• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.344-358
• /
• 2022

Text summarization is the task of producing a shorter version of a long document while accurately preserving the main contents of the original text. Abstractive summarization generates novel words and phrases using a language generation method through text transformation and prior-embedded word information. However, newly coined words or out-of-vocabulary words decrease the performance of automatic summarization because they are not pre-trained in the machine learning process. In this study, we demonstrated an improvement in summarization quality through the contextualized embedding of BERT with out-of-vocabulary masking. In addition, explicitly providing precise pointing and an optional copy instruction along with BERT embedding, we achieved an increased accuracy than the baseline model. The recall-based word-generation metric ROUGE-1 score was 55.11 and the word-order-based ROUGE-L score was 39.65.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.373-377
• /
• 2009

This research was conducted in order to know how influential the acknowledgment of factors such as the quality of educational contents and the conducting of off-line lectures is in terms of effective learning for leaners. Based on the satisfaction-importance model of the multi-attribute attitude model, this study would like to clarify the degree to which the quality of on-line contents of on-line education and the simultaneous conducting of off-line lectures influences one's learning attitude. On-line contents satisfaction will evaluated through the three categories: audio lectures, video lecture and WBI lectures, which make up the quality of on-line contents. We would also like to do a survey on the transformation of learning attitudes when on-line and off-line lectures were conducted simultaneously.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.31-37
• /
• 2022

This paper proposes a study on applying signal processing and deep learning for sound recognition that detects sounds commonly heard in daily life (Screaming, Clapping, Crowd_clapping, Car_passing_by and Back_ground, etc.). In the proposed sound recognition, several techniques related to the spectrum of sound waves, augmentation of sound data, ensemble learning for various predictions, convolutional neural networks (CNN) deep learning, and two-dimensional (2-D) data are used for improving the recognition accuracy. The proposed sound recognition technology shows that it can accurately recognize various sounds through experiments.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.47-55
• /
• 2023

The automotive industry is undergoing a paradigm shift due to the convergence of IT and rapid digital transformation. Various components, including embedded structures and systems with complex architectures that incorporate IC semiconductors, are being integrated and modularized. As a result, there has been a significant increase in vehicle defects, raising expectations for the quality of automotive parts. As more and more data is being accumulated, there is an active effort to go beyond traditional reliability analysis methods and apply machine learning models based on the accumulated big data. However, there are still not many cases where machine learning is used in product development to identify factors of defects in performance and durability of products and incorporate feedback into the design to improve product quality. In this paper, we applied a prediction algorithm to the defects of automotive door devices equipped with automatic responsive sensors, which are commonly installed in recent electric and hydrogen vehicles. To do so, we selected test items, built a measurement emulation system for data acquisition, and conducted comparative evaluations by applying different machine learning algorithms to the measured data. The results in terms of R² score were as follows: Ordinary multiple regression 0.96, Ridge regression 0.95, Lasso regression 0.89, Elastic regression 0.91.

• Research in Mathematical Education
• /
• v.9 no.3 s.23
• /
• pp.285-294
• /
• 2005

The author has been teaching with an instructional module consisting of many mathematical concepts, based on designs formed by personal names or words to arouse students' interesting in learning mathematics. This module has been growing since it was first used as a supplementary lesson for calculus students. Now it consists of concepts that connect with mathematical topics such as number sense, algebraic thinking, geometry, and statistical reasoning, as well as other subjects such as art and quilt design. With its content we can provide our students the basic mathematical knowledge needed for further study in their own fields. In this article, we will demonstrate the latest development of this instructional module, which makes connections between mathematical knowledge and the design of personal quilt patterns. We will exhibit a 'Quilt of Nations' which consists of the designed quilt blocks of different countries, such as USA, Japan, Taiwan, Korea and others, as well as a quilt design using the abbreviation of this seminar. Then we will talk about how the connections are built, and how to design these mathematically rich, uniquely created, beautifully designed, and personalized quilt block patterns.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.497-500
• /
• 2022

High-quality images and videos are being generated as technologies for deep learning-based image style translation and conversion of static images into dynamic images have developed. However, it takes a lot of time and resources to manually transform images, as well as professional knowledge due to the difficulty of natural image transformation. Therefore, in this paper, we study natural style mixing through a style conversion network using GAN and natural dynamic image generation using the First Order Motion Model network (FOMM).

