• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.2
• /
• pp.93-101
• /
• 2019

The mechanical properties and microstructure of 1st stage used and casted buckets of $1,100^{\circ}C$ class gas turbine were analyzed to evaluate quality of the components. Gas turbine 1st stage buckets are exposed and operated in the most severe environment except 1st nozzle among the hot path gas components. Additionally, since the 1st stage bucket is a rotating component, so it may cause additional damage to the rear buckets and nozzles which cause a huge financial loss. Therefore, the quality of the casted bucket must be evaluated prior to use at the plant site. In this study, the microstructure analysis and mechanical properties of the casted bucket were evaluated to verify the casting quality and it was confirmed that the quality conditions designed by KEPCO were satisfied. A bucket operated 46% (11,067EOH) of its life time also evaluated for quality comparison.

• Journal of the Korea Institute of Building Construction
• /
• v.19 no.1
• /
• pp.77-86
• /
• 2019

Due to the increasing demand for and complexity of plant construction projects, unpredictable risk factors are on the consequent increase. For that reason, the quantitative risk analysis is being called for, in order for the development of a risk assessment model using risk indicators for the plant construction projects. This study used the claim payout data collected at a global insurance company to reflect the actual financial losses in plant construction projects as dependent variables in the risk assessment model. In terms of independent variables, the geographic information, i. e., landform, and the construction information including test-run, schedule rate, total cost and duration are adopted. In addition, this study suggests that the regression model containing such independent variables that are statistically significant can be applied to as a foundational guideline for the plant construction project risk analysis during the phase of construction and commissioning.

• The Research Journal of the Costume Culture
• /
• v.27 no.5
• /
• pp.496-511
• /
• 2019

The purpose of this study was to create a theoretical structure for the concept of purchasing risks by identifying the structure of purchasing risks that lead to obstacles in the purchasing decisions of consumers in fashion consumption via online channels. This was a secondary research using books, articles, prior researches, and academic journals on the five topics of "characteristics of fashion consumption," "the concept of purchasing risks," "purchasing risks by product types," "purchasing risks by channel types," and "purchasing risks of fashion consumption on online shopping channels." According to the arguments of prior researches, the study divided the purchasing risks of fashion consumption through online shopping into four categories : (1) fundamental purchasing risks including financial risk and time loss risk pertaining to any product or channel, (2) online channel purchase risks, which include risks in payment, Information leaks, and delivery and return/exchange risk, (3) fashion product risk related to product quality or experience of other people, which includes social risks and risks associated with quality, and (4) the online channel${\times}$fashion product risks, which include the aesthetic and psychological hazards especially amplified in online channels. The four risk factors were then described with a concept map to systemize the multi-dimensional and stereoscopic psychological structure of purchasing risks. Of the four risk factors, consumers placed the most emphasis on the online channel${\times}$fashion product risks, hence, reducing this risk factor is of utmost priority for marketing of online shopping channels.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2019

As the fourth industrial revolution is emerging, many companies are increasingly interested in smart factories and the importance of sensors is being emphasized. In the case that sensors for collecting sensing data fail, the plant could not be optimized and further it could not be operated properly, which may incur a financial loss. For this purpose, it is necessary to diagnose the status of sensors to prevent sensor' fault. In the paper, we propose a scheme to diagnose digital-sensor' fault by analyzing the rising time and falling time of digital sensors through the LSTM(Long Short Term Memory) of Deep Learning RNN algorithm. Experimental results of the proposed scheme are compared with those of rule-based fault diagnosis algorithm in terms of AUC(Area Under the Curve) of accuracy and ROC(Receiver Operating Characteristic) curve. Experimental results show that the proposed system has better and more stable performance than the rule-based fault diagnosis algorithm.

