• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.81-86
• /
• 2002

In current CBR(Case-Based Reasoning) systems, the case adaptation is usually performed by rule-based method that use rules hand-coded by the system developer. So, CBR system designer faces knowledge acquisition bottleneck similar to those found in traditional expert system design. In this thesis, 1 present a model for learning method of case adaptation knowledge using case base. The feature difference of each pair of cases are noted and become the antecedent part of an adaptation rule, the differences between the solutions in the compared cases become the consequent part of the rule. However, the number of rules that can possibly be discovered using a learning algorithm is enormous. The first method for finding cases to compare uses a syntactic measure of the distance between cases. The threshold fur identification of candidates for comparison is fixed th the maximum number of differences between the target and retrived case from all retrievals. The second method is to use similarity metric since the threshold method may not be an accurate measure. I suggest the elimination method of duplicate rules. In the elimination process, a confidence value is assigned to each rule based on its frequency. The learned adaptation rules is applied in riven target Problem. The basic. process involves search for all rules that handle at least one difference followed by a combination process in which complete solutions are built.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.93-102
• /
• 2020

In order for data obtained through all stages of digital crime investigation to be recognized as evidence capability, it must satisfy legal / technical requirements. In this paper, we propose a mechanism and implement software to provide digital forensic evidence by automatically recovering files by scanning / inspecting the unallocated area inside the storage disk block without relying on information provided by the file system. The proposed technique checks / analyzes the RAW disk data of the system under analysis in 512-byte block units based on information on the storage format / file structure of various files stored on the disk without referring to the file system-related information provided by the operating system. The file carving process was implemented, and a smart carving mechanism was proposed to intelligently restore deleted or damaged files in the storage device. As a result, we have provided a block based smart carving method to intelligently identify fragmented and damaged files in storage efficiently for forgery analysis on digital forensic investigation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.2
• /
• pp.149-156
• /
• 2008

In this paper, we propose a method aiming at updating the building information of the digital maps using single high resolution satellite image and digital map. Firstly we produced a digital orthoimage through the automatic co-registration of QuickBird image and 1:1,000 digital map. Secondly we extracted building height information through the template matching of digital map's building vector data and the image's edges obtained by Canny operator. Finally we refined the shape of some buildings by using the result from template matching as the seed polygon of the greedy snake algorithm. In order to evaluate the proposed method's effectiveness, we estimated accuracy of the extracted building information using LiDAR DSM and 1:1,000 digital map. The evaluation results showed the proposed method has a good potential for extraction and revision of building information.

• The Journal of the Korea Contents Association
• /
• v.6 no.9
• /
• pp.152-163
• /
• 2006

The development of Semantic Web basically requires knowledge induced from the formalization and semantization of information, and thus ontology should be introduced as a knowledgization tool. URI(Universal Resource Identifier) is an indispensible scheme to uniquely indicate individuals on ontology. However, it is difficult to find the use cases of URI in real data including science and technology papers. This paper describes the method to construct internal and external human resource information based on URI from the papers. We use co-authors, e-mails, publication date, and affiliation for discriminating authors with the same strings. HRST(Human Resources devoted to Science and Technology) is referred to acquire URIs for human resource. We expect the internal and external human resource information would be adopted to outcome analysis applications such as researcher network analysis and outcome statistics.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.393-398
• /
• 2010

Composite and compact devices equipped with the functionality of digital still image acquisition, such as cellular phones and MP3 players are widely available to common users. In addition, the application of digital still images is becoming common among security and digital recording devices. The amount of still images, that are maintained or shared in personal storage or massive storage provided by various web services, are rapidly increasing. These still images are bound with file names or identifiers that are provided arbitrarily by users or that are generated from device specific naming method. However, those identifiers are vulnerable for unexpected changing or eliminating so that it becomes a problem in still image search or management. In this paper, we propose a method for still image identifier generation that is created from the still image internal information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.573-576
• /
• 2017

