• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.325-330
• /
• 2008

전자우편(email)은 인터넷의 급격한 보급으로 인하여 사용자들이 많이 사용하게 된 통신 메커니즘이다. 그러나 이러한 전자우편의 대중성을 상업적인 목적으로 이용한 스팸메일의 출현으로, 사용자들은 정신적 피해, 업무 방해, 메일서버의 트래픽 과부화로 인한 유지보수 비용 증가와 같은 문제점들을 접하게 되었다. 특히, 최근에는 광고성 이미지들을 첨부하는 등의 새로운 기법이 적용된 스팸메일의 발생으로 기존의 텍스트 기반의 스팸메일 필터링 기법들이 무의미하게 되었으며, 따라서 그로 인한 피해가 증가하는 추세이다. 이러한 이미지 기반의 스팸메일들의 필터링을 위하여 Support Vector Machine과 같은 기계학습 기법을 이용한 기법들이 제안되고 있으나, 여전히 그 성능은 만족스럽지 못하다. 본 논문은 전자우편으로부터 텍스트 및 시각적 의미를 분석하여 전자우편 온톨로지에 기술하고 스팸메일 판단을 위한 의미추론규칙을 적용함으로써 광고성 이미지가 첨부되어 있는 스팸메일을 효과적으로 필터링 하기 위한 시스템을 제안한다.

• Journal of the Korean Society for information Management
• /
• v.20 no.1
• /
• pp.341-371
• /
• 2003

The purpose of the study is to design the ontology-based Prescription Knowledge Management System of Oriental Medicine. The study was done with the premise that the effectiveness of the system can be improved by using ontological abstractional structure based on definition of concept, attribution and relations of words related to the specific area. The system is developed with Protege-2000 by using newly developed KPML(Korean Medicine Prescription Markup Language). The results of the study provide the model of Prescription Knowledge Management System and the possibility of implementing XML-based ontology system to the semantic web environment.

• Journal of Korean Society for Quality Management
• /
• v.44 no.4
• /
• pp.735-749
• /
• 2016

Purpose: This study is addressing the establishment of the knowledge information system supplying the quality management of weapon system. It is going to support the continuous quality management through the linkages and integration between the product structure and the quality information. Methods: The interrelated relationship of the product structure information and quality information of weapon system would be expressed explicitly by taking advantage of the ontology concept. The quality information of distributed systems would be integrated through the SOA(Service Oriented Architecture)-based Web services. After defining the inference rules, which could be utilized in the quality management, in the constructed knowledge information system, the quality information would be inferred through the queries. Results: By building the integrated quality information knowledge system through the ontology and SOA, the connectivity between the product structures and dispersed quality information was enhanced. The utility and applicability of this study were checked up through the inferences on the products and quality information by using the information built by the semantic relationship of facts. Conclusion: We established the knowledge and information system as a systematic approach to support the quality management of weapon system. This is not affected by the organizations and systems, and it seems that it could be utilized across the quality management as the efficient knowledge sharing architecture supporting the quality management of weapon systems in the aspect of the product integration.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.185-193
• /
• 2008

In spite of rapid development of IT-related meteorology and services, human users still ought to check the weather information manually as they did before because traditional weather information retrieval is based on pull-type and human interpretation. Furthermore, the automatic machine-driven weather information processing has been neglected for a long time although the intelligent weather information processing is expected to be very useful for personal daily life and ubiquitous computing. In this paper, we discussed a design of GRIB based ontology to enable smart weather information processing. GRIB is the general purposed and world-wildly used weather data format approved by the World Meteorological Organization. With the designed ontology and the inference system containing Jess engine, several intelligent weather applications have been implemented and tested to verify the virtue of machine-driven weather information processing.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.505-511
• /
• 2003

Production rule based knowledge representation method has many advantages, but has the difficulties in maintaining the consistency of knowledge. Since the consistency maintenance of knowledge exercises a marked effect on the reliability of inference results, the system for consistency maintenance of knowledge is indispensable to increase the reliability. In the most popular pairwise checking method among consistency verification methods, the valuable rules can be omitted and it takes much time in checking the consistency when the rules are numerous. So, this paper is to propose and implement the verification system which can remove the structural errors and semantic ones, making up for the defects of pairwise checking method by using the certain property list and eventual property list and improving the steps of verification.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.13-15
• /
• 2006

