• Journal of Information Technology Services
• /
• v.16 no.3
• /
• pp.167-183
• /
• 2017

The rapid growth of information technology and mobile service platforms, i.e., internet, google, and facebook, etc. has led the abundance of data. Due to this environment, the world is now facing a revolution in the process that data is searched, collected, stored, and shared. Abundance of data gives us several opportunities to knowledge discovery and data mining techniques. In recent years, data mining methods as a solution to discovery and extraction of available knowledge in database has been more popular in e-commerce service fields such as, in particular, movie recommendation. However, most of the classification approaches for predicting the movie popularity have used only several types of information of the movie such as actor, director, rating score, language and countries etc. In this study, we propose a classification-based support vector machine (SVM) model for predicting the movie popularity based on movie's genre data and social network data. Social network analysis (SNA) is used for improving the classification accuracy. This study builds the movies' network (one mode network) based on initial data which is a two mode network as user-to-movie network. For the proposed method we computed degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality as centrality measures in movie's network. Those four centrality values and movies' genre data were used to classify the movie popularity in this study. The logistic regression, neural network, $na{\ddot{i}}ve$ Bayes classifier, and decision tree as benchmarking models for movie popularity classification were also used for comparison with the performance of our proposed model. To assess the classifier's performance accuracy this study used MovieLens data as an open database. Our empirical results indicate that our proposed model with movie's genre and centrality data has by approximately 0% higher accuracy than other classification models with only movie's genre data. The implications of our results show that our proposed model can be used for improving movie popularity classification accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.93-99
• /
• 2006

Ontology is an indispensable component in intelligent and semantic processing of knowledge and information, such as in semantic web. Ontology is considered to be constructed generally on the basis of taxonomy of human concepts about the world. However. as human concepts are unstructured and obscure, ontology construction based on the taxonomy of human concepts cannot be realized systematically furthermore automatically. So, we try to do this from the relation among linguistic symbols regarded representing human concepts, in short, words. We show the similarity between taxonomy of human concepts and relation among words. And we propose a methodology to construct and generate automatically ontologies from these relations mon words and a series of algorithm to convert these relations into ontologies. This paper presents the process and concrete application of this methodology.

• Korean Journal of Human Ecology
• /
• v.17 no.5
• /
• pp.891-902
• /
• 2008

Some Korean men choose to marry a foreigner expecting that marriage will solve all their problems. Therefore, this case study is to provide basic information on how to prevent conflicts in the marriage and how to get used to the marriage life. first, it is apparent that these match-makings between Korean men and married Female Immigrants are commercialized and are based on the two parties' convenience. Second, it is more possible that the issues with the role of husband/wife and the allocation of household labor stem from the cultural differences from international racial differences rather than Korean men are authoritative or patriarchal. It seems that the foreign brides from the third world countries choose to many Korean men with only a single purpose to financially help their parents. While neither willing to share household labor nor providing what is expected to be a wife, they demand financial assists for their parents or choose to get a job at a factory to make money. Third, the husbands expect their wives to learn Korean since there is not much opportunity to learn the wives' language and the culture. Also, the textbooks are rare to find for the languages. Moreover, the husbands do not have the enthusiasm or the ability to team due to age Fourth, the Korean men are rather psychological, financial, social victims than domestic abusers.

• The Journal of Korean Medicine
• /
• v.28 no.1 s.69
• /
• pp.1-10
• /
• 2007

Background : There has been renewed interest in complementary alternative medicine around the world far a decade. On the other hand, the issue of safety of herbal medicine in Korea has been continuously questioned. Issues raised have included not only chemical residue or heavy metals caused by pollution, but also the toxicity of herbal medicine itself. Objectives : The purpose of this study was to review some herbal medicines subject to controversy of toxicity and figure out what kind of problems they evidence. Methods : In this review, PubMed was used to search medical journals. Keywords such as 'herb, or herbal medicine', 'safety, or adverse events, or adverse effect, or toxicity, or liver injury' were applied. Journals were selected by four inclusion criteria, as objectives should be human, researchers should be medical doctors, literature written in the English language, and types of journals should be meta-analysis or practice guideline or reviews. Finally, 9 cases from 60 journals were included in this review. Results : We reviewed 13 herbal medicines for controversy of toxicity such as ephedra(Mahuang), Arisolochia fangchi, Aristolochia manshuriensis, licorice, skullcap , germander, Syo-saiko-to(Xiao-chai-hu-tang), Chelidonium majus, mistletoe, Dictamnus dasycarpus and madder. Conclusions : It suggested that 'who it is prescribed for' is one of the most important factors to identify the causes of toxicity in herbal medicine and dietary supplements, under specific conditions in Korea.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.470-476
• /
• 2015

