• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.149-158
• /
• 2023

As data utilization is becoming more important recently, the importance of data centers is also increasing. However, the data center is a problem in terms of environment and economy because it is a massive power-consuming facility that runs 24 hours a day. Recently, studies using deep learning techniques to reduce power used in data centers or servers or predict traffic have been conducted from various perspectives. However, the amount of traffic data processed by the server is anomalous, which makes it difficult to manage the server. In addition, many studies on dynamic server management techniques are still required. Therefore, in this paper, we propose a dynamic server management technique based on Long-Term Short Memory (LSTM), which is robust to time series data prediction. The proposed model allows servers to be managed more reliably and efficiently in the field environment than before, and reduces power used by servers more effectively. For verification of the proposed model, we collect transmission and reception traffic data from six of Wikipedia's data centers, and then analyze and experiment with statistical-based analysis on the relationship of each traffic data. Experimental results show that the proposed model is helpful for reliably and efficiently running servers.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Nuclear Engineering and Technology
• /
• v.27 no.6
• /
• pp.859-869
• /
• 1995

The present study is to understand the physical phenomena anticipated during the accident with RHR loss under mid-loop operation in a PWR and, at the same time, to examine the prediction capability of RELAP5/MOD3.1 on such an accident, by simulating an integral test relevant to this accident for reliable analysis in an actual PWR. The selected experiment, i.g. BETHSY Test 6.9a, represents the configuration with the pressurizer manway open and steam generators unavailable during the accident. Accordingly, the results of this ok are sure to contribute to understanding both the key events as well as the sensitive parameters, anticipated in the accident, for validity of the actual analysis. In the simulation result overall behavior as well as major phenomena observed in the experiment have been predicted reasonably by RELAP5/MOD3.1, however, the problem associated with enormous computing time .due to small time step size has been encountered. Besides, the code prediction of higher swollen level in the pressure vessel has given rise to overestimation of both pressurizer level and RCS pressure. Subsequently, overprediction of the break flow through the manway has led to earlier core uncovery than that in the experiment by about 400 seconds. As a whole, it is demonstrated from both the experiment and the analysis that gravity feed has not been sufficient to recover the core level and thus additional forced feed has been necessary in this configuration.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.7
• /
• pp.5-16
• /
• 2008

Most of roadway tunnels have been constructed in the form of parallel twin tunnel in Korea. If parallel twin tunnel does not have a sufficient separation distance between tunnels, the problem of tunnel stability can occur. Generally, it is reported that tunnels are not influenced by each other when a center distance between tunnels is two times longer than tunnel diameter under the complete elastic ground and five times under the soft ground. In this study, the scaled model tests of closely-spaced parallel twin tunnel using homogeneous material are performed and induced displacements are measured around the tunnel openings during excavation. The influence of separation distance between tunnels on the behavior of closely-spaced tunnel is investigated. The experimental results are expressed by the induced displacement vector and progress of crack during construction and at failure. The results show that based on the analysis of induced displacement at the crown during construction, the additional displacement of the preceding tunnel induced by the excavation of following tunnel decreases as the separation distance between twin tunnel increases until the center to center distance is two times of tunnel diameter. Beyond this point, however, the additional displacement has become stabilized.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.2
• /
• pp.104-108
• /
• 2023

Because of recent expansion of the electric car market. it is highly growing that should be supplemented its performance and safely issue. The EMI problem due to the interlocking of electrical components that causes various safety problems such as fire in electric vehicles is emerging every time. We strive to achieve optimal charging efficiency by combining various technologies and reduce radioactive noise among the EMI noise of a weirless charging control module, one of the important parts of an electric vehicle was designed and tested. In order to analyze the EMI problems occurring in the wireless charging control module, the optimized wireless charging control module by applying the optimization design technology by learning the accumulated test data for critical factors by utilizing the Python-based script function in the Ansys simulation tool. It showed an EMI noise improvement effect of 25 dBu V/m compared to the charge control module. These results not only contribute to the development of a more stable and reliable weirless charging function in electric vehicles, but also increase the usability and efficiency of electric vehicles. This allows electric vehicles to be more usable and efficient, making them an environmentally friendly alternative.

