• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.451-464
• /
• 2016

Nowadays, entity search such as Google Product Search and Yahoo Pipes has been in the spotlight. The entity search engines have been used to retrieve web pages relevant with a particular entity. However, if an entity (e.g., Chinatown movie) has various meanings (e.g., Chinatown movies, Chinatown restaurants, and Incheon Chinatown), then the accuracy of the search result will be decreased significantly. To address this problem, in this article, we propose a novel method that quantifies the importance of search queries and then offers the best query for the entity search, based on Frequent Pattern (FP)-Tree, considering the correlation between the entity relevance and the frequency of web pages. According to the experimental results presented in this paper, the proposed method (59% in the average precision) improved the accuracy five times, compared to the traditional query terms (less than 10% in the average precision).

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.2
• /
• pp.223-234
• /
• 2014

This paper proposes a flexible and highly reusable modeling methodology for a next-generation combat entity which enables joint analysis of performance/engagement effectiveness. According to the scope of the proposed work, the paper is divided into two parts; Part 1 focuses on a conceptual model design, whereas Part 2 proposes detailed model specification and implementation. In Part 1, we, first, classify the combat entity model as combat logic and battlefield function sub-models for joint analysis. Based on the sub-models, we propose two dimensional model partition method, which creates six groups of a single combat entity model by two dimensions: three-activity and two-abstraction. This grouping enables us to reconfigure the combat entity model by sharing the same interface within the group, and the same interface becomes the fundamental basis of the flexible model composition. Furthermore, the proposed method provides a model structure that effectively reflects the real world and maximizes the multi-level reusability of a combat entity model. As a case study, we construct a model design for anti-surface ship warfare. The case study proves enhancement of model reusability in the process of scenario expansion from pattern running to wire guided torpedo operations.

• The KIPS Transactions:PartC
• /
• v.14C no.2
• /
• pp.171-178
• /
• 2007

In mobile ad hoc networks, an application scenario requires mostly group mobility behavior in the mix of group moving nodes and individually moving nodes. The nodes of those applications tend to belong to the movement group with similar movement behavior. Group mobility is one of the good methods to improve scalability, and reduces the protocol overhead. In this paper, we propose the multicast architecture which regards nodes that have equal group mobility in the heterogeneous group mobility network as the single entity with the multiple interfaces and composes multicast tree, The logical cooperative entity-based multicast architecture accommodates the scalability, the multicast tree simplification, and the protocol overhead reduction which arc obtained from the hierarchical multicast architecture, while it maintains the nat multicast architecture for the data transmission. It also prevents the concentration of the energy consumption dispersing data forwarding load into the several ingress/egress nodes. Results obtained through simulations show that logical cooperative entity based multicast protocol with multiple interfaces offers the protocol scalability and the efficient data transmission.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10d
• /
• pp.531-535
• /
• 2007

유비쿼터스 지능 공간(Ubiquitous Smart Space)에서 동적으로 발생하는 다양한 문제를 협업을 통하여 해결할 수 있는 방법론으로 제안된 커뮤니티 컴퓨팅(Community Computing) 모델을 기반으로 하는 개발도구(Community Computing Developing Tool Kit : CDTK)를 사용하면 특정 문제를 해결할 수 있는 커뮤니티 컴퓨팅 어플리케이션이 생성된다. 이 커뮤니티 컴퓨팅 어플리케이션이 실제로 유비쿼터스 지능 공간에 존재하는 uT-entity에 이식되어 동작하기 위해서 uT-entity의 종류에 상관없이 커뮤니티 컴퓨팅 어플리케이션이 배포될 수 있는 환경을 필요로 한다. 본 연구에서는 CDTK를 이용하여 생성된 커뮤니티 컴퓨팅어플리케이션이 uT-entity에 배포되어 각 uT-entity가 커뮤니티의 멤버로 참여하여 멤버간의 협업을 통해 목적을 달성할 수 있도록 지원하는 어플리케이션 프레임워크인 멤버 프레임워크(Member Framework)를 제안한다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.2
• /
• pp.266-272
• /
• 2011

Real Time Pricing(RTP) is used not only to stabilize the price volatility in electricity market, but to hedge the price risk for Load Serving Entity(LSE). This paper presents an efficient method to reduce the risk of the price volatility in real-time electricity market. For designing the RTP, load patterns of customer are calculated by applying the demand elasticity and customer's utility is also analyzed to compute the RTP revenue through the risk-attribute of the LSE. In the end, the distribution of the LSE's profits can be evaluated to lead the optimal RTP value, depending on the level of customer's participation. Results from the case study based on PJM data are reported to illustrate the proposed method.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.223-226
• /
• 2020

엔터티 링킹을 위해서는 엔터티 링킹을 수행 할 후보 엔터티의 정보를 얻어내는 것이 필요하다. 하지만, 엔터티 정보를 획득하기 어려운 경우, 엔터티 링킹을 수행 할 수 없다. 이 논문에서는 이를 해결하기 위해 데이터셋으로부터 엔터티의 가상 엔터티 설명문을 작성하고, 이를 통해 엔터티 링킹을 수행함으로써 엔터티 정보가 없는 환경에서도 2.58%p밖에 성능 하락이 일어나지 않음을 보인다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.253-256
• /
• 2009

This paper describes a vertical search system based on multiple entity-centric unification, which enables to deal with the search queries including multiple domains. To implement the system, we introduced two search technologies; one is for merging service components dynamically according to the entities in the search keywords, and the other is for searching fields with appropriate entities. Our current system includes about 453,000 overseas journal papers for article information search and two entity types; research topic and researcher.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.801-808
• /
• 2022

Research on how to embed knowledge in large-scale Linked Data and apply neural network models for entity matching is relatively scarce. The most fundamental problem with this is that different labels lead to lexical heterogeneity. In this paper, we propose an extended GCN (Graph Convolutional Network) model that combines re-align structure to solve this lexical heterogeneity problem. The proposed model improved the performance by 53% and 40%, respectively, compared to the existing embedded-based MTransE and BootEA models, and improved the performance by 5.1% compared to the GCN-based RDGCN model.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.4
• /
• pp.29-57
• /
• 2014

This study aims to develop a metadata schema for sports moving records based on a multiple entity model as an attempt to suggest an effective way to manage, retrieve, and utilize sports moving records. The multiple entity model consists of four entities - sports match, match contributors, moving records, and record management business - and metadata elements were developed for each entity. In addition, authority records for sports team and persons were created to ensure the consistency of terminology and provide rich contextual information. The suggested multiple entity model, metadata elements, and authority records for sports teams and persons were verified, modified, and expanded by a group of experts including a sports marketing expert and professors in the sports department.