3
• /
• pp.197-203
• /
• 2008

A shallow high-resolution seismic reflection survey was carried out at the Mineopo tidal flat on the western coast of Korea. The purpose of the survey was to investigate shallow sedimentary structure of the tidal flat associated with the recent sea level change. A total of 795 shots were generated at 1 m interval from a 5-kg hammer source and recorded on 48 channels of 100 Hz geophones along two mutually perpendicular profiles. The water-saturated ground condition resulted in suppressed ground rolls by significantly decreasing rigidity. In addition, seismic velocities over 1500 m/s provided easy segregation of reflected arrivals from lower velocity noise. As a consequence, seismic sections from the study area show significantly higher resolution and signal to noise ratio than conventional land seismic sections. The tidal flat consists of 5 sedimentary sequences above acoustic basement. The seismic sections reveal the continuous structure of the tidal flat formed in association with sea level rise during the Holocene.

• Polymer(Korea)
• /
• v.37 no.6
• /
• pp.669-676
• /
• 2013

Demineralized bone particle (DBP) is a biomaterial used widely in the field of tissue engineering. In this study, in order to study the effect of DBP/poly(lactic-co-glycolic acid) (PLGA) scaffold on disc regeneration in vivo environment, we prepared the porous DBP/PLGA hybrid scaffold. Disc defect was induced by removing the nucleus pulposus tissue after incision the annulus fibrosus tissue in half and scaffolds were transplanted. After 1, 2 and 3 months later, the extracted discs were confirmed by collagen synthesis and glycosaminoglycan (sGAG). We conducted histology (H&E, Safranin-O, Alcian blue, Type I Collagen, Type II Collagen). From the results, it was confirmed that collagen and sGAG content were high in DBP/PLGA scaffold, and the regeneration of intervertebral disc was possible.

• Journal of agriculture & life science
• /
• v.46 no.1
• /
• pp.63-70
• /
• 2012

To provide the basic information for preservation and reasonable management plan of Abies koreana population, vegetation structure and growing condition by altitude were analyzed. Six sites($400m^2$) were set up along the Georim valley in Mt. Jiri from 1,000m to 1,500m. The importance value of A. koreana in tree layer was the highest at 1,400m(site V) and 1,500m(site VI), and that of Quercus mongolica in the other site was high. In subtree layer, the importance value of A. koreana was the highest at site VI which located at 1,500m above the level of the sea. In DBH distribution, A. koreana population distributed evenly at all DBH class(below 10cm, 11-20cm, 21-30cm, above 31cm). Since 2000, the amount of tree-ring growth of A. koreana at site I, II, III, IV, V, and VI were 1.002, 0.996, 1.752, 1.850, 1.198, 0.984 mm/yr, which has decreased slowly in time for 2000, except site III.

• Journal of agriculture & life science
• /
• v.44 no.1
• /
• pp.17-24
• /
• 2010

The purpose of this study was to define the relationship between respondents' social economic condition and willingness to pay on forest landscape. From the result of analyzing the difference of willingness to pay amount with considering social economic condition by using statistical technique, it was found that willingness to pay amount was highest when people are able to access forests landscape. In addition, it was found that women's willingness to pay amount was higher than that of men and the person such as laborer and public employee, who could spare enough time, had the intention to pay higher amount, than the person such as specialist and self-employed person, who spare enough money. For age, it was found that the retired people in their sixties showed low willingness to pay amount on forest scenery. For income per household, it was interesting that although willingness to pay amount increased as income increased, it was rather low in high income class, whose income was more than KRW 10 million.

• The Korean Journal of Air & Space Law and Policy
• /
• v.24 no.2
• /
• pp.187-210
• /
• 2009

