• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.118-125
• /
• 2004

인간의 언어지식은 다양한 개념 관계를 가지며 서로 망(network)의 모습으로 연결되어 있다. 인간의 언어지식의 산물 중에서 가장 체계적이며 구조적으로 언어의 모습을 드러내고 있는 결과물이 사전이라고 할 수 있다. 본 논문에서는 이러한 사전 뜻풀이 말에서 개념 어휘와 자동적인 지식획득을 통하여 의미 정보를 구조적으로 추출한다. 이러한 의미 정보가 추출되면서 동시에 자동적으로 개념 어휘의 의미 참조 모형이 구축된다. 이러한 것은 사전이 표제어 리스트와 표제어를 기술하는 뜻풀이말로 이루어진 구조의 특성상 가능하다. 먼저 172,000여 개의 사전 뜻풀이말을 대상으로 품사 태그와 의미 태그가 부여된 코퍼스에서 의미 정보를 추출하는데, 의미분별이 처리 된 결과물을 대상으로 하기 때문에 의미 중의성은 고려하지 않아도 된다. 추출된 의미 정보를 대상으로 정제 작업을 거쳐 정보이론의 상호 정보량(Ml)을 이용하여 개념 어휘와 의미 정보간에 연관도를 측정한 후, 개념 어휘간의 유사도(SMC)를 구하여 지식표현의 하나로 연관망을 구축한다.

• Journal of Internet Computing and Services
• /
• v.14 no.5
• /
• pp.1-10
• /
• 2013

RFID(Radio Frequency Identification) system is non-contact identification technology. A basic RFID system consists of a reader, and a set of tags. RFID tags can be divided into active and passive tags. Active tags with power source allows their own operation execution and passive tags are small and low-cost. So passive tags are more suitable for distribution industry than active tags. A reader processes the information receiving from tags. RFID system achieves a fast identification of multiple tags using radio frequency. RFID systems has been applied into a variety of fields such as distribution, logistics, transportation, inventory management, access control, finance and etc. To encourage the introduction of RFID systems, several problems (price, size, power consumption, security) should be resolved. In this paper, we proposed an algorithm to significantly alleviate the collision problem caused by simultaneous responses of multiple tags. In the RFID systems, in anti-collision schemes, there are three methods: probabilistic, deterministic, and hybrid. In this paper, we introduce ALOHA-based protocol as a probabilistic method, and Tree-based protocol as a deterministic one. In Aloha-based protocols, time is divided into multiple slots. Tags randomly select their own IDs and transmit it. But Aloha-based protocol cannot guarantee that all tags are identified because they are probabilistic methods. In contrast, Tree-based protocols guarantee that a reader identifies all tags within the transmission range of the reader. In Tree-based protocols, a reader sends a query, and tags respond it with their own IDs. When a reader sends a query and two or more tags respond, a collision occurs. Then the reader makes and sends a new query. Frequent collisions make the identification performance degrade. Therefore, to identify tags quickly, it is necessary to reduce collisions efficiently. Each RFID tag has an ID of 96bit EPC(Electronic Product Code). The tags in a company or manufacturer have similar tag IDs with the same prefix. Unnecessary collisions occur while identifying multiple tags using Query Tree protocol. It results in growth of query-responses and idle time, which the identification time significantly increases. To solve this problem, Collision Tree protocol and M-ary Query Tree protocol have been proposed. However, in Collision Tree protocol and Query Tree protocol, only one bit is identified during one query-response. And, when similar tag IDs exist, M-ary Query Tree Protocol generates unnecessary query-responses. In this paper, we propose Adaptive M-ary Query Tree protocol that improves the identification performance using m-bit recognition, collision information of tag IDs, and prediction technique. We compare our proposed scheme with other Tree-based protocols under the same conditions. We show that our proposed scheme outperforms others in terms of identification time and identification efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.5
• /
• pp.871-885
• /
• 2015

The improved DFSA for 2.4GHz multi-tags active RFID is suggested in 2 different ways: 1) simplified tag collection and Ack procedure using query command and 2) modified Schoute's method to control the number of slots in the frame. To evaluate the performance of the improved system we develop the simulation model. Varying the number of tags in the system we track the performance measures such as throughput, recognition time for multi-tags and tag recognition rate during a given time. The suggested method shows the best performance over all measures. Simplification of collection and Ack commands using query commands contributes to reducing tag recognition time. And the modified Schoute's method which controls the frame size using $k_1$ and $k_2$ contributes to throughput improvement and reduces target cognition time by reducing the number of collection rounds.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1515-1518
• /
• 2003

