• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.3
• /
• pp.205-216
• /
• 2024

Recently, seismic Probabilistic Safety Assessment (PSA) methods have been developed for process plants, such as gas plants, oil refineries, and chemical plants. The framework originated from the PSA of nuclear power plants, which aims to assess the risk of reactor core damage. The original PSA method was modified to adopt the characteristics of a process plant whose purpose is continuous operation without shutdown. Therefore, a fault tree, whose top event is shut down, was constructed and transformed into a Bayesian Network (BN), a probabilistic graph model, for efficient risk-informed decision-making. In this research, the fault tree-based BN from the previous research is further developed to consider the multi-hazard of earthquake-induced fire and explosion (EQ-induced F&E). For this purpose, an event tree describing the occurrence of fire and explosion from a release is first constructed and transformed into a BN. And then, this BN is connected to the previous BN model developed for seismic PSA. A virtual plot plan of a gas plant is introduced as a basis for the construction of the specific EQ-induced F&E BN to test the proposed BN framework. The paper demonstrates the method through two examples of risk-informed decision-making. In particular, the second example verifies how the proposed method can establish a repair and retrofit strategy when a shutdown occurs in a process plant.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.2
• /
• pp.312-320
• /
• 2012

In this study, we introduce a new design methodology of a granular-oriented self-organizing polynomial neural networks (GoSOPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). In contrast to the typical architectures encountered in polynomial neural networks (PNN), our main objective is to develop a methodological design strategy of GoSOPNNs as follows : (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context-based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets (so-called contexts) defined in the output space. (b) The proposed design procedure being applied at each layer of GoSOPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics (such as the number of contexts, the number of clusters, a collection of the specific subset of input variables, and the order of the polynomial) can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed GoSOPNN network, we describe a detailed characteristic of the proposed model using a well-known learning machine data(Automobile Miles Per Gallon Data, Boston Housing Data, Medical Image System Data).

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.693-703
• /
• 2005

Given the local traders with pattern-based multi-predictors of stock prices, we study a method of dynamic asset allocation to maximize the trading performance. To optimize the proportion of asset allocated to each recommendation of the predictors, we design an asset allocation strategy called meta policy in the reinforcement teaming framework. We utilize both the information of each predictor's recommendations and the ratio of the stock fund over the total asset to efficiently describe the state space. The experimental results on Korean stock market show that the trading system with the proposed meta policy outperforms other systems with fixed asset allocation methods. This means that reinforcement learning can bring synergy effects to the decision making problem through exploiting supervised-learned predictors.

• Fashion & Textile Research Journal
• /
• v.18 no.6
• /
• pp.766-775
• /
• 2016

In the era of globalization and unlimited competition, Korean universities need a breakthrough in their education system according to the changing education landscape, such as lower graduation requirements to cultivate more multi-talented convergence leaders. While each student has different learning capabilities, which results in different performance and achievements in the same class, the uniform education that most universities are currently offering fails to accommodate such differences. Blended learning, synergically combining offline and online classes, enlarges learning space and enriches learning experiences through diversified tools and materials, including multimedia. Recently, universities are increasingly adopting video contents and on-offline convergence learning strategy. Thus, this study suggests a teaching method based on blended learning to more effectively teach existing pattern CAD and virtual CAD in the Apparel Pattern CAD class. To this end, this researcher developed a teaching-learning method and curriculum according to the blended learning phase and video-based contents. The curriculum consisted of 2D CAD (SuperAlpha: Plus) and 3D CAD (CLO) software learning for 15 weeks. Then, it was loaded to the Learning Management System (LMS) and operated for 15 weeks both online and offline. The performance analysis of LMS usage found that class materials, among online postings, were viewed the most. The discussion menu most accurately depicted students' participation, and students who did not participate in discussions were estimated to check postings less than participating students. A survey on the blended learning found that students prefer digital or more digitized classes, while preferring face to face for Q&As.

