• Journal of the Korea Convergence Society
• /
• v.4 no.1
• /
• pp.21-26
• /
• 2013

Due to a lack of research regarding disruptive technologies in domestic research, the purpose of this study is to aid in the understanding of disruptive technologies through empirical analysis of cases selected in the computer data storage industry. Analysis results have shown that SSDs, which threaten the existence of HDDs, adhere to the conditions of being a disruptive technology as first presented by Christensen(1992). SSDs are not only technologically superior to HDDs but can be mass produced due to its applicability in a vast array of product categories made possible by their miniaturization, weight reduction, and safety. This diversity of applicable fields makes it possible for mass production leading to further decrease in the unit price ultimately continuing the diffusion of this technology. By presenting empirical cases to aid in the understanding of disruptive technology, it is determined that the findings of this study contribute greatly to both academia and the business world.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.593-598
• /
• 2022

Recently, data production has seen explosive growth, and the storage systems to store these big data safely and quickly is evolving in various ways. A typical configuration of storage systems is the use of SSDs with fast data processing speed as a RAID group that can maintain reliable data. However, since NAND flash memory, which composes SSD, has the feature that deterioration if writes more than a certain number of times are repeated, can increase the likelihood of simultaneous failure on multiple SSDs in a RAID group. And this can result in serious reliability problems that data cannot be recovered. Thus, in order to solve this problem, we propose a method of throttling IOs so that each SSD within a RAID group leads to a different life-end. The technique proposed in this paper utilizes SMART to control the state of each SSD and the number of IOs allocated according to the data pattern used step by step. In addition, this method has the advantage of preventing large amounts of concurrency defects in RAID because it induces differential lifetime finishes of SSDs.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• KNOM Review
• /
• v.22 no.3
• /
• pp.25-30
• /
• 2019

For meteorological applications, meaningful results must be derived and provided within time and resource limits. Forecasts through numerous historical data are time-consuming and still have resource limitations in the case of disaster safety-related analyses/predictions such as local typhoon forecasts. Suitable forecasts should be provided without any problems caused by limited physical environmental conditions and when results are to be drawn under time constraints, such as typhoon forecasts and forecast services for flooded areas by road. In this paper, we analyze the application of weather and climate forecasting to provide a suitable forecasting service in both temporal and resource conditions. Through the analysis of execution time according to mesh sizes, it was confirmed that a mesh adjustment can cope with the case of the temporal constraint. In addition, by analyzing the execution time through memory resource control, we confirmed the minimum resource condition that does not affect the performance and the resource usage pattern of the application through the swap and mlock analysis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.2
• /
• pp.263-272
• /
• 2022

As a result of climate change, the heatwave and urban heat island phenomena have become more common, and the frequency of heatwaves is expected to increase by two to six times by the year 2050. In particular, the heat sensation index felt by workers at construction sites during a heatwave is very high, and the sensation index becomes even higher if the urban heat island phenomenon is considered. The construction site environment and the situations of construction workers vulnerable to heat are not improving, and it is now imperative to respond effectively to reduce such damage. In this study, satellite imagery, land surface temperatures (LST), and long short-term memory (LSTM) were applied to analyze areas above 33 ℃, with the most vulnerable areas with increased synergistic damage from heat waves and the urban heat island phenomena then predicted. It is expected that the prediction results will ensure the safety of construction workers and will serve as the basis for a construction site early-warning system.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.2
• /
• pp.65-79
• /
• 2024

This study employs traditional statistical auto-regressive integrated moving average (ARIMA) and deep learning-based long short-term memory (LSTM) models to predict the deformation of earth retaining walls using inclinometer data from excavation sites. It compares the predictive capabilities of both models. The ARIMA model excels in analyzing linear patterns as time progresses, while the LSTM model is adept at handling complex nonlinear patterns and long-term dependencies in the data. This research includes preprocessing of inclinometer measurement data, performance evaluation across various data lengths and input conditions, and demonstrates that the LSTM model provides statistically significant improvements in prediction accuracy over the ARIMA model. The findings suggest that LSTM models can effectively assess the stability of retaining walls at excavation sites. Additionally, this study is expected to contribute to the development of safety monitoring systems at excavation sites and the advancement of time series prediction models.