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.183-192
• /
• 2023

Digital transformation is taking place rapidly around the world. As the development of digital technology becomes very fast, more information is expected to be digitized. Therefore, the possibility of cyber threats is increasing in transmitting and storing sensitive information such as personal and financial information online. In this paper, we compared and analyzed information security textbooks for elementary and secondary school students in China, where the recent development of artificial intelligence and digital transformation are rapidly occurring. After we collected related textbooks, textbooks suitable for analysis were selected. Then, we analyzed the external and internal systems of the textbooks separately. As a result of the external system analysis, all the textbook covers were properly produced, but the quality difference was significant among textbooks. In the case of textbooks for elementary school students, the excellence of layout and content placement was noticed. On the other hand, due to the internal system analysis, various contents were not included evenly when looking at the learning contents based on the "information society responsibility" learning goals presented in China. Through this paper, we hope to provide implications for information security-related education and textbook development research.

• Journal of English Language & Literature
• /
• v.55 no.3
• /
• pp.383-398
• /
• 2009

Based on the Greek myth of Pygmalion and the fairy tale of Cinderella, Shaw's Pygmalion demonstrates a masterful coalescence of these two narrative motifs into a coherent plot scheme. Even more significant is his keen insight into the conflicts created at the tripartite intersection of human activity concerning language/class/culture, which, as the leitmotif, revolves around lessons in language learning. This play basically deals with human transformation and by its very nature, Higgins's experimentation with transforming Eliza cannot stop at language alone. Her cultural transformation ripples over into the realms of gesture and even a unique way of living (modus vivendi) intimately associated with taste and manners, which Bourdieu terms as habitus. By acquiring a new fashion and language, Eliza is reborn as a new lady aspiring to be filled with a newly acquired habitus. While separating her from her old Cockney style, Higgins inculcates Queen's English in Eliza, in which process her changed speech styles gradually transforms and restructures her deportment and manners, finally generating new practices, perceptions and attitudes. The gist of Pygmalion is however less Eliza's ascent into the middle class than her battle for symbolic capital waged at the level of language. By problematizing his contemporary practice of habitus conventionalized and warped by class distinctions based on economic, social and cultural capitals, Shaw creates a new humanist model of man founded on spiritual and rational virtues. In conclusion, Eliza is not a frigid Galatea but a dynamic character that goes through a brilliant transformation of three stages: 1) linguistic; 2) cultural, and 3) humanist. Finally she is built into a "consort battleship" on an equal standing with her sculptor. The process of her character-building cannot be illuminated without resorting to the dynamic notion of habitus, which highlights the process of inculcation, structuring, generation and transposing. Given the overwhelming weight of the heroine's role and the dynamic process of her transformation as the major plot scheme, this play should be christened Galatea in lieu of Pygmalion.

• Journal of Distribution Science
• /
• v.21 no.2
• /
• pp.45-52
• /
• 2023

Purpose: The Malaysia Education Blueprint is primarily concerned with the transformation of students' minds through the curriculum offered at the school level (2013-2025). Diversity in the application of teaching and learning methods is one means of achieving the transformation of students' minds through the Secondary School Standard Curriculum. Consequently, the production of ExSheetLink's Module for Accounting Education is the primary outcome of this study, which had three objectives: the need for ExSheetLink's Module in the process of producing financial statements for Accounting Students in secondary school to the Accounting Teacher; and the design of ExSheetLink's Module that meets the entire process in the production of financial statements for Accounting Students in secondary school based on the Documents Curriculum and the Accounting Students' needs. Research design, data and methodology: This study outlines the research framework for module development in accordance with the Design and Development Research Method, which combines multiple research techniques (Mixed Method). Results: The development of ExSheetLink's Module is completed and can be used for the level of effectiveness purposes. Conclusion: The transformation of Accounting Students' minds is a success thanks to the ExSheetLink Module. Researchers also suggested that all Malaysian Secondary School accounting students test the ExSheetLink Module.