Big data has been used in diverse areas. For example, in computer science and sociology, there is a difference in their issues to approach big data, but they have same usage to analyze big data and imply the analysis result. So the meaningful analysis and implication of big data are needed in most areas. Statistics and machine learning provide various methods for big data analysis. In this paper, we study a process for big data analysis, and propose an efficient methodology of entire process from collecting big data to implying the result of big data analysis. In addition, patent documents have the characteristics of big data, we propose an approach to apply big data analysis to patent data, and imply the result of patent big data to build R&D strategy. To illustrate how to use our proposed methodology for real problem, we perform a case study using applied and registered patent documents retrieved from the patent databases in the world.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.382-386
• /
• 2004

Recently, with the machine learning trend, most of the machine translation systems on over the world use two syntax tree sets of two relevant languages to learn syntactic tree transfer rules. However, for the English-Vietnamese language pair, this approach is impossible because until now we have not had a Vietnamese syntactic tree set which is correspondent to English one. Building of a very large correspondent Vietnamese syntactic tree set (thousands of trees) requires so much work and take the investment of specialists in linguistics. To take advantage from our available English-Vietnamese Corpus (EVC) which was tagged in word alignment, we choose the SITG (Stochastic Inversion Transduction Grammar) model to construct English- Vietnamese syntactic tree sets automatically. This model is used to parse two languages at the same time and then carry out the syntactic tree transfer. This English-Vietnamese bilingual syntactic tree set is the basic training data to carry out transferring automatically from English syntactic trees to Vietnamese ones by machine learning models. We tested the syntax analysis by comparing over 10,000 sentences in the amount of 500,000 sentences of our English-Vietnamese bilingual corpus and first stage got encouraging result $(analyzed\;about\;80\%)[5].$ We have made use the TBL algorithm (Transformation Based Learning) to carry out automatic transformations from English syntactic trees to Vietnamese ones based on that parallel syntactic tree transfer set[6].

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.673-675
• /
• 2015

In recent years, communication between objects is made possible due to the development of IoT(Internet of Things) to the specified business strategy of major countries around the world. However, the standard for representing information of the device is difficult not been set the communication between the devices with different platforms. This paper shows the Conventional people instrument using the method and the simple sensor to the command directly to the machine control system and the information of the devices utilizing different Socialization expression language, XML Schema, information on the job, relationship information of the equipment and devices Machine Socialization proposes a scheme and use them to propose a device management system for managing devices.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.343-350
• /
• 2007

Virtual environment is an interactive multimedia space that allows users to experience realistic sensory feedbacks and interactions as they do in real world. There have been some work on the development of two-dimensional user interface for supporting interactions in a virtual environment. However, most of them were designed for specific virtual environments and hence could not be easily deployed to other virtual worlds. To address this problem, some frameworks were developed for building two-dimensional user interfaces for virtual environment, but they had limitations in usability or flexibility. In this paper, we present the HIVE framework, which is designed to help ease the development of two-dimensional user interface for the virtual environment while satisfying the requirements of both usability and flexibility. The HIVE framework utilizes XML and scripting capability, dynamic module loading, XML and script language for usability. It provides module reading, configuration, and event processing mechanism for flexibility. This paper first explains the HIVE framework and describes the applications developed for some virtual environments followed by discussing the future research directions.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.949-956
• /
• 2017

Visual interfaces of news sites look similar while their HTML have lots of different specifications and qualities. It's getting more and more significant to describe HTML semantically to make every computer able to understand contents to be shared as HTML5 specification refers. In this study, I have analysed HTML codes of 110 korean news sites in comparison to those of 8 global news sites. As results, 68% of news sites are still described in HTML4 specifications and only 10 out of 110 are in HTML5 specification and as high quality and strong semantics as global news sites. The result shows most korean news sites platforms had not been changed since they developed in mid-2000 and it's needed to be upgraded as language translation technologies are making it possible to share korean digital contents with the rest of world.

• Journal of the Korean Society of Costume
• /
• v.61 no.10
• /
• pp.42-54
• /
• 2011

The study was focused on surveying the cultural identity and the origin of T-shirts, and examining their functions. Six cities were selected to categorize the design motifs of cultural identity appearing in the design of contemporary T-shirts. These cities include a city in France, United Kingdom, Italy, United States and Japan where collections are currently presented at, and also a city in China that has shown a high economic growth as one of the most popular sightseeing cities. Cultural identity was presented in the T-shirts that were examined in this study through diversified design motifs. Motifs used in T-shirt designs to reflect cultural identity included national flags, notable places, letters, names of geographic places, and individuals. A national flag is a motif that signifies national identity and it was used in the front of T-shirts as it is or was just partially used. Also, many world-renowned structures or architectural buildings were applied to T-shirt design. Noted places such as the White House, the Statue of Liberty in the U.S., Tienanmen Square in China and the Eiffel Tower in France were used. The unique characters of language, such as Hangeul in Korea were used as design elements to reflect the structural characteristics of letters. Names of geographic places were used as design elements through the disclosure of the name of a symbolic city or a tourist site in each country. In terms of figures, not only the historical figures or celebrities from each country were used, but the image of bodies and faces that represent each culture were used as well. In addition, this study was used to develop T-shirt designs that reveal the cultural identity of Korea.