• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.198-210
• /
• 2022

The southern strait of Jeju is a divergence point of the Tsushima Warm Current (TWC), and it is the starting point of the thermohaline circulation in the waters of the Korean Peninsula, affecting the size and frequency of marine disasters such as typhoons and tsunamis, and has a very important oceanographic impact, such as becoming a source of harmful organisms and radioactively contaminated water. Therefore, for an immediate response to these maritime disasters, real-time ocean observation is required. However, compared to other straits, in the case of southern Jeju, such wide area marine observations are insufficient. Therefore, in this study, surface current field of the southern strait of Jeju was calculated using High-Frequency radar (HF radar). the large surface current field is calculated, and post-processing and data improvement are carried out through APM (Antenna Pattern Measurement) and FOL (First Order Line), and comparative analysis is conducted using actual data. As a result, the correlation shows improvement of 0.4~0.7 and RMSE of about 1~19 cm/s. These high-frequency radar observation results will help solve domestic issues such as response to typhoons, verification of numerical models, utilization of wide area wave data, and ocean search and rescue in the future through the establishment of an open data network.

• Journal of Platform Technology
• /
• v.10 no.4
• /
• pp.47-55
• /
• 2022

Recently, diverse devices using different wireless technologies are gradually increasing in the IoT environment. In particular, it is essential to design an efficient feature extraction approach and detect the exact types of radio signals in order to accurately identify various radio signal modulation techniques. However, it is difficult to gather labeled wireless signal in a real environment due to the complexity of the process. In addition, various learning techniques based on deep learning have been proposed for wireless signal classification. In the case of deep learning, if the training dataset is not enough, it frequently meets the overfitting problem, which causes performance degradation of wireless signal classification techniques using deep learning models. In this paper, we propose a generative adversarial network(GAN) based on data augmentation techniques to improve classification performance when various wireless signals exist. When there are various types of wireless signals to be classified, if the amount of data representing a specific radio signal is small or unbalanced, the proposed solution is used to increase the amount of data related to the required wireless signal. In order to verify the validity of the proposed data augmentation algorithm, we generated the additional data for the specific wireless signal and implemented a CNN and LSTM-based wireless signal classifier based on the result of balancing. The experimental results show that the classification accuracy of the proposed solution is higher than when the data is unbalanced.

• Economic and Environmental Geology
• /
• v.56 no.4
• /
• pp.365-384
• /
• 2023

We applied the partitioned waveform inversion to 2,026 event data recorded at 173 seismic stations from the Incorporated Research Institutions for Seismology Data Managing Center and the Ocean Hemisphere network Project to estimate S-wave velocity and radial anisotropy models beneath the Western Pacific. In the Philippine Sea plate, high-Vs anomalies reach deeper in the West Philippine basin than in the Parece-Vela basin. Low-Vs anomalies found at 80 km below the Parece-Vela basin extend deeper into the West Philippine Basin. This velocity contrast between the basins may be caused by differences in lithospheric age. Low-Vs anomalies are observed beneath the Caroline seamount chain and the Caroline plate. Overall positive radial anisotropy anomalies are observed in the Western Pacific, but negative radial anisotropy is found at > 220 km depth on the subducting plate along the Mariana trench and at ~50 km in the Parece-Vela basin. Positive radial anisotropy is found at > 200 km depth beneath the Caroline seamount chain, which may indicate the 'drag' between the plume and the moving Pacific plate. High-Vs anomalies are found at 40 ~ 180 km depth beneath the Ontong-Java plateau, which may indicate the presence of unusually thick lithosphere due to underplating of dehydrated plume material.

• Journal of Veterinary Science
• /
• v.24 no.3
• /
• pp.44.1-44.17
• /
• 2023

Background: Antibiotic resistance is a significant public health concern around the globe. Antimicrobial peptides exhibit broad-spectrum and efficient antibacterial activity with an added advantage of low drug resistance. The higher water content and 3D network structure of the hydrogels are beneficial for maintaining antimicrobial peptide activity and help to prevent degradation. The antimicrobial peptide released from hydrogels also hasten the local wound healing by promoting epithelial tissue regeneration and granulation tissue formation. Objective: This study aimed at developing sodium alginate based hydrogel loaded with a novel antimicrobial peptide Chol-37(F34-R) and to investigate the characteristics in vitro and in vivo as an alternative antibacterial wound dressing to treat infectious wounds. Methods: Hydrogels were developed and optimized by varying the concentrations of crosslinkers and subjected to various characterization tests like cross-sectional morphology, swelling index, percent water contents, water retention ratio, drug release and antibacterial activity in vitro, and Pseudomonas aeruginosa infected wound mice model in vivo. Results: The results indicated that the hydrogel C proved superior in terms of cross-sectional morphology having uniformly sized interconnected pores, a good swelling index, with the capacity to retain a higher quantity of water. Furthermore, the optimized hydrogel has been found to exert a significant antimicrobial activity against bacteria and was also found to prevent bacterial infiltration into the wound site due to forming an impermeable barrier between the wound bed and external environment. The optimized hydrogel was found to significantly hasten skin regeneration in animal models when compared to other treatments in addition to strong inhibitory effect on the release of pro-inflammatory cytokines (interleukin-1β and tumor necrosis factor-α). Conclusions: Our results suggest that sodium alginate -based hydrogels loaded with Chol-37(F34-R) hold the potential to be used as an alternative to conventional antibiotics in treating infectious skin wounds.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.5
• /
• pp.53-64
• /
• 2009