과학기술 연구분야에서 인력, 기관 등의 연구 주체와 논문, 과제, 지적재산권 등의 성과에 대한 온톨로지는, 시맨틱 웹 환경에서 이질적 과학기술 연구정보의 의미적 통합과 자동화된 유통, 그리고 암묵적 지식의 추론을 가능케 할 것이다. 이 논문에서는 현재 한국과학기술정보연구원에서 개발 중인 국가과학기술 R&D 기반정보 은톨로지를 소개하고, 그의 응용으로써 은톨로지에 내재된 암묵적 지식들을 규칙을 사용하여 추론하는 과정의 기술에 중점을 둔다. 상기 은톨로지는 인스턴스의 유일성 확보를 위해 URI(Uniform Resource identifier)서버에 기반하여 온톨로지 인스턴스에 고유한 URI를 할당하는 데 중점을 두고 설계되었으며, 논문의 특정순위저자를 모델링한 저작자정보 클래스를 은톨로지 스키마 상에 명시적으로 표현한다는 특징이 있다.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.466-475
• /
• 2009

Considerable research in the field of ontology mapping has been done when information sharing and reuse becomes necessary by a variety of ontology development. Ontology mapping method consists of the lexical, structural, instance, and logical inference similarity computing. Lexical similarity computing used in most ontology mapping methods performs an ontology mapping by using the synonym set defined in the WordNet. In this paper, we define the Super Word Set including the hypenym, hyponym, holonym, and meronym set and propose an ontology mapping method using the Super Word Set. The results of experiments show that our method improves the performance by up to 12%, compared with previous ontology mapping method.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.43-54
• /
• 2019

Currently, a majority of artificial intelligence is used to secure big data; however, it is concentrated in a few of major companies. Therefore, automatic data augmentation and efficient learning algorithms for small-scale data will become key elements in future artificial intelligence competitiveness. In addition, it is necessary to develop a technique to learn meanings, correlations, and time-related associations of complex modal knowledge similar to that in humans and expand and transfer semantic prediction/knowledge inference about unknown data. To this end, a neural memory model, which imitates how knowledge in the human brain is processed, needs to be developed to enable knowledge expansion through modality cooperative learning. Moreover, declarative and procedural knowledge in the memory model must also be self-developed through human interaction. In this paper, we reviewed this essential methodology and briefly described achievements that have been made so far.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.30-33
• /
• 2023

The recent scholarly focus has been directed towards the expeditious and accurate detection of salient objects, a task that poses considerable challenges for resource-limited edge devices due to the high computational demands of existing models. To mitigate this issue, some contemporary research has favored inference speed at the expense of accuracy. In an effort to reconcile the intrinsic trade-off between accuracy and computational efficiency, we present novel model for salient object detection. Our model incorporate group-wise attentive module within the decoder of the encoder-decoder framework, with the aim of minimizing computational overhead while preserving detection accuracy. Additionally, the proposed architectural design employs attention mechanisms to generate boundary information and semantic features pertinent to the salient objects. Through various experimentation across five distinct datasets, we have empirically substantiated that our proposed models achieve performance metrics comparable to those of computationally intensive state-of-the-art models, yet with a marked reduction in computational complexity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.463-466
• /
• 2007

현재 웹 서비스에서 주로 사용하고 있는 키워드 기반 검색은 사용자의 의도와는 상관없는 정보까지 검색하는 경우가 많아서, 실제로 원하는 정보를 찾는데 많은 시간과 노력을 요구한다는 단점이 있다. 이러한 단점을 보완하기 위해서 최근 시맨틱 웹이라는 개념이 등장하였으며, 본 논문에서는 검색 결과의 신뢰성을 향상시키기 위해 온톨로지를 기반으로 시맨틱 검색시스템을 설계하였다. 본 논문에서 설계한 온톨로지 기반의 시맨틱 검색 시스템은 기능적으로 크게 두 부분으로 구성되어 있다. 즉, 자료 수집을 하는 로봇 에이전트와 온톨로지를 기반으로 자료를 검색하는 시맨틱 검색 엔진으로 구성된다. 로봇 에이전트는 자율적으로 웹을 순회하면서 자료를 수집하고 필터링하여 메타데이터 저장소로 가져오는 역할을 한다. 시맨틱 검색 엔진은 사용자의 검색 폼으로부터 전달된 정보 검색 요구사항을 기초로 시맨틱 질의어로 변환한 후, 온톨로지 저장소를 활용하여 검색한다. 시맨틱 검색 엔진은 사용자가 입력한 검색어를 시맨틱 질의어로 변환해 주는 질의처리 모듈과 사용자의 의도를 추론하여 보다 향상된 검색을 가능하게 해주는 추론(Inference) 모듈, 온톨로지를 보관해주는 온톨로지 저장소 등으로 구성된다. 본 논문에서 설계한 온톨로지 기반의 시맨틱 검색 시스템은 키워드 기반 검색에 비해 사용자가 원하는 정보를 찾는데 소요되는 시간과 노력을 줄여 주고, 사용자의 의도에 적합한 정보를 제공할 것으로 기대된다.