• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.201-204
• /
• 2010

하루에도 수많은 도서가 출판되는 현실에서 사용자가 원하는 목적에 맞는 도서를 찾아 읽기는 어려운 일이다. 본 논문에서는 방대한 분량의 도서 데이타를 바탕으로, MapReduce 모델을 활용하여 도서들 사이의 연관 관계를 추출하였다. 추출한 연관 관계 DB를 이용하여 사용자에게 서로 관련 있는 도서를 추천해줄 수 있는 시스템을 개발하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.1067-1069
• /
• 2013

전자상거래 시장의 급격한 성장에 따라 고객이 원하는 정보를 얻기 위해 소요되는 시간과 노력을 절약하기 위한 방안으로 추천 시스템의 필요성이 강조되고 있다. 추천 시스템에 일반적으로 가장 많이 쓰이는 것이 협업필터링 기법이다. 협업 필터링은 추천시스템 분야에서 가장 성공적인 기법으로 전자상거래 포털에서 가장 널리 이용되고 있다. 그러나 희박성, 확장성, 투명성 등의 문제점을 가진다. 본 논문에서는 프로파일링 기법을 사용해 협업필터링의 희박성 문제 해소 방안으로 개인성향을 이용하여, 보다 정확한 추천을 하여 온라인 서점에 적용할 수 있는 추천 시스템이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.544-545
• /
• 2024

최근 성인 독서량은 지속적으로 감소하는데 비해 영상 콘텐츠 소비가 증가하고 있다. 이에 따라 새로운 사용자에 대한 선호도 및 행동 패턴에 대한 정보가 없고 새로운 도서에 대한 사용자 평가나 구매 정보가 부족해 콜드 스타트 문제와 데이터 희소성 문제가 발생하고 있다. 본 논문에서는 영상물 콘텐츠 기반 도서 하이브리드 추천 시스템을 제안하였다. 제안하는 추천 시스템은 영상물의 콘텐츠를 활용하여 콜드 스타트 문제와 데이터 희소성 문제를 해결할 수 있을 뿐만 아니라, 전통적인 도서 추천 시스템에 비해 성능이 향상되었고 장르, 줄거리, 평점 정보 기반 사용자 취향 정보까지 모두 반영된 질 높은 추천 결과까지 확인할 수 있었다.

• Knowledge Management Research
• /
• v.21 no.1
• /
• pp.117-136
• /
• 2020

In the studies for the recommender systems which solve the information overload problem of users, the use of transactional data has been continuously tried. Especially, because the firms can easily obtain transactional data along with the development of IoT technologies, transaction-based recommender systems are recently used in various areas. However, the use of transactional data has limitations that it is hard to reflect domain knowledge and they do not directly show user preferences for individual items. Therefore, in this study, we propose a method applying the word embedding in the transaction-based recommender system to reflect preference differences among users and domain knowledge. Our approach is based on SAR, which shows high performance in the recommender systems, and we improved its components by using FastText, one of the word embedding techniques. Experimental results show that the reflection of domain knowledge and preference difference has a significant effect on the performance of recommender systems. Therefore, we expect our study to contribute to the improvement of the transaction-based recommender systems and to suggest the expansion of data used in the recommender system.

• Journal of the Korean Society for information Management
• /
• v.38 no.3
• /
• pp.311-334
• /
• 2021

The purpose of this study is to present the theoretical basis and quantified objective standards for the establishment of collection management policy. The study results are summarized as follows. Most of the study books were in the form of periodicals as a steady seller. Most of the steady sellers were textbooks which published periodically. As a modern novel, a steady seller was able to confirm the phenomenon of dependence on a specific author. Bestsellers were investigated to be influenced by publishers and authors. Books of publishers that publish comics and children's textbooks had a significant correlation with the selection of bestsellers. The average number of recommended books borrowed per recommended book was 14,871. The average number of loans per book selected as a bestseller was 53,531. Based on the loan data, about 80-82% of all top-tier loans were covered by 90%, and about 27-29% of all top-ranked loans were covered by 50%. This shows that the Pareto Principle can be firmly applied to public library lending patterns. Loans in the field of literature accounted for 50.6% of the total loans. Among literature, Korean literature accounted for 51.3% of the total. The natural sciences were generating more loans with a relatively small pool of literature compared to other subject fields.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.19-38
• /
• 2017

