• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3409-3416
• /
• 2023

Licensing the next-generation of nuclear reactor designs requires extensive use of Modeling and Simulation (M&S) to investigate system response to many operational conditions, identify possible accidental scenarios and predict their evolution to undesirable consequences that are to be prevented or mitigated via the deployment of adequate safety barriers. Deep Learning (DL) and Artificial Intelligence (AI) can support M&S computationally by providing surrogates of the complex multi-physics high-fidelity models used for design. However, DL and AI are, generally, low-fidelity 'black-box' models that do not assure any structure based on physical laws and constraints, and may, thus, lack interpretability and accuracy of the results. This poses limitations on their credibility and doubts about their adoption for the safety assessment and licensing of novel reactor designs. In this regard, Physics Informed Neural Networks (PINNs) are receiving growing attention for their ability to integrate fundamental physics laws and domain knowledge in the neural networks, thus assuring credible generalization capabilities and credible predictions. This paper presents the use of PINNs as surrogate models for accidental scenarios simulation in Nuclear Power Plants (NPPs). A case study of a Loss of Heat Sink (LOHS) accidental scenario in a Nuclear Battery (NB), a unique class of transportable, plug-and-play microreactors, is considered. A PINN is developed and compared with a Deep Neural Network (DNN). The results show the advantages of PINNs in providing accurate solutions, avoiding overfitting, underfitting and intrinsically ensuring physics-consistent results.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.353-360
• /
• 2022

Due to the dense and complicated working environment, the construction industry is susceptible to many accidents. Worker's fall is a severe problem at the construction site, including falling into holes or openings because of the inadequate coverings as per the safety rules. During the construction or demolition of a building, openings and holes are formed in the floors and roofs. Many workers neglect to cover openings for ease of work while being aware of the risks of holes, openings, and gaps at heights. However, there are safety rules for worker safety; the holes and openings must be covered to prevent falls. The safety inspector typically examines it by visiting the construction site, which is time-consuming and requires safety manager efforts. Therefore, this study presented a worker-driven approach (the worker is involved in the reporting process) to facilitate safety managers by developing integrated computer vision and inertia sensors-based mobile applications to identify openings. The TensorFlow framework is used to design Convolutional Neural Network (CNN); the designed CNN is trained on a custom dataset for binary class openings and covered and deployed on an android smartphone. When an application captures an image, the device also extracts the accelerometer values to determine the inclination in parallel with the classification task of the device to predict the final output as floor (openings/ covered), wall (openings/covered), and roof (openings / covered). The proposed worker-driven approach will be extended with other case scenarios at the construction site.

• Journal of Creative Information Culture
• /
• v.5 no.1
• /
• pp.35-43
• /
• 2019

In this study, we analyzed how information and technology education in elementary and middle school curriculum affects learning achievement of computational thinking courses in university. We conducted a questionnaire survey on students who took computer-related courses for the past year and collected data on what type of computer-related education they received. As a result of analyzing the data, students who received computer-related education in the previous curriculum showed higher overall academic achievement. However, there was a significant difference in learning achievement according to types of contents, and it is necessary to consider the design and improvement of efficient computational thinking education in the future through the results. It is also necessary to continue the analysis of the impact of the new education curriculum.

• Journal of Creative Information Culture
• /
• v.5 no.3
• /
• pp.203-214
• /
• 2019

This study is to investigate the effects of multimedia education on the teaching method of safety education knowledge and safety education attitude of children based on the analysis, design, development, implementation and evaluation stages of ADDIE model. In order to verify the above research problem, the experiment was conducted with 52 children aged 5 years in A nursery school located in Busan, for about 3 week. The main results of this study were summarized as follows. Frist, multimedia-based instruction group showed higher safety education knowledge score than instruction group using direct teaching method, and statistically significant difference was found. Second, there was no statistically significant difference between the group using multimedia and the class using direct teaching method.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.197-202
• /
• 2023

This paper presents the design method and electrical characteristics of a high-efficiency power amplifier for a 50 Watts class repeater applied to a 5G system and used in in-building, subway, and tunnel. GaN was used for the termination transistor of the power amplifier designed here, and intermodulation signals were removed using DPD to satisfy linearity. In addition, in order to handle various requirements such as amplifier gain control and alarm processing required in the 5G system, the microprocessor is designed to exist inside the power amplifier. The amplifier manufactured to confirm the electrical performance of the power amplifier satisfying these conditions satisfied 46.5 dBm and the overall efficiency of the amplifier was 37%, and it was confirmed that it satisfied various alarm conditions and electrical characteristics required by telecommunication companies.

