• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1010-1014
• /
• 2010

Article-related product recommender system is an emerging e-commerce service which recommends items based on association in contexts between items and articles. Current services recommend based on the similarity between tags of articles and items, which is deficient not only due to the high cost in manual tagging but also low accuracies in recommendation. As a component of novel article-related item recommender system, we propose a new method for tagging item images based on pre-defined categories. We suggest a hypernetwork-based algorithm for learning association between images, which is represented by visual words, and categories of products. Learned hypernetwork are used to assign multiple tags to unlabeled item images. We show the ability of our method with a product set of real-world online shopping-mall including 1,251 product images with 10 categories. Experimental results not only show that the proposed method has competitive tagging performance compared with other classifiers but also present that the proposed multi-tagging method based on hypernetworks improves the accuracy of tagging.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.3
• /
• pp.745-753
• /
• 2010

Many studies using RFID which can identify the movement of targeted objects has been conducted actively. In this paper, we propose improved tagging method to check exactly the amount of fish feed by the aquaculture tank in a land-based aquaculture farm and design the RFID feeding system to perform auto feeding history. Also, we implement the prototype system which it includes development program for auto-identification and auto-recording and self-made RFID feeding cart equipped the weight device, RFID reader, control module and display device.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.737-743
• /
• 2017

The intelligent life-log system proposed in this paper is intended to identify and record a myriad of everyday life information as to the occurrence of various events based on when, where, with whom, what and how, that is, a wide variety of contextual information involving person, scene, ages, emotion, relation, state, location, moving route, etc. with a unique tag on each piece of such information and to allow users to get a quick and easy access to such information. Context awareness generates and classifies information on a tag unit basis using the auto-tagging technology and biometrics recognition technology and builds a situation information database. In this paper, we developed an active modeling method and an application that recognizes expressionless and smile expressions using lip lines to automatically record emotion information.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.123-124
• /
• 2010

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.56-67
• /
• 2019

The aim of this study is to develop Artificial Intelligence (AI) based business models of media firms. We define AI and discuss 'AI activity model'. The practices of the efficiency model are home equipment-based personalization and media content recommendation. The practices of the expert model are media content commissioning, content rights negotiation, copyright infringement, and promotion. The practices of the effectiveness model are photo & video auto-tagging and auto subtitling & simultaneous translation. The practices of the innovation model are content script creation and metadata management. The related use cases from 2012 to 2017 are introduced along the four activity models of AI. In conclusion, we propose for media companies to fully utilize the AI for transforming from traditional to successful digital media firms.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.6
• /
• pp.816-833
• /
• 1999

스타일 정보를 중심으로 하는 기존의 워드 프로세서의 출력 문서들을 차세대 인터넷 문서인 XML문서방식에 따라서 표기하고 또한 제목, 초록, 장 및 단락 등과 같은 논리적인 구조를 반영할 수 있도록 구조화함으로써 문서들의 상호교환뿐만 아니라 인터넷에서 유효하게 사용할 수가 있다. 본 논문에서는 스타일 또는 표현 속성 중심으로 하는 다양한 문서의 평면 구조를 XML의 계층적인 논리적인 구조로, 또한 다양한 DTD(Document Type Definition)환경하에서 변경시킬 수가 있는 변환 스크립트 언어를 표현할 수 있도록 하기 위하여 XTML(XML Transformation Markup Language)을 DTD형식으로 정의하고 이를 이용하여 변환 스크립트를 작성하였으며 자동태깅에 적용하여 보았다.XTML은 그 인스턴스에 해당하는 변환 알고리즘의 효과적인 수행을 위하여 즉 기존의 XML문서를 효과적으로 다루기 위하여 문서를 GROVE라는 트리 구조로 만들어 저장하고 또한 이를 조작할 수 있는 기능 및 다양한 명령어 인터페이스를 제공하였다. Abstract Output documents of existing word processors based on style informations or presentation attributes can be structured by converting them into XML(Extensible Markup Language) documents based on hierarchically logical structures such as title, abstract, chapter and so on. If so, it can be very useful to interchange and manipulate documents under Internet environment. The conversion need the complicate process calling auto-tagging by which elements of output documents can be inferred from style informations and sequences of text etc, and which is different from various kinds of simple conversion.In this paper, we defined XTML(XML Transformation Markup Language) of DTD(Document Type Definition) form and also defined the script language as instances of its DTD for the auto-tagging. XTML and its DTD are represented in XML syntax.Especially XTML includes various functions and commands to generate tree structure named as "GROVE" and also to process, store and manipulate the GROVE in order to process efficiently XML documents.documents.

• Journal of fish pathology
• /
• v.26 no.2
• /
• pp.59-64
• /
• 2013

This study aimed to develop an algorithm to determine the optimal injection position in olive flounder, Paralichthys olivaceus when a vaccine is injected into the fish by using a vision-based automatic equipment measruing the total length (TL), width and weight of the fish. Over a 5-month period, 500 olive flounders were examined to analyze the relation of the fish size and to the shape and location of its abdomen, using radiography, a ruler plate and scale. There were significant correlations between the TL and the shape and location of the abdomen. The abdomen was located 0.232TL - 2.7221 mm ($R^2$=0.8787) from the end of the mouth of the fish. The height and width of the abdomen in the fish were 0.1292TL + 1.8768 mm ($R^2$=0.7935) and 0.183TL-5.9791 mm ($R^2$=0.8641), respectively. The injection point in the abdominal region avoiding organs was determined by calculating the center of gravity of the abdomen volume. This can be expressed as g (0.2759TL - 2.0965, 0.1295TL - 4.2325) on the basis of TL line coordinates. The injection point by the expressed coordinates had errors for the x and y axes as 12.15 mm and 8.28 mm, respectively. These were enough to use the algorithm to injection for the equipment. This automated method to determine the position of any part in the fish can also be used for other purposes, for example, intramuscular injection or auto-tagging of fish.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.4
• /
• pp.171-185
• /
• 2014

The purposes of this study are to examine the various methods of subject access in the rapidly changing environment and to suggest the future of subject access in National Library of Korea (NLK). First of all, current status and problems of Library of Congress Subject Headings List as an representative subject headings in the world and the ways of improving effectiveness of subject retrieval were dealt with. As the ways of improving subject access, social bookmarking, folksonomy, tagging, facet applications, automatic assignment of keyword, thesauri, classification system, and auto-assigned search box were suggested. Finally, current status of NLK subject headings and the ways of improving for utilization of the subject headings as subject access were provided.