• 한국ITS학회:학술대회논문집
• /
• 2005.11a
• /
• pp.62-66
• /
• 2005

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.192-195
• /
• 2008

People have tendency of forgetting music title, though they easily remember particular part of music. If a music search system can find the title through a part of melody, this will provide very convenient interface to users. In this paper, we propose an algorithm that enables this type of search using feature transformation function. The original music is transformed to new feature information with sequential melodies. When a melody that is a part of search music is given to the system, the music retrieval system searches the music similar to the feature information of the melody. Moreover, this transformation function can be easily extended to various music recognition systems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.443-450
• /
• 2005

In this paper, we propose an intelligent model lot extraction of the web user's preference and present the results of evaluation. For this purpose, we analyze shortcomings of current information retrieval engine being used and reflect preference weights on learner. As it doesn't depend on frequency of each word but intelligently learns patterns of user behavior, the mechanism Provides the appropriate set of results about user's questions. Then, we propose the concept of preference trend and its considerations and present an algorithm for extracting preference with examples. Also, we design an intelligent model for extraction of behavior patterns and propose HTML index and process of intelligent learning for preference decision. Finally, we validate the proposed model by comparing estimated results(after applying the Preference) of document ranking measurement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.345-359
• /
• 2017

Optical Character Recognition (OCR) that has been a main research topic of computer vision and artificial intelligence now extend its applications to detection of text area from video or image contents taken by camera devices and retrieval of text information from the area. This paper aims to implement a binarization algorithm that removes user intervention and provides robust performance to outdoor lights by using TopHat algorithm and channel transformation technique. In this study, we particularly concentrate on text information of outdoor signboards and validate our proposed technique using those data.

• Journal of Korean Library and Information Science Society
• /
• v.40 no.2
• /
• pp.139-159
• /
• 2009

This study is to develop knowledge base system for query extension to the user oriented information retrieval. This study has survey the theories of the concept-based information retrieval method and statistic based information retrieval method. In the construction method of knowledge base, the common hypothesis is that the emergence of related term is the frequency of simultaneous emergence of a set of documents. Using the subject index file algorithms and the 'and' operator of boolean logic based on this hypothesis, this study builds the knowledge base. In this research experiment, a subject of knowledge base is education. Using the book of the Introduction to Education, two experimental knowledge base systems is constructed by the different indexing method. One system has constructed by controlled language indexing method, and another system has constructed by natural language indexing method. The performance of two knowledge base system is evaluated.

• Journal of Intelligence and Information Systems
• /
• v.13 no.3
• /
• pp.1-15
• /
• 2007

Recently, semantic web technology, represented by ontology building, is being combined with web services technology, creating 'Semantic Web Services' as a new promising field in information retrieval research. Accordingly, many brokering and matchmaking agents are being developed and used in the field. However, literature review revealed that most models do not take QoS(Quality of Services) into consideration. In this study, a QoS-augmented matchmaking algorithm is developed based on service availability, response time, maximum transaction amount, reliability, accessibility and price as critical QoS items. A prototype for Intelligent Semantic Web Services System is developed using publicly available data. Performance test was conducted and reported at the end.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.766-771
• /
• 2006

In this paper, we focus on the building domain ontology from corpus by extracting concepts and properties relationships based on linguistic patterns. The pharmacy field is selected as an experiment domain and we present an algorithm to extract hierarchical structure for terminology based on the noun/suffix patterns of terminology in domain texts. In order to show usefulness of our domain ontology, we compare a typical keyword based retrieval method with an ontology based retrieval mettled which uses related information in an ontology for a related feedback. As a result, our method shows the improvement of precision by 4.97% without losing recall.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.7-15
• /
• 2014

Image retrieval has become a huge part of computer vision and data mining. Although commercial image retrieval systems such as Google show great performances, the improvement on the performances are constantly on demand because of the rapid growth of data on web space. To satisfy the demand, many re-ranking methods, which enhance the performances by reordering retrieved results with independent algorithms, has been proposed. Conventional re-ranking algorithms are based on the assumption that visual patterns are not used on initial image retrieval stage. However, image search engines in present have begun to use the visual and the assumption is required to be reconsidered. Also, though it is possible to suspect that integration of multiple retrieval systems can improve the overall performance, the research on the topic has not been done sufficiently. In this paper, we made the condition that other manner than cooperation cannot improve the ranking result. We evaluate the algorithm on toy model and show that propose module can improve the retrieval results.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.272-277
• /
• 2001

In this paper, we describe a new method for selecting information sources in a distributed environment. Recently, there has been much research on distributed information retrieval, that is information retrieval (IR) based on a multi-database model in which the existence of multiple sources is modeled explicitly. In distributed IR, a method is needed that would enable selecting appropriate sources for users\` queries. Most existing methods use statistical data such as document frequency. These methods may select inappropriate ate sources if a query contains polysemous words. In this paper, we describe an information-source selection method using two types of thesaurus. One is a thesaurus automatically constructed from documents in a source. The other is a hand-crafted general-purpose thesaurus(e.g. WordNet). Terms used in documents in a source differ from one another and the meanings of a term differ depending on th situation in which the term is used. The difference is a characteristic of the source. In our method, the meanings of a term are distinguished between by the relationship between the term and other terms, and the relationship appear in the co-occurrence-based thesaurus. In this paper, we describe an algorithm for evaluating a usefulness of a source for a query based on a thesaurus. For a practical application of our method, we have developed Papits, a multi-agent-based in formation sharing system. An experiment of selection shows that our method is effective for selecting appropriate sources.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.7
• /
• pp.93-100
• /
• 2019

In this paper, we propose an intelligent marketing service system that can provide custom advertisements and events to both businesses and customers by identifying the location and contents using the ultrasonic signals and feature information in voice signals. We also develop the encoding and decoding algorithm of ultrasonic signals for this system and analyze the performance evaluation results. With the development of the hyper-connected society, the on-line marketing has been activated and is growing in size. Existing store marketing applications have disadvantages that customers have to find out events or promotional materials that the headquarters or stores throughusing the corresponding applications whenever they visit them. To solve these problems, there are attempts to create intelligent marketing tools using GPS technology and voice recognition technology. However, this approach has difficulties in technology development due to accuracy of location and speed of comparison and retrieval of voice recognition technology, and marketing services for customer relation are also much simplified.