• Journal of Industrial Convergence
• /
• v.21 no.3
• /
• pp.195-202
• /
• 2023

This study analyzes the results of a survey based on classes conducted in the field to understand the educational needs of learners, and reflects the elements necessary for SW education. In this study, various experimental elements according to learning motivation and learning achievement were constructed and designed through previous studies. As a survey applied to this study, experimental elements in three categories: Faculty Competences(FC), Learner Competences(LC), and Educational Conditions(EC) were analyzed by primary area and secondary major, respectively. As a result of analyzing CT-based SW education by area, the development of educational materials, understanding of lectures, and teaching methods showed high satisfaction, while communication with students, difficulty of lectures, and the number of students were relatively low. The results of the analysis by major were found to be more difficult and less interesting in the humanities than in the engineering field. In this study, Based on these statistical results proposes the need for non-major SW education to improve into an interesting curriculum for effective liberal arts education in the future in terms of enhancing learners' problem-solving skills.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.297-312
• /
• 2022

Although education using teaching tools is important to both students and teachers, the quality problem of distributed teaching tools is constantly being raised. Therefore, the purpose of this study is to analyze the teaching tools by classifying them into three quality factors, and to confirm the satisfaction and repurchase intentions of elementary school teachers. This study was conducted by dividing the first CIT survey and the second survey targeting incumbent elementary school teachers, and the PLS statistical program was used as an analysis tool. Through empirical analysis, it was analyzed that product quality, educational quality, and service quality had a positive (+) effect on teacher satisfaction, and that teacher satisfaction had a positive (+) effect on repurchase intention. Through this, it gives teachers insight into what they should focus on when purchasing or evaluating teaching tools and how to use them usefully for education, and for researchers, it provides an important clue to research for product quality improvement, and for companies that produce and distribute teaching tools, it gives to effective guidelines for the development of new products and contents. In the future, in addition to the relationship between the teaching tools and teachers, additional research on the organic relationship between the teaching tools and various objects is needed, and this is suggested as a future study.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.2
• /
• pp.230-237
• /
• 2023

Due to the COVID-19 pandemic and climate change, shortages of essential commodities and resources continue to occur globally. To address this problem, trade volume demand suddenly increased, driving up the freight rate of container ships sharply. The size of container vessels progressively increased from 1,500 TEU (twenty-foot equivalent unit) in the 1960s to 24,400 TEU in 2021. As the improvement of container loading capacity is closely related to the enlargement of the lashing bridge structure, it is necessary to design a structure effective for good container securing and safe under the various external loads that occur during voyage. Major classification societies have recently issued structural-analysis-based guidelines to evaluate the structural safety of lashing bridges, but their acceptance criteria and evaluation methods are different, causing confusion among engineers during design. In this study, the strength change characteristics are summarized by variations in the main variables (modeling range, opening consideration, mesh size) likely to affect the results. Based on this result, the authors propose a reasonable structural-analysis-based evaluation that is expected to serve as a reference in the next revision of classification standards.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.227-241
• /
• 2022

Full waveform inversion (FWI) in the field of seismic data processing is an inversion technique that is used to estimate the velocity model of the subsurface for oil and gas exploration. Recently, deep learning (DL) technology has been increasingly used for seismic data processing, and its combination with FWI has attracted remarkable research efforts. For example, DL-based data processing techniques have been utilized for preprocessing input data for FWI, enabling the direct implementation of FWI through DL technology. DL-based FWI can be divided into the following methods: pure data-based, physics-based neural network, encoder-decoder, reparameterized FWI, and physics-informed neural network. In this review, we describe the theory and characteristics of the methods by systematizing them in the order of advancements. In the early days of DL-based FWI, the DL model predicted the velocity model by preparing a large training data set to adopt faithfully the basic principles of data science and apply a pure data-based prediction model. The current research trend is to supplement the shortcomings of the pure data-based approach using the loss function consisting of seismic data or physical information from the wave equation itself in deep neural networks. Based on these developments, DL-based FWI has evolved to not require a large amount of learning data, alleviating the cycle-skipping problem, which is an intrinsic limitation of FWI, and reducing computation times dramatically. The value of DL-based FWI is expected to increase continually in the processing of seismic data.