Collaborative filtering (CF) algorithm has been popularly used for implementing recommender systems. Until now, there have been many prior studies to improve the accuracy of CF. Among them, some recent studies adopt 'hybrid recommendation approach', which enhances the performance of conventional CF by using additional information. In this research, we propose a new hybrid recommender system which fuses CF and the results from the social network analysis on trust and distrust relationship networks among users to enhance prediction accuracy. The proposed algorithm of our study is based on memory-based CF. But, when calculating the similarity between users in CF, our proposed algorithm considers not only the correlation of the users' numeric rating patterns, but also the users' in-degree centrality values derived from trust and distrust relationship networks. In specific, it is designed to amplify the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the trust relationship network. Also, it attenuates the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the distrust relationship network. Our proposed algorithm considers four (4) types of user relationships - direct trust, indirect trust, direct distrust, and indirect distrust - in total. And, it uses four adjusting coefficients, which adjusts the level of amplification / attenuation for in-degree centrality values derived from direct / indirect trust and distrust relationship networks. To determine optimal adjusting coefficients, genetic algorithms (GA) has been adopted. Under this background, we named our proposed algorithm as SNACF-GA (Social Network Analysis - based CF using GA). To validate the performance of the SNACF-GA, we used a real-world data set which is called 'Extended Epinions dataset' provided by 'trustlet.org'. It is the data set contains user responses (rating scores and reviews) after purchasing specific items (e.g. car, movie, music, book) as well as trust / distrust relationship information indicating whom to trust or distrust between users. The experimental system was basically developed using Microsoft Visual Basic for Applications (VBA), but we also used UCINET 6 for calculating the in-degree centrality of trust / distrust relationship networks. In addition, we used Palisade Software's Evolver, which is a commercial software implements genetic algorithm. To examine the effectiveness of our proposed system more precisely, we adopted two comparison models. The first comparison model is conventional CF. It only uses users' explicit numeric ratings when calculating the similarities between users. That is, it does not consider trust / distrust relationship between users at all. The second comparison model is SNACF (Social Network Analysis - based CF). SNACF differs from the proposed algorithm SNACF-GA in that it considers only direct trust / distrust relationships. It also does not use GA optimization. The performances of the proposed algorithm and comparison models were evaluated by using average MAE (mean absolute error). Experimental result showed that the optimal adjusting coefficients for direct trust, indirect trust, direct distrust, indirect distrust were 0, 1.4287, 1.5, 0.4615 each. This implies that distrust relationships between users are more important than trust ones in recommender systems. From the perspective of recommendation accuracy, SNACF-GA (Avg. MAE = 0.111943), the proposed algorithm which reflects both direct and indirect trust / distrust relationships information, was found to greatly outperform a conventional CF (Avg. MAE = 0.112638). Also, the algorithm showed better recommendation accuracy than the SNACF (Avg. MAE = 0.112209). To confirm whether these differences are statistically significant or not, we applied paired samples t-test. The results from the paired samples t-test presented that the difference between SNACF-GA and conventional CF was statistical significant at the 1% significance level, and the difference between SNACF-GA and SNACF was statistical significant at the 5%. Our study found that the trust/distrust relationship can be important information for improving performance of recommendation algorithms. Especially, distrust relationship information was found to have a greater impact on the performance improvement of CF. This implies that we need to have more attention on distrust (negative) relationships rather than trust (positive) ones when tracking and managing social relationships between users.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.27-44
• /
• 2020

In order to solve the user's information overload problem, recommender systems infer users' preferences and suggest items that match them. The collaborative filtering (CF), the most successful recommendation algorithm, has been improving performance until recently and applied to various business domains. Visual information, such as book covers, could influence consumers' purchase decision making. However, CF-based recommender systems have rarely considered for visual information. In this study, we propose VizNCS, a CF-based deep learning model that uses visual information as additional information. VizNCS consists of two phases. In the first phase, we build convolutional neural networks (CNN) to extract visual features from image data. In the second phase, we supply the visual features to the NCF model that is known to easy to extend to other information among the deep learning-based recommendation systems. As the results of the performance comparison experiments, VizNCS showed higher performance than the vanilla NCF. We also conducted an additional experiment to see if the visual information affects differently depending on the product category. The result enables us to identify which categories were affected and which were not. We expect VizNCS to improve the recommender system performance and expand the recommender system's data source to visual information.

• PNF and Movement
• /
• v.10 no.1
• /
• pp.53-59
• /
• 2012

Purpose : This thesis aims to explore sports physical therapist program of university of education of korea and usa for the whole process of becoming sports physical therapist and provide better education programs for cultivating sports physical therapist in the future. Methods : This thesis education programs of physical therapy department in Korea and 3 universities in east california region were selected with recommendation of a professional on sports physical therapist in USA. for the purpose of this study, curriculum of physical education department at school of education was analyzed using internet survey, phone survey, visitor survey and examination of hand book in korea. in usa, homepage, internet survey, e-mail and examination of handbook were used to analyze the data. Results : First, the results of this study can be summarized as follows: second, In comparison of required subjects and selective subject of physical therapy education in Korea and USA, Korea presents the least required subjects for major while USA offer more required subjects for majors. Korea puts focus on education practice while USA offers initial field experience and education practice well connected and organized systematically. Third, comparison of system of professional sports physical therapist, Korea did not establish system of a professional sports physical therapist, USA systematically established system of a professional sports physical therapist. Conclusion : On the basis Professional physical therapist, PNF association has to need to study hardly about special therapist.

