• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.161-171
• /
• 1999

Query language has been widely used as a convenient tool to obtain information from a database. However, users demand more intelligent query processing systems that can understand the intent of an imprecise query and provide additional useful information as well as exact answers. This paper introduces a meta-database and presents a query processing mechanism that supports a variety of intelligent queries in a consistent and integrated way. The meta-database extracts data abstraction knowledge form an underlying database on the basis of a multilevel knowledge representation framework KAH. In cooperation with the underlying database, the meta-database supports four types of intelligent queries that provide approximately or conceptually equal answers as well as exact ones.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.55-64
• /
• 2018

In this paper, we propose fully convolutional neural networks based automatic detection of a pothole that directly causes driver's safety accidents and the vehicle damage. First, the training DB is collected through the camera installed in the vehicle while driving on the road, and the model is trained in the form of a semantic segmentation using the fully convolutional neural networks. In order to generate robust performance in a dark environment, we augmented the training DB according to brightness, and finally generated a total of 30,000 training images. In addition, a total of 450 evaluation DB was created to verify the performance of the proposed automatic pothole detection, and a total of four experts evaluated each image. As a result, the proposed pothole detection showed robust performance for missing.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.607-614
• /
• 2010

History centered knowledge based story-telling project planning tool supports the process of story creation in narrative genre about history of families or individuals. Narrative fields not only include drama, mythology, legend, history but also non-verbal epics such as movie, play, ballet and opera. But as verbal epic, this research paper focuses on the family history and individual history of each household. This story-telling planning tool redevelops each genre of story-telling about family history through sampleDB and informationDB, and it is widely applicable in concreting high quality stories in both its content and value. Reduces the time of planning story-telling, and impose minimum expenses in human resources. Content about family history is one of the most the fundamental and renowned contents in Story-telling but planning tool that is easily applicable in creating such content does not exist in statue quo. In this current system lacking creative infra, this research paper seeks to provide a planning tool that public can easily utilize, and by systemizing the tool. it aims to create a creative contents tool model applicable in variety of genres.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.423-430
• /
• 2013

The development of information technology introduced digital contents and Social Network Services(SNS), and allowed the virtual transaction and communication between users called "the experience knowledge" advanced from "the objective knowledge." This paper will analyze interactive storytelling system creating different types of stories on narrative genre about family history, personal history and so on. Through analysis on narrative interviews, direct observations, documentations and visual records, contents about CEO story, corporate story, family story and especially family history will be categorized into sampleDB and informationDB. Accumulated contents will allow the user to increase the value and usage of the contents through interactive storytelling system by restructuring the contents on family history. This research has developed writing tool data model using different digital contents such as texts, images and pictures to encourage open communications between first generations and third generations in Korea. Furthermore, researched about connected system on interactive storytelling creation device using various genre of family story that has been data based.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.372-377
• /
• 2006

In this paper, we propose sensibility recognition model that recognize user's sensibility using brain waves. Method to acquire quantitative data of brain waves including priority living body data or sensitivity data to recognize user's sensitivity need and pattern recognition techniques to examine closely present user's sensitivity state through next acquired brain waves becomes problem that is important. In this paper, we used pattern recognition techniques to use Multi Layer Perceptron (MLP) that is pattern recognition techniques that recognize user's sensibility state through brain waves. We measures several subject's emotion brain waves in specification space for an experiment of sensibility recognition model's which propose in this paper and we made a emotion DB by the meaning data that made of concentration or stability by the brain waves measured. The model recognizes new user's sensibility by the user's brain waves after study by sensibility recognition model which propose in this paper to emotion DB. Finally, we estimates the performance of sensibility recognition model which used brain waves as that measure the change of recognition rate by the number of subjects and a number of hidden nodes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.220-224
• /
• 2000