Space law(or outer space law) and the law of the sea are branches of international law dealing with activities in geographical ares which do not or do only in part come under national sovereignty. Legal rules pertaining to the outer space and sea began to develop once activities emerged in those areas: amongst others, activities dealing with transportation, research, exploration, defense and exploitation. Naturally the law of the sea developed first, followed, early in the twentieth century, by air law, and later in the century by space law. Obviously the law of the sea, of the air and of outer space influence each other. Ideas have been borrowed from one field and applied to another. This article examines some analogies and differences between the outer space law and the law of the sea, especially from the perspective of the legal status, the exploration and exploitation of the natural resources and environment. As far as the comparisons of the legal status between the outer space and high seas are concerned the two areas are res extra commercium. The latter is res extra commercium based on both the customary international law and treaty, however, the former is different respectively according to the customary law and treaty. Under international customary law, whilst outer space constitutes res extra commercium, celestial bodies are res nullius. However as among contracting States of the 1967 Outer Space Treaty, both outer space and celestial bodies are declared res extra commercium. As for the comparisons of the exploration and exploitation of natural resources between the Moon including other celestial bodies in 1979 Moon Agreement and the deep sea bed in the 1982 United Nations Convention on the Law of the Sea, the both areas are the common heritage of mankind. The latter gives us very systematic models such as International Sea-bed Authority, however, the international regime for the former will be established as the exploitation of the natural resources of the celestial bodies other than the Earth is about to become feasible. Thus Moon Agreement could not impose a moratorium, but would merely permit orderly attempts to establish that such exploitation was in fact feasible and practicable, by allowing experimental beginnings and thereafter pilot operations. As Professor Carl Christol said until the parties of the Moon Agreement were able to put into operation the legal regime for the equitable sharing of benefits, they would remain free to disregard the Common Heritage of Mankind principle. Parties to one or both of the agreements would retain jurisdiction over national space activities. In so far as the comparisons of the protection of the environment between the outer space and sea is concerned the legal instruments for the latter are more systematically developed than the former. In the case of the former there are growing tendencies of concerning the environmental threats arising from space activities these days. There is no separate legal instrument to deal with those problems.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.5
• /
• pp.636-640
• /
• 2000

Cup-plant (Silphium perfoliatum L.) has potential to produce high biomass and highly digestible forage in the wetlands where other productive forages do not grow or produce well. However, high moisture content at harvest is a considerable disadvantage of cup-plant for the production of high quality silage. This study was conducted to determine the effect of moisture content on the characteristics of cup-plant silage. Harvested cup-plant was ensiled in farm scale plastic bag silos and laboratory silos. In the plastic bag silos, first growth (FG) and regrowth (RG) cup-plant was harvested, wilted and ensiled. Dry matter content of FG and RG was 280 g/kg and 320 g/kg after 48 hr of wilting. The silage made with FG had pH 5.3 and 5.63 g/kg DM of acetate as a major volatile fatty acid. The composition of lactate, butyrate and acetate production was 1.0: 0.9: 2.3. The pH of silage made with RG was 4.5 and lactate was a major fermentation end product (16.8 g/kg DM). In the laboratory silos, wilted and unwilted first growth cup-plant material was ensiled to compare the early fermentation end products at days 2, 4, 11, and 40. Wilting increased dry matter content by 42% in the harvested material. Wilted silage showed about one unit lower pH until day 11. The contents of ammonia nitrogen and acetate were higher in un wilted silage, while that of lactate was higher in wilted silage (p<0.05). Butyrate and propionate were not detected in the wilted silage until day 40. We conclude from the results that moisture control is essential for the production of high quality cup-plant silage and high pH of cup-plant silage is due to low concentrations of fermentation end products.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.48-55
• /
• 2022

Tomato crops are easy to expose to disease and spread in a short period of time, so late measures against disease are directly related to production and sales, which can cause damage. Therefore, there is a need for a service that enables early prevention by simply and accurately diagnosing tomato diseases in the field. In this paper, we construct a system that applies a deep learning-based model in which ImageNet transition is learned in advance to classify and serve nine classes of tomatoes for disease and normal cases. We use the input of MobileNet, ResNet, with a deep learning-based CNN structure that builds a lighter neural network using a composite product for the image set of leaves classifying tomato disease and normal from the Plant Village dataset. Through the learning of two proposed models, it is possible to provide fast and convenient services using MobileNet with high accuracy and learning speed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.59-64
• /
• 2024

Recently, research on the convergence of drones and artificial intelligence technologies have been conducted in various industrial fields. In this paper, we propose an illegal parking vehicle recognition model using deep learning-based object recognition and classification algorithms. The model of object recognition and classification consist of YOLOv8 and ResNet18, respectively. The proposed model was trained using image data collected in general road environment, and the trained model showed high accuracy in determining illegal parking. From simulation results, it was confirmed that the proposed model has generalization performance to identify illegal parking vehicles from various images.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.29-39
• /
• 2022

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted high-resolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The Recall reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The IoU of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The IoU of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the IoU by 2.9%. In general, our method is of great significance for crack detection.