• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.347-354
• /
• 2023

In this study, virtual reality software was developed to support the generation of an analysis model of a Hanok and to increase the use of the completed analysis model. The structural analysis model of the Hanok was generated using midas Gen, a general-purpose structural analysis software. After converting it into a text-based input file, the developed software stores the data necessary for the examination of the analysis model. Then, in the developed virtual reality software, the three-dimensional analysis model of the Hanok can be visualized in various ways and the related data can be shown by selecting a specific member. Through this process, errors in the analysis model can be identified and corrected to build a complete analysis model. The developed software was applied to three Hanok cases to verify its applicability and effectiveness. The software is expected to be used in other fields besides the structural field.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Korean Journal of Cognitive Science
• /
• v.17 no.2
• /
• pp.75-102
• /
• 2006

Three experiments were conducted using a verification task to examine good and poor readers' generation of causal inferences(with because sentences) and contrastive inferences(with although sentences). The unfamiliar, critical verification statement was either explicitly mentioned or was implied. In Experiment 1, both good and poor readers responded accurately to the critical statement, suggesting that both groups had the linguistic knowledge necessary to the required inferences. Differences were found, however, in the groups' verification latencies. Poor, but not good, readers responded faster to explicit than to implicit verification statements for both because and although sentences. In Experiment 2, poor readers were induced to generate causal inferences for the because experimental sentences by including fillers that were apparently counterfactual unless a causal inference was made. In Experiment 3, poor readers were induced to generate contrastive inferences for the although sentences by including fillers that could only be resolved by making a contrastive inference. Verification latencies for the critical statements showed that poor readers made causal inferences in Experiment 2 and contrastive inferences in Experiment 3 doting comprehension. These results were discussed in terms of context effect: Specific encoding operations performed on anomaly backgrounded in another passage would form part of the context that guides the ongoing activity in processing potentially relevant subsequent text.

• 대한공업교육학회지
• /
• v.38 no.1
• /
• pp.49-67
• /
• 2013

The purpose of this study is to analyze the external systems and the units 'problem solving and invention' of the middle school technology and home economics 1 textbooks of the revised 2011 national curriculum in an effort to provide some information on the content system of invention education in technology class, as invention education was provided as part of a regular subject for the first time. The findings of the study were as follows: First, 'Technology and Inventions' chapter of Technology and Home Economics 1 Textbooks occupied 10-18% share, with the subchapter of 'Problem Solving and Invention' unit taking up 6.7-29% of the textbooks. Second, for most textbooks, 'Technological Problem Solving', 'Idea Generation' 'Multi-dimensional Projection Method', 'Expansive Thought-Processing Methodology', 'Converging Thought Methodology' and 'Invention in Everyday Lives' were included as main contents based on the accomplishment criteria presented in education process interpretation documents. Third, the detailed structures were generally made up as follows: Introduction (Broad Chapter Title, Subchapter Table of Contents, Introduction, Subchapter Title, Study Objectives, Open Thinking); Development (Unit Title, Thinking Ahead, Core Terms, Main Text, Study Helper, Activities, Research Exercises, Supplemental Readings, In-depth Study Topics, Technology in Everyday Lives, Reading Topics, Discussion Topics, and Career Helpers); and Summary (Subchapter Summary, Study Summary, Terms Summary, Writing Follow-up, Self Review, Broad Chapter Evaluation). Fourth, based on the analysis of figures included, photographs had the largest share, followed by figures, tables, and graphs. The photos were used to illustrate various inventions, invention methodologies, and exercise activities, while figures were included to depict the contents included in the main text, and the tables to assist to preparation of process diagrams or materials lists. Fifth, based on the analysis of content weights, greater weights were placed on 'Inventions and Thoughts', and 'Invention Experiment Activities,' while 'Understanding Inventions' and 'Invention and Patents' chapters did not have a lot of texts involved. Sixth, based on the analysis of content presentation methods, most textbooks combined figures, tables, illustrations and texts to discuss the topics. Based on the above study results, we suggest the following: First, a consistent education curriculum should be developed over the topic of invention; and second, more precise and systematic analysis of textbooks would need to be performed.

• Journal of Science Education
• /
• v.45 no.3
• /
• pp.292-303
• /
• 2021

This study identifies the terms frequently used together with energy in online science news articles and topics of the news reports to find out how the term energy is used in everyday life and to draw implications for science curriculum and instruction about energy. A total of 2,171 online news articles in science category published by 11 major newspaper companies in Korea for one year from March 1, 2018 were selected by using energy as a search term. As a result of natural language processing, a total of 51,224 sentences consisting of 507,901 words were compiled for analysis. Using the R program, term frequency analysis, semantic network analysis, and structural topic modeling were performed. The results show that the terms with exceptionally high frequencies were technology, research, and development, which reflected the characteristics of news articles that report new findings. On the other hand, terms used more than once per two articles were industry-related terms (industry, product, system, production, market) and terms that were sufficiently expected as energy-related terms such as 'electricity' and 'environment.' Meanwhile, 'sun', 'heat', 'temperature', and 'power generation', which are frequently used in energy-related science classes, also appeared as terms belonging to the highest frequency. From a network analysis, two clusters were found including terms related to industry and technology and terms related to basic science and research. From the analysis of terms paired with energy, it was also found that terms related to the use of energy such as 'energy efficiency,' 'energy saving,' and 'energy consumption' were the most frequently used. Out of 16 topics found, four contexts of energy were drawn including 'high-tech industry,' 'industry,' 'basic science,' and 'environment and health.' The results suggest that the introduction of the concept of energy degradation as a starting point for energy classes can be effective. It also shows the need to introduce high-tech industries or the context of environment and health into energy learning.

