• Asia pacific journal of information systems
• /
• v.21 no.1
• /
• pp.103-122
• /
• 2011

Recently, numerous documents have been made available electronically. Internet search engines and digital libraries commonly return query results containing hundreds or even thousands of documents. In this situation, it is virtually impossible for users to examine complete documents to determine whether they might be useful for them. For this reason, some on-line documents are accompanied by a list of keywords specified by the authors in an effort to guide the users by facilitating the filtering process. In this way, a set of keywords is often considered a condensed version of the whole document and therefore plays an important role for document retrieval, Web page retrieval, document clustering, summarization, text mining, and so on. Since many academic journals ask the authors to provide a list of five or six keywords on the first page of an article, keywords are most familiar in the context of journal articles. However, many other types of documents could not benefit from the use of keywords, including Web pages, email messages, news reports, magazine articles, and business papers. Although the potential benefit is large, the implementation itself is the obstacle; manually assigning keywords to all documents is a daunting task, or even impractical in that it is extremely tedious and time-consuming requiring a certain level of domain knowledge. Therefore, it is highly desirable to automate the keyword generation process. There are mainly two approaches to achieving this aim: keyword assignment approach and keyword extraction approach. Both approaches use machine learning methods and require, for training purposes, a set of documents with keywords already attached. In the former approach, there is a given set of vocabulary, and the aim is to match them to the texts. In other words, the keywords assignment approach seeks to select the words from a controlled vocabulary that best describes a document. Although this approach is domain dependent and is not easy to transfer and expand, it can generate implicit keywords that do not appear in a document. On the other hand, in the latter approach, the aim is to extract keywords with respect to their relevance in the text without prior vocabulary. In this approach, automatic keyword generation is treated as a classification task, and keywords are commonly extracted based on supervised learning techniques. Thus, keyword extraction algorithms classify candidate keywords in a document into positive or negative examples. Several systems such as Extractor and Kea were developed using keyword extraction approach. Most indicative words in a document are selected as keywords for that document and as a result, keywords extraction is limited to terms that appear in the document. Therefore, keywords extraction cannot generate implicit keywords that are not included in a document. According to the experiment results of Turney, about 64% to 90% of keywords assigned by the authors can be found in the full text of an article. Inversely, it also means that 10% to 36% of the keywords assigned by the authors do not appear in the article, which cannot be generated through keyword extraction algorithms. Our preliminary experiment result also shows that 37% of keywords assigned by the authors are not included in the full text. This is the reason why we have decided to adopt the keyword assignment approach. In this paper, we propose a new approach for automatic keyword assignment namely IVSM(Inverse Vector Space Model). The model is based on a vector space model. which is a conventional information retrieval model that represents documents and queries by vectors in a multidimensional space. IVSM generates an appropriate keyword set for a specific document by measuring the distance between the document and the keyword sets. The keyword assignment process of IVSM is as follows: (1) calculating the vector length of each keyword set based on each keyword weight; (2) preprocessing and parsing a target document that does not have keywords; (3) calculating the vector length of the target document based on the term frequency; (4) measuring the cosine similarity between each keyword set and the target document; and (5) generating keywords that have high similarity scores. Two keyword generation systems were implemented applying IVSM: IVSM system for Web-based community service and stand-alone IVSM system. Firstly, the IVSM system is implemented in a community service for sharing knowledge and opinions on current trends such as fashion, movies, social problems, and health information. The stand-alone IVSM system is dedicated to generating keywords for academic papers, and, indeed, it has been tested through a number of academic papers including those published by the Korean Association of Shipping and Logistics, the Korea Research Academy of Distribution Information, the Korea Logistics Society, the Korea Logistics Research Association, and the Korea Port Economic Association. We measured the performance of IVSM by the number of matches between the IVSM-generated keywords and the author-assigned keywords. According to our experiment, the precisions of IVSM applied to Web-based community service and academic journals were 0.75 and 0.71, respectively. The performance of both systems is much better than that of baseline systems that generate keywords based on simple probability. Also, IVSM shows comparable performance to Extractor that is a representative system of keyword extraction approach developed by Turney. As electronic documents increase, we expect that IVSM proposed in this paper can be applied to many electronic documents in Web-based community and digital library.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.1
• /
• pp.99-104
• /
• 2014