Many slope failures are induced by rainfall infiltration. A lot of recent researches are therefore focused on rainfall-induced slope instability and the rainfall infiltration is recognized as the important triggering factor. The rainfall infiltrates into the soil slope and makes the matric suction lost in the slope and even the positive pore water pressure develops near the surface of the slope. They decrease the resisting shear strength. In Korea, a few public institutions suggested conservative slope design guidelines that assume a fully saturated soil condition. However, this assumption is irrelevant and sometimes soil properties are misused in the slope design method to fulfill the requirement. In this study, a more relevant slope stability evaluation method is suggested to take into account the real rainfall infiltration phenomenon. Unsaturated soil properties such as shear strength, soil-water characteristic curve and permeability for Korean weathered soils were obtained by laboratory tests and also estimated by artificial neural network models. For real-time assessment of slope instability, failure warning criteria of slope based on deterministic and probabilistic analyses were introduced to complement uncertainties of field measurement data. The slope stability evaluation technique can be combined with field measurement data of important factors, such as matric suction and water content, to develop an early warning system for probably unstable slopes due to the rainfall.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.576-584
• /
• 2022

As an important branch of cognitive psychology, "constructivism" is called a "revolution" in contemporary educational psychology, which has a profound influence on the field of pedagogy and psychology. Based on "WOS" database, this study selects "WOS Core database" and "KCI database", uses CiteSpace visualization software as analysis tool, and makes knowledge map analysis on the research literature of "constructivism" in the field of education in recent 35 years. Analysis directions include annual analysis, network connection analysis by country(region) branch, author, institution or University, and keyword analysis. The purpose of the analysis is to grasp the subject areas, research hotspots and future trends of the research on constructivism, and to provide theoretical reference for the research on constructivism. There are three conclusions from the study. 1. Studies on the subject of constructivism have continued from the 1980s to the present. It is now in a period of steady development. 2. Countries concerned with the subject of constructivism mainly include the United States, Canada, Britain, Australia and the Netherlands. The main research institutions and authors are mainly located in these countries. 3. Currently, the keywords constructivism research focus on the clusters of "instructional strategies", and the development of science and technology is affecting individual learning. In the future, instructional strategies will become the focus of structural constructivism research. With the development of instructional technology, it is necessary to conduct research related to the development of new teaching models.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.133-145
• /
• 2022

Compared to the continuously increasing dog population and industry size in Korea, systematic analysis of related data and research on breed classification methods are very insufficient. In this paper, an automatic breed classification method is proposed using deep learning technology for 14 major dog breeds domestically raised. To do this, dog images are collected for deep learning training and a dataset is built, and a breed classification algorithm is created by performing transfer learning based on VGG-16 and Resnet-34 as backbone networks. In order to check the transfer learning effect of the two models on dog images, we compared the use of pre-trained weights and the experiment of updating the weights. When fine tuning was performed based on VGG-16 backbone network, in the final model, the accuracy of Top 1 was about 89% and that of Top 3 was about 94%, respectively. The domestic dog breed classification method and data construction proposed in this paper have the potential to be used for various application purposes, such as classification of abandoned and lost dog breeds in animal protection centers or utilization in pet-feed industry.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.197-216
• /
• 2022

With the development of Internet and mobile technology and the spread of social media, a large amount of information is being generated and distributed online. Some of them are useful information for the public, but others are misleading information. The misleading information, so-called 'fake news', has been causing great harm to our society in recent years. Since the global spread of COVID-19 in 2020, much of fake news has been distributed online. Unlike other fake news, fake news related to COVID-19 can threaten people's health and even their lives. Therefore, intelligent technology that automatically detects and prevents fake news related to COVID-19 is a meaningful research topic to improve social health. Fake news related to COVID-19 has spread rapidly through social media, however, there have been few studies in Korea that proposed intelligent fake news detection using the information about how the fake news spreads through social media. Under this background, we propose a novel model that uses Graph2vec, one of the graph embedding methods, to effectively detect fake news related to COVID-19. The mainstream approaches of fake news detection have focused on news content, i.e., characteristics of the text, but the proposed model in this study can exploit information transmission relationships in social engagement networks when detecting fake news related to COVID-19. Experiments using a real-world data set have shown that our proposed model outperforms traditional models from the perspectives of prediction accuracy.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.85-100
• /
• 2023

Corporate ESG performance (environmental, social, and corporate governance) reflecting a company's strategic sustainability has emerged as one of the main factors in today's investment decisions. The traditional ESG performance rating process is largely performed in a qualitative and subjective manner based on the institution-specific criteria, entailing limitations in reliability, predictability, and timeliness when making investment decisions. This study attempted to predict the corporate ESG rating through automated machine learning based on quantitative and disclosed corporate financial information. Using 12 types (21,360 cases) of market-disclosed financial information and 1,780 ESG measures available through the Korea Institute of Corporate Governance and Sustainability during 2019 to 2021, we suggested a deep neural network prediction model. Our model yielded about 86% of accurate classification performance in predicting ESG rating, showing better performance than other comparative models. This study contributed the literature in a way that the model achieved relatively accurate ESG rating predictions through an automated process using quantitative and publicly available corporate financial information. In terms of practical implications, the general investors can benefit from the prediction accuracy and time efficiency of our proposed model with nominal cost. In addition, this study can be expanded by accumulating more Korean and international data and by developing a more robust and complex model in the future.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.85-92
• /
• 2023

Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.