• The korean journal of orthodontics
• /
• v.53 no.2
• /
• pp.125-136
• /
• 2023

Before progress was recently made in the application of temporary anchorage devices (TADs) in bio-mechanical design, orthodontists were rarely able to intrude molars to reduce upper posterior dental height (UPDH). However, TADs are now widely used to intrude molars to flatten the occlusal plane or induce counterclockwise rotation of the mandible. Previous studies involving clinical or animal histological evaluation on changes in periodontal conditions after molar intrusion have been reported, however, studies involving human histology are scarce. This case was a Class I malocclusion with a high mandibular plane angle. Upper molar intrusion with TADs was performed to reduce UPDH, which led to counterclockwise rotation of the mandible. After 5 months of upper molar intrusion, shortened clinical crowns were noticed, which caused difficulties in oral hygiene and hindered orthodontic tooth movement. The mid-treatment cone-beam computed tomography revealed redundant bone physically interfering with buccal attachment and osseous resective surgeries were followed. During the surgeries, bilateral mini screws were removed and bulging alveolar bone and gingiva were harvested for biopsy. Histological examination revealed bacterial colonies at the bottom of the sulcus. Infiltration of chronic inflammatory cells underneath the non-keratinized sulcular epithelium was noted, with abundant capillaries being filled with red blood cells. Proximal alveolar bone facing the bottom of the gingival sulcus exhibited active bone remodeling and woven bone formation with plump osteocytes in the lacunae. On the other hand, buccal alveolar bone exhibited lamination, indicating slow bone turnover in the lateral region.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.124-132
• /
• 2022

Recently, due to COVID-19, online remote classes and non-face-to-face exams have made it difficult to manage class attitudes and exam cheating. Therefore, there is a need for a system that automatically recognizes and detects the behavior of students online. Action recognition, which recognizes human action, is one of the most studied technologies in computer vision. In order to develop such a technology, data including human arm movement information and information about surrounding objects, which can be key information in online classes and exams, are needed. It is difficult to apply the existing dataset to this system because it is classified into various fields or consists of daily life action. In this paper, we propose a dataset that can classify attitudes in real-time online tests and classes. In addition, it shows whether the proposed dataset is correctly constructed through comparison with the existing action recognition dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• Journal of Industrial Convergence
• /
• v.21 no.7
• /
• pp.41-49
• /
• 2023

In recent years, various educational institutions have used online certificate services to verify academic achievement related to graduation and grades. However, the certificate of the existing system has limitations in verifying and tracking whether it is true or not and detailed academic background. In this regard, cases of forgery/falsification of online/offline certificates continue to occur. This study proposes a blockchain-based verification method that is safe from forgery and alteration, focusing on university institutions. Necessary information such as detailed class categories for each department, attendance, and detailed grades was collected/analyzed to create a linkage relationship through blockchain. In addition, the system/network environment required for blockchain sharing was considered, and it was implemented as an extension module in the form of an independent web application. As a result of the block chain verification, it was proved that the safe trust verification of educational information and the relationship between detailed information can be traced. This study aims to contribute to the improvement of academic credential verification services and information security for Korean educational institutions in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.592-593
• /
• 2021

In July of last year, the Korean version of the New Deal National Report Conference was held in the presence of the President, and the "Korean version of the New Deal Comprehensive Plan" was announced as its core strategy. In the field of education, the "Green Smart Future School" project has been included as one of the top 10 Korean New Deal projects. And last year, due to the spread of non-face-to-face classes due to COVID-19, the demand for ICT technology in front-line education sites rapidly increased. Therefore, In this paper, we examine the problems of the wireless network and wired infrastructure of the classroom in the past, and design wired network infrastructure and wireless network equipment for green smart classrooms with high-speed wireless networks that can be used for non-face-to-face and face-to-face classes, and build them in actual classrooms. An example for the following was presented.