• 시스템엔지니어링학술지
• /
• 제13권2호
• /
• pp.49-56
• /
• 2017

Implementation of Model-based Systems Engineering(MBSE) depends on a model supporting efficient communication among engineers from various domains. And SysML is designed to create models supporting MBSE but unfortunately, SysML itself is not practical enough to be used in real-world engineering projects. SysML is designed to express generic systems and requires specialized knowledge, so a model written in SysML is less capable of supporting communication between a systems engineer and a sub-system engineer. Domain Specific Languages(DSL) can be a great solution to overcome the weakness of the standard SysML. A SysML based DSL means a customized SysML for a specific engineering domain. Unfortunately, current researches on SysML Domain Specific Language(DSL) for the plant engineering industry are still on the early stage. So as the first step, we have developed our own SysML based Piping & Instrumentation Diagram (P&ID) creation environment and P&ID itself of a specific plant system, using a widely used SysML authoring tool called MagicDraw. P&ID is one of the most critical output during the plant design phase, which contains all information required for the plant construction phase. So a SysML based P&ID has a great potential to enhance the communication among plant engineers of various disciplines.

• Journal of Information Processing Systems
• /
• 제3권2호
• /
• pp.73-81
• /
• 2007

In this paper, we introduce a domain-independent classification framework based on both k-nearest neighbor and Naive Bayesian classification algorithms. The architecture of our system is simple and modularized in that each sub-module of the system could be changed or improved efficiently. Moreover, it provides various feature selection mechanisms to be applied to optimize the general-purpose classifiers for a specific domain. As for the enhanced classification performance, our system provides conditional probability boosting (CPB) mechanism which could be used in various domains. In the mood classification domain, our optimized framework using the CPB algorithm showed 1% of improvement in precision and 2% in recall compared with the baseline.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2005년도 춘계학술발표대회
• /
• pp.651-654
• /
• 2005

Ontology developing process has aroused a lot of controversy among knowledge engineers and knowledge users. The recent surges on ontology building methodologies and practical ontology applications have explored a broad spectrum of knowledge management challenges. On the one hand, the abundant methodology theories provide us with a set of useful heuristic rules, from which we get the overview of ontology building process. But on the other hand, every research groups would like to justify their theories by listing their specific characteristics and unique method when approaching the right way. However, there is still no one “correct” way or methodology for developing ontologies. In this case, the methods used to evaluate only a subset of specific domain do not make any sense to the commonsense users. As a result, a comprehensive understanding of domain ontology is urgent and necessary.

• ETRI Journal
• /
• 제35권5호
• /
• pp.838-848
• /
• 2013

This paper presents a novel approach to automatically generate Korean multiword sentiment expressions by using a seed sentiment lexicon and a large-scale domain-specific corpus. A multiword sentiment expression consists of a seed sentiment word and its contextual words occurring adjacent to the seed word. The multiword sentiment expressions that are the focus of our study have a different polarity from that of the seed sentiment word. The automatically extracted multiword sentiment expressions show that 1) the contextual words should be defined as a part of a multiword sentiment expression in addition to their corresponding seed sentiment word, 2) the identified multiword sentiment expressions contain various indicators for polarity shift that have rarely been recognized before, and 3) the newly recognized shifters contribute to assigning a more accurate polarity value. The empirical result shows that the proposed approach achieves improved performance of the sentiment analysis system that uses an automatically generated lexicon.

• 인터넷정보학회논문지
• /
• 제7권4호
• /
• pp.67-77
• /
• 2006

기존의 도메인 지식 기반의 랩퍼 학습 방법은 도메인에 대한 정보를 바탕으로 해당 정보 소스에 대한 랩퍼를 생성한다. 용용 분야에 맞게 정의된 도메인 지식을 이용함으로써 정보 소스에서 제공하는 다양한 텍스트의 의미와 형태를 이해할 수 있다. 그러나 정보 소스에서 제공되는 모든 텍스트에 의미 인식의 근거가 되는 레이블이 붙어서 제공되는 것이 아니기 때문에 도메인 지식만을 이용해서 랩퍼를 학습하는 방법은 한계에 부딪힐 수밖에 없다. 이러한 문제를 해결하기 위해서 본 논문은 인터넷에 존재하는 다양한 웹 정보 소스에서 효율적이고 정확하게 랩퍼를 생성하는 도메인 지식 기반의 확률적 랩퍼 생성 시스템을 제안한다. 효율적이고 정확한 랩퍼 생성 시스템을 구축하기 위해서 도메인 지식뿐 아니라 상세 정보로 연결되어 있는 하이퍼링크와 엔티티 인식을 위한 확률 모델을 이용한다. 이와 같은 방법을 적용함으로써 사용자의 개입 없이 다양한 정보 소스에 대해서 보다 추출 성능이 좋은 랩퍼를 생성할 수 있다.