• Journal of the Korean Society of Costume
• /
• v.1
• /
• pp.101-117
• /
• 1977

This thesis is a study of the Simui(深衣) system which was a dress regulation peculiar to old China with skirt and coat. The origin of Simui is a very long time, that is, before Ju dynasty in China. Its wearing range had a large circle irrespective of rank and good or bad luck. This was a ordinary dress to the Emperor or the lords, a below court attire or a below sacrificial rites attire to the illustrious officials, and good luck dress to the common people. But this was a funeral rites attire or coming-of-age ceremony attire in domestic behaviour. In the times of Song dynasty, lots of confucian scholars had put on this simui because of Juhi's recommendation for domestic behaviour. This Simui had been put on through all the times of China and was the original text of all the dress. Especially the court attire and silkworm working dress of Empress, and the court attire and underwear court attire of Emperor is also made out of this Simui, therefore this is a origin of the ceremonial dress which formed into long coat. In Korea it is said that this Simui was brought in prior to the middle of Goryeo dynasty. But we can't tell the correct transmitted age. According to the following records in Goryeo History, "King had put on the Simui as a sacrificial rite attire in the times of Yejong". It is sure that this Simui was brought in prior to the times of Yejong. In fact, lots of confucian scholars had put on the Simui since the introduction of confucianism in the end of Goryeo dynasty and after that time this was taken by many confucian scholars through Yi dynasty. Korean Simui system was complied with Chinese system through confucian domestic behaviour, This was respected for court dress of confucian scholars, as it were, Chumri, (an ordinary dress of scholars), Nansam (a uniform of upper student), and Hakchangui (a uniform of confucian student). There are many deta about Simui system in the book of Yeki, chapter Okcho and Simui, and other many canfucian books. But we didn't demonstrate the theory about it till now. Especially there are diversifies of opinions about the phrase of "Sok Im Ku Byun" in Yeki. Simui was cut in separate and then was stitched together in one piece. Generally its shape had round sleeve and angled lapel, its length reaches to the anklebone. And it has a line around the lapel, the sleeve band, and the edge of skirt. It is called Simui because the body can be wrapped deeply in broad width and large sleeve. The Simui was made of white fine linen and was cut by the natural size of body. Every part of Simui had a profound meaning; the round sleeve in compliance with regulation can keep a courtesy when a walker moves his hands and the angled lapel like a carpenter's square in compliance with square keeps them front loosing their Justice and a string of the back also keeps them loosing from their righteousness and the flat lower part of Simui makes their heart and mind calm. This Simui was usually attendant on a head cover and belt made cloth, and black shoes. This thesis was made a study of documents and portrait from Yi dynasty, for the actual object was not obtained.

• 대한공업교육학회지
• /
• v.31 no.2
• /
• pp.233-256
• /
• 2006

The purpose of this study was to analyse between foreign curriculum and our high school industrial technology subject-matter curriculum, to review trend and stream of curriculum revision, and purpose and content system of subject-matter. This study was conducted through reviewing literature; research reference, journal, book, and Web materials. in this study, comparative target country was restricted to Japan, U. S. A., U. K., and N. Z., Australia that administer to similar subject with our industrial technology subject-matter. The major finding of this study were as follows: 1. A similar subject-matter with our industrial technology subject0matter was Japan' 'foundation of industrial technology' and 'project research', U. S. A.' 'technology' and etc, U. K.' 'design and technology', and N. Z.' 'technology', 'New South Wales in Australia' design and technology'. 2. The result of analysis to purpose and strength of subject-matter, our' industrial technology subject-matter was oriented to knowledge, understanding and career search in industrial area. but, the other was emphasized technological problem solving by process-based method with thinking and action. 3. In the curriculum content, our country was treat to content area of a broad industrial world. on the other hand, Japan; relationship between human and technology, environment, process technology and product technology, project research. U. S. A.; technology content standards by knowledge, process and context, U. K., N. Z., and Australia were focused 'design process'. Based on above results, the recommendation can be established as follows: 1. A study on the implementation of industrial technology curriculum. 2. A study on the perception and need assessment of expert and stakeholder about purpose and content system. of industrial technology subject-matter.