• IMMUNE NETWORK
• /
• v.5 no.2
• /
• pp.89-98
• /
• 2005

Background: DNA vaccination represents an anticipated approach for the control of numerous infectious diseases. Used alone, however, DNA vaccine is weak immunogen inferior to viral vectors. In recent, heterologous prime-boost vaccination leads DNA vaccines to practical reality. Methods: We assessed prime-boost immunization strategies with a DNA vaccine (minigene, $gB_{498-505}$ DNA) and recombinant vaccinia virus $(vvgB_{498-505})$ expressing epitope $gB_{498-505}$ (SSIEF ARL) of CD8+ T cells specific for glycoprotein B (gB) of herpes simplex virus (HSV). Animals were immunized primarily with $gB_{498-505}$ epitope-expressing DNA vaccine/recombinant vaccinia virus and boosted with alternative vaccine type expressing entire Ag. Results: In prime-boost protocols using vvgBw (recombinant vaccinia virus expressing entire Ag) and $vvgB_{498-505}$, CD8+ T cell-mediated immunity was induced maximally at both acute and memory stages if primed with vvgBw and boosted with $vvgB_{498-505}$ as evaluated by CTL activity, intracellular IFN-staining, and MHC class I tetramer staining. Similarly $gB_{498-505}$ DNA prime-gBw DNA (DNA vaccine expressing entire Ag) boost immunization elicited the strongest CD8+ T cell responses in protocols based on DNA vaccine. However, the level of CD8+ T cell-mediated immunity induced with prime-boost vaccination using DNA vaccine expressing epitope or entire Ag was inferior to those based on vvgBw and $vvgB_{498-505}$. Of particular interest CD8+ T cell-mediated immunity was optimally induced when $vvgB_{498-505}$ was used to prime and gB DNA was used as alternative boost. Especially CD7+ T cell responses induced by such protocol was longer lasted than other protocols. Conclusion: These facts direct to search for the effective strategy to induce optimal CD8+ T cell-mediated immunity against cancer and viral infection.

• Korean Journal of Environmental Agriculture
• /
• v.30 no.3
• /
• pp.288-294
• /
• 2011

BACKGROUND: Methylmercury is analyzed by HPLC-ICP/MS because of the simplicity for sample preparation and interference. However, most of the pre-treatment methods for methylmercury need a further pH adjustment of the extracted solution and removal of organic matter for HPLC. The purpose of this study was to establish a rapid and accurate analytical method for determination of methylmercury in fish by using HPLC-ICP/MS. METHOD AND RESULTS: We conducted an experiment for pre-treatment and instrument conditions and analytical method verification. Pre-treatment condition was established with aqueous 1% L-cysteine HCl and heated at $60^{\circ}C$ in microwave for 20 min. Methylmercury in $50{\mu}L$ of filtered extract was separated by a C18 column and aqueous 0.1% L-cysteine HCl + 0.1% L-cysteine mobile phase at $25^{\circ}C$. The presence of cysteine in mobile phase and sample solution was essential to eliminate adsorption, peak tailing and memory effect problems. Correlation coefficient($r^2$) for the linearity was 0.9998. The limits of detection and quantitation for this method were 0.15 and $0.45{\mu}g/kg$ respectively. CONCLUSION: Result for analytical method verification, accuracy and repeatability of the analytes were in good agreement with the certified reference materials values of methylmercury at a 95% confidence level. The advantage of the established method is that the extracted solution can be directly injected into the HPLC column without additional processes and the memory effect of mercury in the ICP-MS can be eliminated.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.22 no.4
• /
• pp.253-261
• /
• 2011

Objectives : This study aimed to investigate the efficacy and safety of Metadate CD (MCD) when given to Korean children and adolescents with attention-deficit hyperactivity disorder (ADHD). We also explored the effects of the drug on diverse neuro-cognitive functions. Methods : Ninety-one subjects with ADHD (mean age 8.6${\pm}$2.2 years) were recruited at 6 outpatient clinics in Seoul, Korea. We used the ADHD Rating Scale (ARS), Clinical Global Impression (CGI), and comprehensive attention test (CAT) to measure the drug's effects. Results : After 0.92${\pm}$0.32mg/kg/day of MCD were administered for 57.4${\pm}$7.6 days, there was a 48.5% reduction in the mean total ARS scores (p<.001). Fifty-seven subjects (64.8%) showed either much improved or very much improved outcomes on the CGI-Improvement scale. The CGI-Severity scale also decreased from an average of 4.7 to an average of 2.9 (p<.001). Errors and response time standard deviations of the CAT, sustained attention test-to-response tasks, the flanker test, and divided attention test scores decreased after treatment (p<.05). The forward memory span of the spatial working memory test scores increased (p<.05). Thirty-five patients (39.8%) experienced side effects, of which the most common were headache (14.8%), nausea (12.5%), and anorexia (9.1%). Conclusion : This open-label study suggests that MCD is effective and safe in improving the symptoms and neurocognitive functions of Korean children and adolescents with ADHD.