Purpose: This study was to investigate the functional improvement in peripheral vision following eccentric viewing training. Methods: 14 subjects with normal vision took a part with their right eye, peripheral retinal which is $20^{\circ}$ lateral area from the fovea was examined for contrast sensitivity(CS). Eccentric viewing training was performed for 21days with an hour image viewing and examination was repeated. Results: The critical durations for 0.7 cpd were increased 2.67(467 ms) for pre-eccentric viewing training to 2.79(616 ms) for post-eccentric viewing training (p>0.05). The critical durations for 3.0 cpd were also increased 2.53(341 ms) for pre-eccentric viewing training to 3.04(1102 ms) for post-eccentric viewing training (p>0.05). Conclusions: It is recommended to use higher spatial frequency with higher CS for eccentric viewing training and to train more frequently for a short time. Moreover, the study on Korean standardizing of the visual rehabilitation for low vision based on the etiology is sorely required.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.11-19
• /
• 2021

The purpose of the study is to explore a plan for effective education using virtual reality in English education. In order to achieve the purpose of the study, the perception of English education using virtual reality was comprehensively investigated and analyzed for teachers(n=20) in the field of English education. The results of the study reveal the followings: 1) Teachers are positively aware of the necessity of English education using virtual reality, but most teachers complained of a psychological burden on education using virtual reality; 2) negative responses were somewhat higher than positive responses to the expectation that virtual reality-based English content would be practical in the educational field; 3) In order to increase the effectiveness of English education using virtual reality, it is necessary to share experiences for educational experience of virtual reality and need to provide various virtual reality contents; and 4) For virtual reality educational application, there is a high demand for teaching and learning method education and training using virtual reality and provision of guidelines for education using virtual reality.

• Journal of Practical Engineering Education
• /
• v.12 no.1
• /
• pp.213-230
• /
• 2020

Until now, various educational budgets, facilities, and programs have been put into school education, but the results have not been clearly evaluated. This study presents a model to analyze the effectiveness of educational support for students in high schools across the country. In this model, we first use EM cluster analysis to make clusters with similar inputs for school operation, and then calculate the relative efficiency in each cluster by using Network DEA analysis. The Network DEA analysis has a two-stage structure where the first stage uses six inputs in terms of school infrastructure to generate outputs such as the number of academic persistence. In the Network DEA analysis, the second stage uses 10 inputs in terms of school programs to generate outputs such as the number of enrollees to higher learning and the number of employees and per capita usage of library as the connection variable. Based on the efficiency analysis results, Tier analysis is performed by applying the Euclidean distance to select targets for benchmarking. In this study, we applied the model to analyze the efficiency of educational support by collecting data regarding student education support in general and vocational high school nationwide. The stepwise benchmarking method proposed that the target be selected for efficiency improvement step by step, taking into account inefficient school elements to complement the problem of the choice of benchmarking targets. Based on this study, it is expected that schools with low efficiency of educational support for students will be used as basic data for stepwise benchmarking for efficient operation of educational support for students.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Cartoon and Animation Studies
• /
• s.19
• /
• pp.145-159
• /
• 2010

Similar to the other cultural contents, the character industry is based on the media which acts as the technological background. In fact, the character industry is the process of that a created character accesses to the consumers via media, builds its value and becomes licensed as a brand in the market. Therefore, it is crucial to select the most effective media for the consistence of a character in the market, as well as for construction of a higher brand quality of the character. Today, "Webtoon" might be considered as one of the marketing means which utilizes the Internet media for raising the character as a brand. Webtoon has apparent strength because it can be produced in shorter period and with less expense than through other media. Furthermore, Webtoon can be simply featured by the easiness of two-way communication and transference to another media through it. For these reasons, and according to the result of analyzing some Korean Webtoons, it seems obvious that the most effective media in character marketing is the Internet. In addition to the Internet, the strategic development in the media-mix is also important for establishing a brand of a character. However, the effective media-mix is available only when the character's external identity meets with the trait of its media. For the purpose of learning how the media-mix works when a character reaches for the consumers, a character "Hamataeng" was born and used in the experiment. This study will explain the marketing process through the use of own-created Webtoon and other contents, and suggest the ways to build a brand of a character. In addition, it is also indicated that a media-mixing strategy for transformation and expansion of the character to other media.

