• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.54-60
• /
• 2011

The study is content-based video retrieval system based on the news video domain as researching for the video data processing method for searching the multimedia information. For the implementation of effective system, We retrieval meaning information and special information using the knowing knowledge about formation and structure of the video data. These are possible to retrieval searching by articles fast and accurately by indexing contents the users want to search. The news domain used in experiment of our system is the KBS news on the air nowadays and precision and recall is used to evaluate the experiment and performance.

• Journal of the Korean Dietetic Association
• /
• v.15 no.3
• /
• pp.286-297
• /
• 2009

Studies based on food analysis or food databases use the national standard food database. Although Internet information services are increasing gradually, users are only able to get definitive and profitable information using standard food terms. Until now, it has been uncommon to find food retrieval services that include users' regional or historical characteristics. Thus, this study introduces a prototype for Food and Dish Synonym Retrieval (NutriSyn) that includes synonyms and related words. The environments which NutriSyn was implemented were Linux for the server operating system, the Microsoft Windows series for the users' operating system and Apache for a web server. The development languages used are PHP, JavaScript and HTLM with a MySQL database. Users can access NutriSyn using Internet browsers. The main menu items are (1) Food Synonym DB, (2) Dish Synonym DB, (3) Food Information DB, (4) Dish Information DB, and (5) Food and Menu Synonym Retrieval. This system is expected to be a useful tool for food experts and interdisciplinary research.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.1-10
• /
• 2005

This paper presents the information retrieval system which can retrieve the most appropriate answer sentence for user queries by using the concept and the attribute for the knowledge retrieval. The system analyzes the user query into the Boolean queries with the concept and the attribute and then retrieve the relevant documents in the indexing set of answer documents. Users can retrieve the relevant answer sentences from the relevant documents. For this, the answer documents indexed by the concept and the attribute are segmented by each sentence respectively. Thus, the segmented sentences are analyzed into the concept and the attribute of which the relevance degree with indexing units of documents is evaluated. Then, the system indexes the location of answer sentences. In the experiment, we evaluate the performance of our answer retrieval system against 100 user queries and show the experimental results.

• Journal of the Korean Society for information Management
• /
• v.17 no.3
• /
• pp.45-70
• /
• 2000

• Journal of Technology Innovation
• /
• v.7 no.2
• /
• pp.119-144
• /
• 1999

Recently, knowledge management(KM) has attracted increasing attention from academicians and practitioners alike. Amongst others, technological knowledge(TK) is considered principal asset of KM and R,&D organization of private firms selves as primary actor of KM. It is also noted that the notion of sectoral pattern of innovation highlights idiosyncratic differences across industrial sectors in terms of TK management. That is, knowledge contents, knowledge generation and How pattern are considerably different among industries. This paper first analyzes the correlation between structural of R&D organization and industrial(sectoral) type to identify the dominant structure of R&D organization for each industry. Second, sector-specific architectures of TK management system are proposed. According to structural characteristic of R&D-organization type, test-practice forms of TK management system are suggested in terms of such factors as knowledge contents(technology information), knowledge generation activities, and knowledge storage/retrieval modes.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.4
• /
• pp.69-76
• /
• 2004

A framework for knowledge management system has been explored which enables the semantic search of knowledge on the web. Knowledge representation by RDF and RDF schema enables machine cognition of knowledge documents. Dublin core was adopted for structured metadata representation. Thereby, it enables the CBR and rule based reasoning for intelligent knowledge retrieval. Grafting of the WFMS technique unto the KMS facilitates the effective utilization of process knowledge and creation of new knowledge.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.355-361
• /
• 1999

An application of case-based reasoning is proposed to build an influence diagram for identifying successful new ventures. The decision to invest in new ventures in characterized by incomplete information and uncertainty, where some measures of firm performance are quantitative, while some others are substituted by qualitative indicators. Influence diagrams are used as a model for representing investment decision problems based on incomplete and uncertain information from a variety of sources. The building of influence diagrams needs much time and efforts and the resulting model such as a decision model is applicable to only one specific problem. However, some prior knowledge from the experience to build decision model can be utilized to resolve other similar decision problems. The basic idea of case-based reasoning is that humans reuse the problem solving experience to solve a new decision. In this paper, we suggest a case-based reasoning approach to build an influence diagram for the class of investment decision problems. This is composed of a retrieval procedure and an adaptation procedure. The retrieval procedure use two suggested measures, the fitting ratio and the garbage ratio. An adaptation procedure is based on a decision-analytic knowledge and decision participants knowledge. Each step of procedure is explained step by step, and it is applied to the investment decision problem in new ventures.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.505-509
• /
• 2020

Twitter is a useful medium to grasp various damage situations that have occurred in society. However, it is a laborious task to spot damage-related topics according to time in the environment where information is constantly produced. This paper proposes a methodology of constructing a knowledge structure by combining the BERT-based classifier and the community detection techniques to discover the topics underlain in the damage information. The methodology consists of two steps. In the first step, the tweets are classified into the classes that are related to human damage, infrastructure damage, and industrial activity damage by a BERT-based transfer learning approach. In the second step, networks of the words that appear in the damage-related tweets are constructed based on the co-occurrence matrix. The derived networks are partitioned by maximizing the modularity to reveal the hidden topics. Five keywords with high values of degree centrality are selected to interpret the topics. The proposed methodology is validated with the Hurricane Harvey test data.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.153-156
• /
• 2005

In this paper, a framework for implementing UFIS (Unified Fuzzy rule-based knowledge Inference System) is presented. First, fuzzy clustering and fuzzy rules deal with the presence of the knowledge in DB (DataBase) and its value is presented with a value between 0 and 1. Second, RDB (Relational DB) and SQL queries provide more flexible functionality fur knowledge management than the conventional non-fuzzy knowledge management systems. Therefore, the obtained fuzzy rules offer the user additional information to be added to the query with the purpose of guiding the search and improving the retrieval in knowledge base and/ or rule base. The framework can be used as DM (Data Mining) and ES (Expert Systems) development and easily integrated with conventional KMS (Knowledge Management Systems) and ES.

• Journal of Information Processing Systems
• /
• v.10 no.4
• /
• pp.581-588
• /
• 2014

To facilitate the implementation of a wide variety of context-aware applications based on mobile devices, general-purpose context-aware framework that applications can use by calling is needed. The context-aware framework is a middleware that performs the sensing, reasoning, and retrieving based on the knowledge base. The knowledge base must systematically represent the information required on the behavior of the context-aware framework, such as context information and reasoning information. It must also provide functions for storage and retrieval. To date, previous research on the representation of the context information have been carried out, but studies on the unified representation of the knowledge base has seen little progress. This study defines the knowledge base as the unified context information, and proposes the UniOWL, which can do a good job of representing it. UniOWL is based on OWL and represents the information that is necessary for the operation of the context-aware framework. Therefore, UniOWL greatly facilitates the implementation of the knowledge base on a context-aware framework.