• Journal of Technology Innovation
• /
• v.20 no.3
• /
• pp.1-28
• /
• 2012

This study conducted a qualitative analysis on the Korea's nuclear energy sector in 2030 through scenario-based strategic foresight method. Specifically, the relationships between environmental influencing factors of the future nuclear energy sector was examined from a multi-dimensional perspective on the basis of STEEP analysis and network analysis. In addition, scenario planning method was used with key uncertainty factors (KUF) to create three predictable strategic scenarios including optimistic, business as usual, and pessimistic. Common strategies that need to be urgently pursued as well as the maximum risk avoidance strategies for each scenario were also presented. This study further identified energy pricing, global economic trend, competitiveness in nuclear technology, and marketing capability as key uncertainty factors in the future nuclear energy industry sector. In order to furnish effective export strategy in the future nuclear energy sector, it was also suggested that government policy should adopt following measures as top priorities: securing nuclear safety technology, educating nuclear engineers, securing nuclear resources such as uranium, increasing nuclear capability and so on. The implications and limitations of this study were then discussed based on research findings.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.87-97
• /
• 2020

The purpose of this study was to investigate effect of simulation based education using standardized patient for contact precaution infection control for nursing student. This study was conducted by including 67 nursing student A university from October to December 2019. This study was mixed method research design. Knowledge and performance confidence related to multidrug resistant organism(MDRO) infection control were measured using questionnaires pre and post test, analyzed using paired t-test and reflection sheet was analyzed using content analysis method. After intervention, two variables were increased significantly. Results of the content analysis showed there were 39 significant statements, which were classified into 13 categories. These results suggest that education on simulation program using standardized patient for contact precaution infection control is effective strategy to enhance knowledge and performance confidence related to MDRO infection control and practical nursing infection control skill, patient centered care, interprofessional collaboration.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.77-80
• /
• 2017

One of the fundamental limits of Bluetooth Low Energy(BLE) is that the data transmission is available via singlehop connection. In this research, we suggested the stable multihop transmission method to overcome this limitation. In multihop connection situation, multiple singlehop connection should be made and disconnected dynamically. Therefore, we stored the data within the GATT layer and tried to send it dynamically. We divided whole process as 4 states, and let each nodes transfers around each states to make data connection safely. Also, we set the transfer policy between each states during the transmission to make a robust system. From the experiment in real-time environment, we proved that our method showed high rate of packet delivery in a multihop network, which consists of more than 3 nodes.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.8
• /
• pp.33-39
• /
• 2005

The maximum output torque and power developed by the machine is ultimately depended on the allowable inverter current rating and maximum voltage which the inverter can supply to the machine. Therefore, considering the limited voltage and current capacities, it is desirable to consider a control method which yields the best possible torque per ampere. In this paper, we propose fuzzy neural network(FNN) controller that combines a fuzzy control and the neural network for high performance control of induction motor drive. This controller composes antecedence of the fuzzy rules and consequence by a clustering method and a multi-layer neural networks. This controller is compounding of advantages that robust control of a fuzzy control and high-adaptive control of the neural networks. Also, this paper is proposed control of maximum torque per ampere(MTPA) of induction moor. This strategy is reposed which is simple in structure and has the honest goal of minimizing the stator current magnitude for given load torque. The performance of the proposed induction motor drive with maximum torque control using FNN controller is verified by analysis results at dynamic operation conditions.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

• Korean Security Journal
• /
• no.31
• /
• pp.125-155
• /
• 2012

Terrorist organization has shown the trend of secret organization and it is harder to cope with terrorism because of uncertainty of terrorism. Homegrown terrorism is the one, whose preparation, execution and effect are restricted to domestic area. By the way, in the worldwide economic depression, violence and radical demonstration have shown the expansion trends as in Middle East, political revolution of Africa, anti-social resistance of Europe and Wall Street Occupation of USA. Homegrown terrorism is occurring in various countries such as UK and Spain as well as USA. Specialists warn homegrown terrorism in Korea. The purpose of this study was to prospect the possibility of homegrown terrorism that can be generated in the transfer to multi-culture society as various foreigners come to Korea rapidly and suggest the method to cope with the trend. The study analyzed environment and analysis of homegrown terrorism that Korea faces now. The methods to cope with homegrown terrorism are as follows. First, distribution of radical homegrown terrorism via internet should be prevented. Second, the connection between terrorist organization and homegrown terrorist should be prevented. Third, there should be a cooperation among government, residents and religious group. Fourth, there should be an open approach against multi-culture society. Fifth, there should be a systematic control for cause of new conflict. Finally, there should be a long-term approach to cause of new conflict. If we do not make an effort to prevent homegrown terrorism, terrorism environment may face new aspect and national and social cost for it will increase.