• Korean Institute of Interior Design Journal
• /
• v.20 no.5
• /
• pp.236-244
• /
• 2011

As the digital information infrastructure is established for the public library system in the contemporary age, expectations and demands surrounding the public library system are growing rapidly as the place of exchange and enjoyment of information and culture, and as the place of life-long learning. In addition, a new kind of information & culture services are needed to meet the demands of contemporary men and women, who are exploring information as the information environment undergoes rapid changes - from increase in the volume of digital publications, to increase in the usefulness of online information resources, to strides made in the media industry. The public library will continue to play its role and function by providing to all users all available information, whether it's available online or offline, whether it's in a physical format or in a digital format. As such, design and management of a space appropriate as a new information environment are needed. It is deemed that an information infrastructure for Daegu that can improve the quality of life in the region and can increase user accessibility to information in this information age is needed, as well as reorganization of the pertinent environment. Therefore more public libraries have to be built in Daegu as a necessity, and it is urgently needed that the information services be expanded through an organic linkage between local libraries such as between the central library and the branch libraries. This paper aims to provide basic data for building of public libraries in Daegu. To establish an information infrastructure for Daegu, a direction is given for the establishment of a local network of public libraries and ways for improvement are explored. This paper is significant in that, first, it helps in the planning of a local network of public libraries, which plays a crucial role in improving accessibility to information as well as the level of their use; and second, it helps in setting up guidelines for spatial configuration of the user space. As for the method, quantitative review of the information environment is to be done by analyzing the present situation of the public library network in Daegu from the perspectives of region, facility, and space, in order to present a method of user-centered spatial configuration that meets the changes in social roles and forms of information in the contemporary society.

• The KIPS Transactions:PartD
• /
• v.17D no.2
• /
• pp.129-146
• /
• 2010

Nowadays, XML has been favored by many companies internally and externally as a means of sharing and distributing data. there are many researches and systems for modeling and storing XML documents by an object-oriented method as for the method of saving and managing web-based multimedia document more easily. The representative tool for the object-oriented modeling of XML documents is UML (Unified Modeling Language). UML at the beginning was used as the integrated methodology for software development, but now it is used more frequently as the modeling language of various objects. Currently, UML supports various diagrams for object-oriented analysis and design like class diagram and is widely used as a tool of creating various database schema and object-oriented codes from them. This paper proposes an Efficinet Query Modelling of XML-GL using the UML class diagram and OCL for searching XML document which its application scope is widely extended due to the increased use of WWW and its flexible and open nature. In order to accomplish this, we propose the modeling rules and algorithm that map XML-GL. which has the modeling function for XML document and DTD and the graphical query function about that. In order to describe precisely about the constraint of model component, it is defined by OCL (Object Constraint Language). By using proposed technique creates a query for the XML document of holding various properties of object-oriented model by modeling the XML-GL query from XML document, XML DTD, and XML query while using the class diagram of UML. By converting, saving and managing XML document visually into the object-oriented graphic data model, user can prepare the base that can express the search and query on XML document intuitively and visually. As compared to existing XML-based query languages, it has various object-oriented characteristics and uses the UML notation that is widely used as object modeling tool. Hence, user can construct graphical and intuitive queries on XML-based web document without learning a new query language. By using the same modeling tool, UML class diagram on XML document content, query syntax and semantics, it allows consistently performing all the processes such as searching and saving XML document from/to object-oriented database.

• Journal of Elementary Mathematics Education in Korea
• /
• v.22 no.3
• /
• pp.267-282
• /
• 2018

The purpose of this study is to develop and apply a Convergence program for teaching of congruence and symmetry and to investigate the effects of the mathematical creativity and convergence talent. For these purposes, research questions were set up as follows: 1. How is a Convergence program for teaching of congruence and symmetry developed? 2. How does a Convergence program affect the mathematics creativity and convergence talent of fifth grade student in elementary school? The subjects in this study were 16 students in fifth-grade class in elementary school located in Songpa-gu, Seoul. A Convergence program was developed using the integrated unit design process chose the concept of congruence and symmetryas its topic. The developed program consisted of a total 12 class activities plan, lesson plans for 5 activities. Mathematics creativity test, a test on affective domain related with convergence talent measurement were carried out before and after the application of the developed program so as to analyze the its effects. In addition, students' satisfaction for the developed program was investigated by a questionnaire. The results of this study were as follows: First, A convergence program should be developed using the integrated unit design process to avoid focusing on the content of any one subject area. The program for teaching of congruence and symmetry should be considered students' learning style and their preferences for media. Second, the convergence program improved the students' mathematical creativity and convergence talent. Among the sub-factors of mathematical creativity, originality was especially improved by this program. Students thought that the program is good for their creativity. Plus, this program use two subject class, Math and Art, so student do not think about one subject but focus on topic 'congruence and symmetry'. It help students to develop their convergence talent.