XML의 대표적인 특징은 기존의 다른 컨텐츠와는 달리 문서의 구조를 기술할 수 있다는 것이다. 구조적 정보는 활용 방법에 파라 XML문서의 다양한 처리에 있어 성능을 향상시키는 핵심적인 요소가 될 수 있다. 그러나 XML 태그의 자기 서술적인 특성에서 비롯되는 구조적 표현의 차이는 오히려 문서의 식별을 어렵게 하는 원인이 된다. 본 논문에서는 기존의 비트맵 인덱스(Bitmap Index)를 이용한 XML 문서 검색 시스템이 다양한 구조적 유사성을 판별할 수 없는 단점을 보완 가능하도록 경로 중심의 유사 문서 인식 기법을 제안한다. 이 기법은 '경로 구성 유사도'와 '유사 경로 테이블'을 통해 기존의 비트맵 인덱스가 갖는 유사 경로를 인식하지 못하는 단점을 해결하고 검색의 유연성을 부여함으로써 보다 양질의 검색 결과를 도출할 수 있다. 또 이것은 기존 시스템의 Bit-wise 연산에 완전히 이식됨으로써 비트맵 인덱스의 장점인 빠른 성능을 그대로 유지할 수 있게 된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.481-487
• /
• 2013

To successfully accomplish a bit synchronization, a synchronizer should exploit a preamble pattern. A MFM (modified frequency modulation) flag is uses as a preamble in a PJM (phase jitter modulation) mode RFID standard. In the recent work, a synchronizer for a PJM mode tag was proposed, which is composed of several correlators. In this paper, we present a new bit synchronizer in which a coarse synchronization is done as in the previous work while a fine synchronization is performed via exploiting a violation bit included in the MFM flag. We show that the proposed synchronizer can significantly reduce the overall hardware complexity at the expense of slight burden to a demodulator structure. Through simulation, we also show that its performance is comparable to that of the previous system despite its hardware simplicity.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2010.08a
• /
• pp.21-28
• /
• 2010

본 연구에서는 PubMed에 등재되었으나 Medical Subject Headings(MeSH)가 부여되지 않은 국내 의학학술지의 문헌을 대상으로 미국국립의학도서관 (NLM: National Library of Medicine)의 Medical Text Indexer(MTI)를 활용하여 MeSH 용어를 추천받은 후, PubMed 레코드의 유사주제문헌 (Relation Citations, PRC)에 부여된 MeSH와의 일치여부를 분석하였다. 또한 논문의 저자가 부여한 키워드(저자키워드)와 PRC MeSH의 일치여부도 비교하였다. PRC MeSH와 MTI MeSH 추천어의 일치율은 주표목이 21.1%였고, 체크태그는 18.1%, 부표목은 16.5%로 나타났다. 우리나라 의학논문에 나타난 저자키워드의 중요한 특징은 MeSH 주표목 위주이고, 체크태그와 부표목은 거의 사용하지 않는 것이다. 따라서 저자키워드와 PRC MeSH 주표목과의 일치율은 23.4%에 이르지만, 체크태그와 부표목의 일치율은 각각 1%, 2.1%였다. 색인전문가가 통제어휘를 사용하여 색인하는 과정에서 PRC와 MTI의 MeSH 주표목과 저자키워드가 일치하는 용어를 주표목으로 부여하고, PRC와 MTI가 추천하는 체크태그와 부표목을 활용하는 등 국내 의학문헌의 MeSH 용어 부여 작업을 반자동화(semi-indexing)하면, 정확하고 신속한 MeSH 부여 작업이 가능할 것이다.

• KIISE Transactions on Computing Practices
• /
• v.22 no.6
• /
• pp.290-295
• /
• 2016

Recently, folksonomy-based image-sharing sites where users cooperatively make and utilize tags of image annotation have been gaining popularity. Typically, these sites retrieve images for a user request using simple text-based matching and display retrieved images in the form of photo stream. However, these tags are personal and subjective and images are not categorized, which results in poor retrieval accuracy and low user satisfaction. In this paper, we propose a categorization scheme for folksonomy images which can improve the retrieval accuracy in the tag-based image retrieval systems. Consequently, images are classified by the semantic similarity using text-information and image-information generated on the folksonomy. To evaluate the performance of our proposed scheme, we collect folksonomy images and categorize them using text features and image features. And then, we compare its retrieval accuracy with that of existing systems.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.16 no.12 s.103
• /
• pp.1206-1212
• /
• 2005

In this paper, we propose a novel antenna structure which uses the electric and magnetic currents so as to eliminate nulls on their radiation pattern. The tag antenna was matched to the conjugate impedance of the commercial tag chip using the modified double T matching network. The radiation efficiency is about $90\%$, and the bandwidth($S_{11}< -10 dB$) is 848${\~}$926 MHz. Also it shows the gain deviation between the maximum and minimum gains about 4 dB at any direction of the tag antenna at the operating frequency. The readable range of the tag is 1.7${\~}$2.4 m for an arbitrary rotation angle of the tag with a commercial tag chip.

• 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.