• Research in Community and Public Health Nursing
• /
• v.30 no.2
• /
• pp.217-225
• /
• 2019

Purpose: The purpose of this study is to assess socio-demographic, disaster-related, physical health-related, psychological, and social factors that may adversely affect disaster victims' QoL (Quality of Life). Methods: A cross sectional study was designed by using the secondary data. From the 3rd Disaster Victims Panel Survey (2012~2017), a total of 1,659 data were analyzed by using descriptive statistics including frequency, percentage, t-test, ANOVA, and multivariate linear regression. Results: Older people with lower health status lacking financial resources prior to a disaster were more at risk of low levels of QoL. Lower levels of perceived health status, resilience, and QoL were reported by disaster exposed individuals, while their depression was higher than the depression in the control group of disaster unexposed ones. Resilience, social and material supports were positively associated with QoL whereas depression and PTSD (Post-Traumatic Stress Disorders) were negatively associated. Conclusion: These findings suggest that psychological symptoms and loss due to disasters can have adverse impacts on the QoL of disaster victims in accordance with their prior socio-demographic background. They also indicate that targeted post-disaster community nursing intervention should be considered a means of increased social support as well as physical and mental health care for disaster victims.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.3
• /
• pp.545-552
• /
• 2012

The rapid development of information technology is making large changes in our lives today. Also the infrastructure and services are combinding with information technology which predicts another huge change in our environment. However, the development of information technology brings various types of side effects and these side effects not only cause financial loss but also can develop into a nationwide crisis. Therefore, the detection and quick reaction towards these side effects is critical and much research is being done. Intrusion detection systems can be an example of such research. However, intrusion detection systems mostly tend to focus on judging whether particular traffic or files are malicious or not. Also it is difficult for intrusion detection systems to detect newly developed malicious codes. Therefore, this paper proposes a method which determines whether the present network model is normal or abnormal by comparing it with past network situations.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.511-517
• /
• 2021

In this paper, we analyzed the impact of capital adequacy requirements on the profitability of Korean banks using DOLS model. As a result of the analysis, the impact of BIS capital ratios on commercial and regional banks was different. Demand for capital adequacy has a greater and more significant negative impact on regional banks than on commercial banks. It was shown that bank characteristic variables rather than macroeconomic variables have a more significant effect on bank profitability. In addition, a rise in the BIS capital ratio reduces the profitability of commercial and regional banks, and the higher the ratio of loan-loss provisions, the stronger the relationship. In the case of commercial banks, it is estimated that the demand for capital adequacy did not have a significant impact as they are relatively large and faithful in capital compared to regional banks. However, in the case of regional banks, safer assets need to be selected to meet the BIS capital ratio, and the increasing propotion of these safe assets seems to have a relatively greater negative impact on profitability. Consequency, the financial authorities should consider this results and implement the bank's capital regulation policy.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.31-36
• /
• 2021

As the global economy stagnated due to the Corona 19 virus from Wuhan, China, most countries, including the US Federal Reserve System, introduced policies to boost the economy by increasing the amount of money. Most of the stock investors tend to invest only by listening to the recommendations of famous YouTubers or acquaintances without analyzing the financial statements of the company, so there is a high possibility of the loss of stock investments. Therefore, in this research, I have used artificial intelligence deep learning techniques developed under the existing automatic trading conditions to analyze and predict macro-indicators that affect stock prices, giving weights on individual stock price predictions through correlations that affect stock prices. In addition, since stock prices react sensitively to real-time stock market news, a more accurate stock price prediction is made by reflecting the weight to the stock price predicted by artificial intelligence through stock market news text mining, providing stock investors with the basis for deciding to make a proper stock investment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.199-206
• /
• 2022

A malfunction or breakdown of a manufacturing facility leads to product defects and the suspension of production lines, resulting in huge financial losses for manufacturers. Due to the spread of smart factory services, a large amount of data is being collected in factories, and AI-based research is being conducted to predict and diagnose manufacturing facility breakdowns or manufacturing site efficiency. However, because of the characteristics of manufacturing data, such as a severe class imbalance about abnormalities and ambiguous label information that distinguishes abnormalities, developing classification or anomaly detection models is highly difficult. In this paper, we present an deep learning algorithm for anomaly detection of a manufacturing facility using reconstruction loss of CNN-based model and ananlyze its performance. The algorithm detects anomalies by relying solely on normal data from the facility's manufacturing data in the exclusion of abnormal data.