• 지능정보연구
• /
• 제28권4호
• /
• pp.251-273
• /
• 2022

최근 텍스트 분석을 딥러닝에 적용한 연구가 꾸준히 이어지고 있으며, 특히 대용량의 데이터 셋을 학습한 사전학습 언어모델을 통해 단어의 의미를 파악하여 요약, 감정 분류 등의 태스크를 수행하려는 연구가 활발히 이루어지고 있다. 하지만 기존 사전학습 언어모델이 특정 도메인을 잘 이해하지 못한다는 한계를 나타냄에 따라, 최근 특정 도메인에 특화된 언어모델을 만들고자 하는 방향으로 연구의 흐름이 옮겨가고 있는 추세이다. 도메인 특화 추가 사전학습 언어모델은 특정 도메인의 지식을 모델이 더 잘 이해할 수 있게 하여, 해당 분야의 다양한 태스크에서 성능 향상을 가져왔다. 하지만 도메인 특화 추가 사전학습은 해당 도메인의 말뭉치 데이터를 확보하기 위해 많은 비용이 소요될 뿐 아니라, 고성능 컴퓨팅 자원과 개발 인력 등의 측면에서도 많은 비용과 시간이 투입되어야 한다는 부담이 있다. 아울러 일부 도메인에서 추가 사전학습 후의 성능 개선이 미미하다는 사례가 보고됨에 따라, 성능 개선 여부가 확실하지 않은 상태에서 도메인 특화 추가 사전학습 모델의 개발에 막대한 비용을 투입해야 하는지 여부에 대해 판단이 어려운 상황이다. 이러한 상황에도 불구하고 최근 각 도메인의 성능 개선 자체에 초점을 둔 추가 사전학습 연구는 다양한 분야에서 수행되고 있지만, 추가 사전학습을 통한 성능 개선에 영향을 미치는 도메인의 특성을 규명하기 위한 연구는 거의 이루어지지 않고 있다. 본 논문에서는 이러한 한계를 극복하기 위해, 실제로 추가 사전학습을 수행하기 전에 추가 사전학습을 통한 해당 도메인의 성능 개선 정도를 선제적으로 확인할 수 있는 방안을 제시한다. 구체적으로 3개의 도메인을 분석 대상 도메인으로 선정한 후, 각 도메인에서의 추가 사전학습을 통한 분류 정확도 상승 폭을 측정한다. 또한 각 도메인에서 사용된 주요 단어들의 정규화된 빈도를 기반으로 해당 도메인의 특수성을 측정하는 지표를 새롭게 개발하여 제시한다. 사전학습 언어모델과 3개 도메인의 도메인 특화 사전학습 언어모델을 사용한 분류 태스크 실험을 통해, 도메인 특수성 지표가 높을수록 추가 사전학습을 통한 성능 개선 폭이 높음을 확인하였다.

• Journal of Communications and Networks
• /
• 제8권1호
• /
• pp.106-115
• /
• 2006

The current trend toward the utilization of the Internet as a common means for the offer of heterogeneous services imposes to address the issues related to end-to-end service assurance in the inter-domain scenario. In this paper, we first present an architecture for service management in networks based on service level specifications (SLS). The architecture is designed to be independent both of the specific network technology adopted and of the high level service semantics. Then, we focus on a specific functionality of the proposed architecture: Resource allocation in the multi-domain scenario. A distributed admission control algorithm is introduced, its complexity is evaluated and a comparison with related solutions is provided.

• 한국정밀공학회지
• /
• 제24권11호
• /
• pp.126-133
• /
• 2007

Tuberculosis (TB) is a chronic or acute infectious disease which damages more people than any other infectious diseases according to WHO estimates. In this paper, a new automatic detection system of tuberculosis bacilli by using their color information is proposed. Through the deep investigation of color and intensity compositions of tuberculosis images, new pre-processing and segmentation algorithms are suggested. Specific features of bacilli are extracted from the processed images and number counting is done by using domain-specific knowledge rules.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.121-130
• /
• 1999

The objective of this paper is to apply Extended AND-OR Graph (EAOG)-related techniques to extract knowledge from a specific problem-domain and perform analysis in complicated decision making area. Expert systems use expertise about a specific domain as their primary source of solving problems belonging to that domain. However, such expertise is complicated as well as uncertain, because most knowledge is expressed in causal relationships between concepts or variables. Therefore, if expert systems can be used effectively to provide more intelligent support for decision making in complicated specific problems, it should be equipped with real-time inference mechanism. We develop two kinds of EAOG-driven inference mechanisms(1) EAOG-based forward chaining and (2) EAOG-based backward chaining. and The EAOG method processes the following three characteristics. 1. Real-time inference : The EAOG inference mechanism is suitable for the real-time inference because its computational mechanism is based on matrix computation. 2. Matrix operation : All the subjective knowledge is delineated in a matrix form, so that inference process can proceed based on the matrix operation which is computationally efficient. 3. Bi-directional inference : Traditional inference method of expert systems is based on either forward chaining or backward chaining which is mutually exclusive in terms of logical process and computational efficiency. However, the proposed EAOG inference mechanism is generically bi-directional without loss of both speed and efficiency.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2002년도 Language, Information, and Computation Proceedings of The 16th Pacific Asia Conference
• /
• pp.465-474
• /
• 2002

Korean government has adopted the French TGV as a high-speed transportation system and the first service is scheduled at the end of 2003. TGV-relevant documents are consisted of huge volumes, of which over than 76% has been translated in English. A large part of the English version is, however, incomprehensible without referring to the original French version. The goal of this paper is to demonstrate how DiET 2.5, a lexicon builder, makes it possible to build with ease domain-specific terminology lexicon that may contain multimedia and multilingual data with multi-layered logical information. We believe our wok shows an important step in enlarging the language scope and the development of electronic lexica, and in providing the flexibility of defining any type of the DTD and the interconnectivity among collaborators. As an application of DiET 2.5, we would like to build a TGV-relevant lexicon in the near future.