본 연구는 홍삼 등급판정 과정에서 내부 조직 치밀도 분석을 위해 의료 영상 분석 방법을 이용하여 적외선 영상 측정기기를 개발하였다. 기존 홍삼 내부분석방법은 수동으로 암실환경에서 강한 조명을 홍삼에 투과하여 사람 눈으로 직접 판별하는 과정을 거친다. 이러한 기존 검사 과정은 작업 비효율성과 불균일한 검사기준으로 제품 품질 신뢰도 저하의 단점을 가져온다. 이러한 문제점을 해결하기 위해 본 연구는 적외선 조명환경에서 자동 측정이 가능한 홍삼 내부 측정기기를 개발하였다. 개발된 장치는 홍삼의 빛 투과 특성을 응용한 920nm 파장대역의 적외선 조명기구, 조명 제어회로, 적외선 대역 촬영이 가능한 영상 측정 카메라 장치, $0.9^{\circ}$의 간격으로 $360^{\circ}$ 홍삼 영상취득이 가능한 회전 엑츄에이터로 구성이 된다. 본 연구에서 제안 하는 홍삼 단층 영상분석 방법은, 홍삼을 $0.9^{\circ}$ 간격으로 회전시키어 $360^{\circ}$ 홍삼 내부영상을 취득하여 라돈 변환(Radon transform)을 통해 사이노그램(Sinogram)으로 재구성 하였으며, 역 라돈 변환(Inverse Radon transform)을 통해 단층 영상복원(Back-projection)알고리즘을 구현하였다. 이 결과 홍삼을 절단하지 않고 홍삼 내부 단면영상 획득이 가능하였으며 내공(內空), 내백(內白)의 유무를 판단하고 직경을 파악할 수 있었다. 이를 토대로 등급 판별 공식을 산출하면 신뢰성 있는 홍삼 등급 자동화 측정기기를 개발할 수 있을 것으로 기대된다.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.426-429
• /
• 2007

CrossRef operates a cross-publisher citation linking system based on the DOI(R) global identifier. The number of organization building a reference citations linking structure through CrossRef is increasing. This paper concentrates on developing a Citation Matcher Solution to effectively build the reference linking structure. Citation Matcher automatically builds and processes the reference citation and identifier mapping which used to be handled manually. After the copy & paste of the reference citation, analyzation is processed to parse the journal title, author name, volume, issue, and start pages from the free style text. CrossRef, PubMed, and YesKISTI's identifiers are collected by through a standardized method. Renovation of the building process for domestic scholastic resources' reference linking and matching will be made possible by using a Citation Matcher. The connection between resources and seamless access for the electronic full-text will enhance the usability.

• Journal of Advanced Navigation Technology
• /
• v.5 no.2
• /
• pp.123-133
• /
• 2001

The existing visualization methods using the satellite images or map images require complicated preprocessing stages and a large amount of visual data to represent the 3-D terrain. This paper presents a 3-D visualization method for geographical information, which enables automatic generation of 3-D terrain. It is generated based, on contour information obtained from a numerical map. This paper also introduces a method that resolves the three main problems needed to visualize 3-D terrain from contour lines such as correspondence, tiling, and branching. The virtual contour line is defined to extend a distorted contour line to have a similar shape to the corresponding contour line that is used, to generate 3-D surfaces. It helps that 3-D terrain is represented exactly and in detail.

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.755-765
• /
• 2002

In this paper, we observe various syntactic information for Korean parsing and propose a method to learn constraints and improve the efficiency of a parsing model by using the constraints. The proposed method has the following three characteristics. First, it improves the parsing efficiency since we use constraints that can prevent the parser from generating unsuitable candidates. Second, it is robust on a given Korean sentence because the attributes for the constraints are selected based on the syntactic and lexical idiosyncrasy of Korean. Third, it is easy to acquire constraints automatically from a treebank by using a decision tree learning algorithm. The experimental results show that the parser using acquired constraints can reduce the number of overgenerated candidates up to 1/2~1/3 of candidates and it runs 2~3 times faster than the one without any constraints.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.3
• /
• pp.227-240
• /
• 2003

When we develop and use the java-based distributed object system, the system developer must deploy distributed object, which is implemented to predefined interface, to network and the system user acquires reference about distributed object and changes reference to interface type. Sharing of interface is essential for these works In this paper, we propose the IRSJ(interface repository service based on jim) to improve efficiency of interface sharing at the JINI system development. the IRSJ is consisted of the java classes for JINI system and interface sharing service. If development teams perform collaborative work in short distance, the IRSJ can search interface file without information of lookup server or interface writer If development teams perform collaborative work in long distance, the IRJS can search interface with only an address of server that executes lookup service. Although the interface object not requires additional search, the interface object that failed search interface can download interface and use interface using remote event model. When the message service fails in interface search, the message service sends interface request message to a development team member who use the IRSJ automatically, so that interface sharing may be possible in short time.