• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.2
• /
• pp.265-275
• /
• 1994

Lexical disambiguation is one of the most basic areas in natural language processing such as speech recognition/synthesis, information retrieval, corpus tagging/ etc. This paper describes a Korean lexical disambiguation mechanism where the disambigution is perfoemed on the basis of the statistical information collected from corpora. In this mechanism, the token tags corresponding to the results of the morphological analysis are used instead of part of speech tags for the purpose of detail disambiguation. The lexical selection function proposed shows considerably high accuracy, since the lexical characteristics of Korean such as concordance of endings or postpositions are well reflected in it. Two disambiguation methods, a unique selection method and a multiple selection method, are provided so that they can be properly according to the application areas.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.8A
• /
• pp.847-857
• /
• 2007

For the implementation of a RFID system, an anti-collision algorithm is required to identify multiple tags within the range of a RFID Reader. A Bit-by-Bit algorithm is defined by Auto ID Class 0. In this paper, we propose a SBBB(Stack Bit-by-Bit) algorithm. The SBBB algorithm save the collision position and makes a query using the saved data. SBBB improve the efficiency of collision resolution. We show the performance of the SBBB algorithm by simulation. The performance of the proposed algorithm is higher than that of BBB algorithm. Especially, the more each tag bit streams are the duplicate, the higher performance is.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.123-131
• /
• 2019

Social network service users actively express and share their feelings about social issues and content of interest through postings. As a result, the sharing of emotions among individuals and community members in social network is spreading rapidly. Therefore, resulting in active research of emotion analysis on posting of users. However, There is insufficient research on emotion analysis for postings containing various emotions. In this paper, we propose a method that analyzes the emotions of an Instagram posts using hashtags and images. This method extracts representative emotion from user posts containing multiple emotions with 66.4% accuracy and 81.7% recall, which improves the emotion classification performance compared to the previous method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.561-566
• /
• 2011

In EPCglobal Class-1 Gen-2 RFID system, a slot-count selection algorithm has been proposed to determine the slot-count size depending on the status of reply slot. In the slot-count selection algorithm of Gen-2, the slot-count value is increased or decreased by the weight C, which is identical and independent of the slot status. It has an advantage that the algorithm is simple, but it is difficult to maintain an optimal slot-count size. Therefore, in this paper, we propose an adaptive slot-count selection algorithm, which applies the parameter C differently based on the result of tag replies. Through simulations, it is demonstrated that the collision rate for the proposed scheme is about 42% and 65% lower than the schemes proposed by Wang and Gen-2. Therefore, the adaptive slot-count selection algorithm achieves faster tag identification time compared with the existing algorithms due to the low collision rate.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.4
• /
• pp.61-67
• /
• 2011

In these days, RFID adoption in supply chain management system needs technically part of the performance improvement of RFID Anti-Collision technology. We contrived new scanning algorithm that improve RFID Anti Collision performance, also can be applied to existing RFID readers. In this paper, the proposed algorithm were applied to the actual logistics scene recognition performance much better than the existing practices are presented. For improve of RFID Anti Collision performance, our algorithm implemented in the middleware associated with RFID PDA readers, and actually mount the RFID inventory data from the experiment were accumulated. Through this experiment, the proposed algorithm was confirmed that helps to minimize unaware area of the existing RFID inventory system and significantly improves performance of RFID field solution.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1169-1172
• /
• 2005

In this paper, we propose an improved anti-collision algorithm for multi tag interrogation in ubiquitous sensor network(USN) and show the result of simulation for multi tag interrogation in RFID systems. We have analyzed an EPC(Electronic Product Code) protocol which specifies the physical and logical requirements for a passive-backscatter Reader-Talk-First(RTF) RFID(Radio Frequency Identification) system operating in the $860MHz{\sim}960MHz$ frequency range. We have also designed and implemented the simulator of the RFID system based on the EPC protocol. Finally, we find that proposed algorithm works better than an existing algorithm.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.325-326
• /
• 2010

Web2.0 서비스가 늘어나면서, 집단의 지혜를 바탕으로 한 개인화 서비스에 대한 관심이 증가하고 있다. 유튜브(youtube) 등 에서 태그를 공유함으로써 유용한 정보에 쉽게 접근할 수 있도록 하고 있다. 이에, 본 연구에서는 사용자가 생산한 학습콘텐츠를 바탕으로 개인화 서비스를 위한 추천시스템에 관한 연구를 진행하고자 한다. 이를 위해 교육용 UCC 사이트에서 정보추천을 위해 제공하는 속성들을 바탕으로 Tag와 Rating을 이용한 UCC분류기반 추천시스템을 제안하고, 이를 위한 메타데이터와 추천시스템을 설계하고자 한다.

• Journal of Information Technology Services
• /
• v.12 no.3
• /
• pp.331-343
• /
• 2013

In RFID systems, the anti-collision algorithm is being improved to recognize Tag's ID within recognition area of the reader quickly and efficiently. This paper focuses on Tag collision. Many studies have been carried out to resolve Tag collision. This paper proposes a new N-ary Query Tree Algorithm to resolve more than Tag collision simultaneously, according to the value of m(2 ~ 6). This algorithm can identify more tags than existing methods by treating a maximum 6 bit collision, regardless of the continuation/non-continuation Tag's ID patterns. So, it extracts maximumly different $2^6$ bit patterns per single prefix in recognition process. The performance of N-ary Query Tree Algorithm is evaluated by theoretical analysis and simulation program.

• Journal of Digital Convergence
• /
• v.11 no.3
• /
• pp.311-316
• /
• 2013

In order to maximize an efficient management of human cell resource under the cryogenic environments, in this paper, a middleware is introduced to support the function for multiple-perceiving RFID tags of intelligent sample case which can share medical information between sensor network devices. Optimized user interface is also designed for that. On based of the designing, special tasks required of a genetic resource working process can be processed on Complex Machine.