• School Mathematics
• /
• v.6 no.1
• /
• pp.1-19
• /
• 2004

Recently, we have been listening such a words, that is, the crisis of public education through the mass communication such as newspaper or broadcasting. This means that we didn't have an enough opportunity to think it over about good education programme which the education of school can be normalized or the design of curriculum in the current problems such as overcrowded class, teacher and poor finance which is not still solved. As we know, it is true that the older generation is familiar with the rote learning which was under the control of behaviorism for about three hundred years. Fortunately, The 7th curriculum which had made public by the ministry of education on 30 Dec. 1997 have changed so many things such as real life based or activity based and so on. But it still leaves something to be desired in reflecting the demand of teachers of field. Taking into account this real situation, I have wondered how they run curriculum and how math learning programme of lower grade is different with ours in New Zealand, etc and so I had tried to find some suggestive points through the comparison of curriculum and text between Korea and New Zealand. But, if we want to compare all the strands of curriculum between two countries, it is too global and so in this paper, we deal with only number and operations(number), measurement, figure(geometry), equation and patter(algebra), probability and statistics(statistics) which are dealt with more comparatively in the lower grade of primary school. Because the main purpose of this paper is a comparison and analysis of the curriculum and math learning program of the lower grade in the primary school between two countries and so we compare global characteristics of education system and curriculum between two countries, at first and then we dealt with the very core part of the content of New Zealand curriculum within the ranges of level 1, 2 and 3 and global characteristics of learning program simultaneously.

• The Journal of Art Theory & Practice
• /
• no.6
• /
• pp.101-121
• /
• 2008

An artist, Oh Yun(1946~86)'s theory of people's art during his final period is summed up in his essay 'Expansion of Artistic Imagination and World' (1985). Emphasizing the mystic and traditional characteristics of Oh Yun's artistic oeuvre during his final period, some critics focus on Oh Yun's experience of medical treatment and shamanistic custom at Jin Do island, and his belief in Jeung San Do, the dao of Jeung-san, the Ruler of the Universe. However, they forget the practical intention and implication of his theory of art during his final period, which aimed to overcome the contradiction of revelation itself. Oh Yun's essay criticized the loss of artistic imagination and the ignorance of traditional culture that resulted from the elevation of science to a religion, and insisted that the stereotyped idealism, scientism and elitism in art should be overcome in order to recover the full reality in realism and to continue traditional cultures. The essay is comprised of 18 paragraphs. Oh Yun criticized monochromatic art, conceptual art, hyper-realistic art, objet d'art, and neo-dadaist art, saying that they were simply mechanical forms of modern art derived from scientism and a fetishistic lens culture. In addition, he criticized naturalism in art, which had continued as a tendency in the development of western art, for the same reason. He pointed out that even the world of realism had been diminished by elite stereotypes and diagrams. He declared the need to overcome the imitation of shells or stereotyped propaganda, and recover full realism, which seems to have started with a reflective examination of current problems in 'Reality and Utterance', in which he participated. Especially, he thought that universality and the extension of full realism could be achieved by building on the views of traditional cultures, which is meaningful. This logic is same as the theory of epic theatre that Bertolt Brecht(1898~1956) has developed under the ancient Greek masque and Pieter Bruegel the Elder(1525~69)'s story-like picture style. The universality of realism and the extension of acquisition to include incantation art, rather than move toward incantation art, is what Oh Yun intended to propose in 'Artistic Imagination'. This attitude is same as Bertoh Brecht's aesthetic viewpoint in the 1930s. But regrettably, Oh Yun's style wording, which seems covert and far-sighted, is often misunderstood as 'mysticism'. In the flow of people's art in the 1980s, Oh Yun was a traditionalist in a narrow sense, and an realist in a broad sense. However, his critical mind, which comprehends tradition and reality, was attempting to expand universality and extend full realism, and this attempt found many sympathizers and had an influence on the next generation of people's artists, such as "Levee" which is field-centered, to which we should pay attention. This means that while their works thought about 'tradition', we should be careful not to connect them with 'aesthetic conservatism' or 'classical art'. This is the why the meaning of Oh Yun's theory of art during his final period should be closely examined again.

• Journal of The Korean Association For Science Education
• /
• v.37 no.6
• /
• pp.1005-1014
• /
• 2017

Focusing on the role of the science museum as an institution to improve the scientific literacy of the public, this study investigated public perception and behavior about science museum to know how much science museums affect the public by using social media big data analysis. For this purpose, we extracted texts containing 'science museum' in Naver blogs and Twitter, analyzed them by using network, frequency, co-ocurrence, and semantics analysis and compared them with the results in English speaking countries. As a result, blogs were mainly concerned with science museum among parents who have young children, while in Twitter posts from many students who visited as a group appeared. Therefore, the Korean public used science museum mainly as a space for children's experience, and in this case, programs and exhibitions of science museums are perceived positively. On the other hand, students who visited as a group showed some negative emotions. The result of comparison with the cases of foreign countries in terms of the function of the third generation science museum such as communications with the science museum and the public and the participation of the public in science, the Korean public hardly mentioned the scientific contents, words related to communications such as 'argue', and curators or staff after visiting the science museum. In contrast to many verbs related to meaningful activities such as 'learn', 'participate', 'listen', 'read', 'ask', 'think' appeared in English, only a small number of verbs include 'ask' and 'thin' appeared in Korean. Therefore, science museum need to improve impression, communicating with public, and involving activity with impact and variety after visit.