데이터 마이닝란 대량의 실제 데이터에서 묵시적이고 잠재적으로 유용한 정보를 추출하는 작업이다. 본 논문에서 서로 관계가 정의되지 않은 데이터베이스의 각 테이블간에서 필요한 정보를 추출 또는 가공하기 위해 데이터 마이닝 기법을 사용한다. 마이닝 기법인 연관 규칙은 어떤 사건이 일어나면 다른 사건이 일어나는 관련성을 의미하는 것이고, 제시된 규칙 기반의 데이터 마이닝 기법은 연관 규칙의 한 분야로서 데이터를 규칙 맞게 분류하는 기법이다. 이런 마이닝 기법을 구현하기 위해 인공지능 분야의 규칙 기반의 전문가 시스템을 사용하였고, 실 시스템인 GDS(Grating automatic Drawing System)에 적용하였다.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 1999.10c
• /
• pp.618-624
• /
• 1999

For many soft ground embankment projects , instrumentation programs for stability and settlement management is being essential . This usually leads to generate large volume of data, which can be used for further research. Database technique is most effective method for data management . Data produced by soft ground embankment instrumentation can not be used by itself but must be reproduced using geotechnical analysis technique. In this study, a intelligent database system for softground called IDSIM was developed to examine applicability intellgent database. . The IDSIM analysis instrumentation data automatically and present results by Web/DB interface successfully.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.316-318
• /
• 2000

데이터마이닝 기능은 문서의 구조화되지 않은 텍스트보다는 테이블과 일반적인 DB에 있는 구조화된 자료에 초점이 맞춰져 있다. 정보화의 과정속에서 많은 기업이나 조직들은 과거의 시스템을 DB로 구축하여 어느 정도 형태를 갖추게 되었지만, E-business, E-commerce가 활발해지면서 보유하고 있는 DB기반이 아닌 무작위의 새로운 데이터가 사용자들에 의해 생성되기도 한다. 본 논문에서는 이러한 텍스트 문서에 숨어있는 정보들을 발견하기 위한 텍스트마이닝 과정을 시나리오로 설정하고, 문서와 문서집합에 대해 분석도구를 적용하는 어플리케이션을 구현해 보았다. 대규모의 문서집합에 분석도구를 이용함으로써 빠른 문서처리가 가능하고 이는 사용자가 많은 양의 문서들을 다룰 때의 시간비용을 최소화시킬 수 있는 방법이 될 수 있다. 또한 마이닝과정을 통해 발견한 지식과 특징들을 기반으로 반구조화된 파일로 변환하여, 규칙발견, 데이터마이닝기법을 적용하여 의미있는 새로운 결론을 얻을 수 있을 것이다.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.161-171
• /
• 1999

Query language has been widely used as a convenient tool to obtain information from a database. However, users demand more intelligent query processing systems that can understand the intent of an imprecise query and provide additional useful information as well as exact answers. This paper introduces a meta-database and presents a query processing mechanism that supports a variety of intelligent queries in a consistent and integrated way. The meta-database extracts data abstraction knowledge from an underlying database on the basis of a multilevel knowledge representation framework KAH. In cooperation with the underlying database, the meta-database supports four types of intelligent queries that provide approximately or conceptually equal answers as well as exact ones.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.629-634
• /
• 2009

In real-time system application, the feature extraction and scoring algorithm for classification of the passive sonar target has the following problems: it requires an accurate and efficient feature extraction method because it is very difficult to distinguish the features of the propeller shaft rate (PSR) and the blade rate (BR) from the frequency spectrum in real-time, it requires a robust and effective feature scoring method because the classification database (DB) composed of extracted features is noised and incomplete, and further, it requires an easy design procedure in terms of structures and parameters. To solve these problems, an intelligent feature extraction and scoring algorithm using the evolution strategy (ES) and the fuzzy theory is proposed here. To verify the performance of the proposed algorithm, a passive sonar target classification is performed in real-time. Simulation results show that the proposed algorithm effectively solves sonar classification problems in real-time.