• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.21-30
• /
• 2023

The study proposes a model that utilizes Python-based deep learning text classification techniques to detect the legality of illegal financial advertising posts on the internet. These posts aim to promote unlawful financial activities, including the trading of bank accounts, credit card fraud, cashing out through mobile payments, and the sale of personal credit information. Despite the efforts of financial regulatory authorities, the prevalence of illegal financial activities persists. By applying this proposed model, the intention is to aid in identifying and detecting illicit content in internet-based illegal financial advertisining, thus contributing to the ongoing efforts to combat such activities. The study utilizes convolutional neural networks(CNN) and recurrent neural networks(RNN, LSTM, GRU), which are commonly used text classification techniques. The raw data for the model is based on manually confirmed regulatory judgments. By adjusting the hyperparameters of the Korean natural language processing and deep learning models, the study has achieved an optimized model with the best performance. This research holds significant meaning as it presents a deep learning model for discerning internet illegal financial advertising, which has not been previously explored. Additionally, with an accuracy range of 91.3% to 93.4% in a deep learning model, there is a hopeful anticipation for the practical application of this model in the task of detecting illicit financial advertisements, ultimately contributing to the eradication of such unlawful financial advertisements.

• Korean Journal of Transplantation
• /
• v.31 no.4
• /
• pp.182-192
• /
• 2017

Background: In recent years, introduction of novel immunosuppressive agents and its proper implementation for clinical practice have contributed to improving clinical outcomes of kidney transplantation (KT). Here, we report clinical outcomes of KTs and related risk factors. Methods: From July 1998 to June 2016, 354 KTs (182 from living and 172 from deceased donors) have been performed at Ulsan University Hospital. We retrospectively reviewed the clinical characteristics and outcomes of KT recipients, then estimated graft and patient survival rate were estimated and analyzed risk factors using Cox-regression. Results: The median follow-up period was 53 months (range; 3 to 220 months). The mean ages of recipients and donors were 45.0 years (SD, 12.5) and 44.7 years (SD, 13.6) years, respectively. During follow-up, 18 grafts were lost and 5- and 10-year death-censored graft survival was 96.7% and 91.5%, respectively. Biopsy-proven acute rejection (BPAR) occurred in 71 patients (55 cases of acute cellular rejection and 16 of antibody-mediated rejection). Cox-regression analysis showed that BPAR was a risk factor related to graft loss (hazard ratio [HR], 14.38; 95% confidence interval [CI], 3.79 to 54.53; P<0.001). In addition, 15 patients died, and the 5- and 10-year patient survival was 97.2% and 91.9%, respectively. Age ≥60 years (HR, 6.03; 95% CI, 1.12 to 32.61; P=0.037) and diabetes (HR, 6.18; 95% CI, 1.35 to 28.22; P=0.019) were significantly related to patient survival. Conclusions: We experienced excellent clinical outcomes of KT in terms of graft failure and patient survival despite the relatively high proportion of deceased donors. Long-term and short-term clinical outcomes have improved in the last two decades.

• Maritime Security
• /
• v.6 no.1
• /
• pp.1-35
• /
• 2023

The purpose of this study is to present the direction of development of our navy's response strategy through analysis at the ends, ways, and means level of the Chinese navy's offensive strategy for the West Sea. As a result of the analysis, at the ends level, the Chinese Navy's offensive strategy for the West Sea strategy is being linked to a grand strategy to protect maritime rights and achieve maritime power between the U.S. and China competition, at the ways level, the Chinese Navy is expected to create a foundation for the international community to recognize the West Sea as China's inland sea through "routine entry" and "exercise authority", and in case of emergency, it will try to secure sea control in the West Sea in a short period of time by blocking Korea's maritime transportation route based on the overwhelming preemptive attack capability of aircraft carriers. At the means level, it is accelerating the construction of aircraft carrier warfare units and improving its ability to engage long-range missiles. As a direction of development of the Korean Navy's response strategy in response to this, first, Establishment and Development of National Maritime Security Strategy in conjunction with the Korean Indo-Pacific Strategy. Second, it proposes the development of the concept of effective security operations for the east sea area of the West Sea intermediate line, and third, the development of the concept of combat performance and capacity building to strengthen survival and lethality.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3C
• /
• pp.187-196
• /
• 2008

An earthquake of magnitude 5.0 occurred at Ssang-gye-sa, a Buddhist temple in Jirisan, located near the southern border of the Korean peninsula on 4 July 1936. It resulted in severe damage of several buildings and structures in Ssang-gye-sa. Particularly, the top component of a five-story stone pagoda in the temple was tipped over and fell down during the earthquake. This earthquake damage case would be usefully applied to estimating the intensity of ground motion in the Korean peninsula, a moderate seismicity region, where strong motion has never been recorded with the exception of historic seismic events. In order to estimate the local site effects and the corresponding ground motion at Ssang-gye-sa site, intensive site investigations including borehole drilling and in-situ seismic tests such as crosshole and SASW tests were performed in the temple area. Based on the site characteristics, site-specific seismic response analyses using various input motions were conducted for a representative Ssang-gye-sa site by means of both one-dimensional equivalent-linear and nonlinear methods with six input rock outcrop acceleration levels ranging from 0.044g to 0.220g. The resultant site-specific seismic responses indicated the amplified ground motions in the short-period range near the site period of Ssang-gye-sa. Furthermore, the intensity on rock outcrop of the 1936 Jirisan earthquake was estimated by making a comparison between the site responses analysis results in this study and the full-scaled seismic test of pagoda model in the prior study.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6B
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.34 no.1
• /
• pp.8-15
• /
• 2024

The CaF₂ single crystal has notable characteristics such as a large band gap (12 eV), excellent transparency over a wide wavelength range, low refractive index and dispersion. Due to these outstanding properties, CaF₂ single crystal has considered as a promising material for short-wavelength light sources in recent lithography processes. However, there is an inherent birefringence of the material at 157 nm and the resulting aberration can be compensated for through the combination of the (100) plane and the (111) plane. Therefore, it is necessary to investigate the characteristics according to the plane. In this study, we analyzed crystallinity, optical properties of commercial CaF₂ single crystal wafers grown by the Czochralski method. In particular, through chemical etching under various conditions, it was confirmed that the shape of etch pits appears differently depending on the plane and the shape and array of specific etch pits affected by dislocations and defects were examined.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.119-131
• /
• 2024

Understanding accurate traffic performance is crucial for ensuring efficient highway operation and providing a sustainable mobility environment. On the other hand, an immediate and precise estimation of highway traffic performance faces challenges because of infrastructure and technological constraints, data processing complexities, and limitations in using integrated big data. This paper introduces a framework for estimating traffic performance by analyzing real-time data sourced from toll collection systems and dedicated short-range communications used on highways. In particular, this study addresses the data errors arising from segmented information in data, influencing the individual travel trajectories of vehicles and establishing a more reliable Origin-Destination (OD) framework. The study revealed the necessity of trip linkage for accurate estimations when consecutive segments of individual vehicle travel within the OD occur within a 20-minute window. By linking these trip ODs, the daily average highway traffic performance for South Korea was estimated to be248,624 thousand vehicle kilometers per day. This value shows an increase of approximately 458 thousand vehicle kilometers per day compared to the 248,166 thousand vehicle kilometers per day reported in the highway operations manual. This outcome highlights the potential for supplementing previously omitted traffic performance data through the methodology proposed in this study.

• Journal of Life Science
• /
• v.34 no.4
• /
• pp.227-235
• /
• 2024

Hepatocyte damage caused by medications or herbal products is one of the important problem when these compounds are chronically administrated. Thus, improving hepatocyte survival during treatment offers a wide range of opportunities. Valproic acid (VPA), a branched short-chain fatty acid derived from naturally occurring valeric acid, is commonly used to treat epilepsy and seizures. Although VPA exerts numerous effects in cancer, HIV therapy, and neurodegenerative disease, its effects on the liver and its mechanism of action have not been fully elucidated. Here, we demonstrated that VPA caused moderate liver cell toxicity and apoptosis. Interestingly, VPA treatment increased transcription levels of PPAR alpha (PPAR-α) and fibroblast growth factor 21 (FGF21) in murine (Hepa1c1c7) hepatoma cells in a time and concentration dependent manner. VPA-induced FGF21 expression was significantly weaker under PPAR-α silencing condition than in cells transfected with non-targeting control siRNA. Subsequent experiments showed that cell viability was significantly lowered when the FGF21 signaling pathway was blocked by FGF receptor antagonist. Finally, we further determined that AMPK phosphorylation was not responsible for VPA-induced FGF21 expression and PPAR-a increments. These results indicate that increases of FGF21 expression alleviate VPA-induced hepatic toxicity, thereby making FGF21 a potential biomarker for predicting liver damage during VPA treatments.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.25 no.4
• /
• pp.84-89
• /
• 2024

Light is an important component among which plays a crucial role in determining the production and quality of fruit trees. Since the disturbance of light directly leads to reduced photosynthetic efficiency, their damage can be increased especially in fruit trees such as Japanese apricots with a short growing time. In this study, we investigated how the effects of shading condition can affect the production and quality of Japanese apricots according to increased damages by light disturbance in the main orchard complex. The average photosynthetically active radiation (PAR) level in Japanese apricots was rapidly dropped as the shading time was increased compared to the control (304 μmol/m²/s) and the PAR level decreased to 142 μmol/m²/s after shaded for eight hours. The maximum photosynthetic efficiency, with a PAR value of 900 to 1,000 μmol/m²/s, corresponds to the time period without shading and the time period with 2 hours of shading, and these times range from 11 a.m. to 3 p.m. And the time period for shading for 4 hours was from 1:00 p.m. to 2:00 p.m., and under conditions of shading for 6 and 8 hours, the effect was a low amount of light. There was no difference in the weight of Japanese apricots during 2 hours shading time, however, it was significantly reduced as shading time were increased. The difference of the acid content and L/D ratio was not significant on shading time, but the SSC was decreased as times going on. In conclusion, our results indicate that the shading for more than 2 hours make negative effects to decrease the weight and SSC and the yield and affects directly to drop in fruit quality.