• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1082-1087
• /
• 1994

A set of text database is indispensable to the probabilistic models for speech recognition, linguistic model, and machine translation. We introduce an environment to canstruct text databases : an automatic tagging system and a set of tools for lexical knowledge acquisition, which provides the facilities of automatic part of speech recognition and guessing.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.13-15
• /
• 2021

텍스트에 나타나는 감성을 분석하는 NLP task 중 하나인 감성분석에 자주 사용되는 한국어와 외국어 데이터들에 대해 다양한 BERT 모델들을 적용한 결과를 고성능 순서로 정리한 사이트(Paper with code)와 Github를 통해 준수한 성능을 보이는 BERT 모델들을 분석하고 실행해보며 성능향상을 통한 차별성을 가지는 것이 목표이다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.101-107
• /
• 2022

Modeling and simulation is a technique used for operational verification, performance analysis, operational optimization, and prediction of target systems. Discrete Event System Specification (DEVS) of this representative technology defines models with a strict formalism and stratifies the structures between the models. When the atomic DEVS models operate with an intention different the target system, the simulation may lead to erroneous decision-making. However, most DEVS systems have the exclusion of the model test or provision of the manual test, so developers spend a lot of time verifying the atomic models. In this paper, we propose a script-based automated test system for accurate and fast validation of atomic models in Python-based DEVS. The proposed system uses both the existing method of manual testing and the new method of the script-based testing. As Experimental results in our system, the script-based test method was executed within 24 millisecond when the script was executed 10 times consecutively. Thus, the proposed system guarantees a fast verification time of the atomic models in our script-based test and improves the reusability of the test script.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.43-50
• /
• 2024

This paper evaluates the Korean sentiment analysis performance of large language models like GPT-3.5 and GPT-4 using a zero-shot approach facilitated by the ChatGPT API, comparing them to pre-trained Korean models such as KoBERT. Through experiments utilizing various Korean sentiment analysis datasets in fields like movies, gaming, and shopping, the efficiency of these models is validated. The results reveal that the LMKor-ELECTRA model displayed the highest performance based on F1-score, while GPT-4 particularly achieved high accuracy and F1-scores in movie and shopping datasets. This indicates that large language models can perform effectively in Korean sentiment analysis without prior training on specific datasets, suggesting their potential in zero-shot learning. However, relatively lower performance in some datasets highlights the limitations of the zero-shot based methodology. This study explores the feasibility of using large language models for Korean sentiment analysis, providing significant implications for future research in this area.

• The Journal of Society for e-Business Studies
• /
• v.1 no.2
• /
• pp.117-131
• /
• 1996

This paper presents the results of the systems analysis for the FCIM (Flexible Computer Integrated Manufacturing) system at the U.S. Tobyhanna Army Repair Depot, which is one of the RAMP (Rapid Acquisition of Manufactured Part) program sites for CALS implementation in the U.S. military. The FCIM system's acquisition and supply processes are represented by IDEFO function models and FCIM information systems are briefly decribed in this paper. The models presented here can be used at a reference for the development of CALS acquisition and supply systems. In addition. the distinction between input and control information on the IDEFO model it suggested from the practical modeling viewpoint.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.754-759
• /
• 1993

An adaptive model predictive control (AMPC) strategy using auto-regression moving-average (ARMA) models is presented. The characteristic features of this methodology are the small computer memory requirement, high computational speed, robustness, and easy handling of nonlinear and time varying MIMO systems. Since the process dynamic behaviors are expressed by ARMA models, the model parameter adaptation is simple and fast to converge. The recursive least square (RLS) method with exponential forgetting is used to trace the process model parameters assuming the process is slowly time varying. The control performance of the AMPC is verified by both comparative simulation and experimental studies on distillation column control.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.515-524
• /
• 2007

This paper deals with local linear estimation of fuzzy regression models based on Diamond(1998) as a new class of non-linear fuzzy regression. The purpose of this paper is to introduce a use of smoothing in testing for lack of fit of parametric fuzzy regression models.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.109-112
• /
• 2000

Many applications in computer graphics require highly detailed complex models. However, the level of detail may vary considerably according to applications. It is often desirable to use approximations in place of excessively detailed models. We have developed a surface simplification algorithm which uses iterative contractions of edges to simplify models and maintains surface error approximations using a quadric metric. In this paper, we present an improved quadric error metric for simplifying meshes. The new metric, based on subdivided edge classification, results in more accurate simplified meshes. We show that a subdivided edge classification captures discontinuities efficiently. The new scheme is demonstrated on a variety of meshes.

• Journal of the Korea Society for Simulation
• /
• v.6 no.1
• /
• pp.61-69
• /
• 1997

In 3D computer graphics, fractal techniques have been applied to terrain models. Even though fractal models are convenient way to get the data of terrain models, it is not easy to gain the final results by manipulating the data of terrain model. However, by using the object oriented programming techniques, we could reduce the effort of programming job to find the final result. In this paper, a set of classes made by object oriented programming technique is presented. To show the results, the data of a terrain model were made by a fractal technique, namely, the midpoint displacement methods with square lattices of points.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.2965-2980
• /
• 1999

There are several models and the corresponding diagrams to express software system in many kinds of viewpoints, but these are supposed to be integrated and implemented into only one system. Therefore, the software modelers should have the models ensuring the consistency between information in software development life cycle. To support the robust models for modelers using OO modeling methods, i.e. UML, and CASE tools, the meta models of the software architecture and the consistency rules between the models are suggested in this thesis. Finally, the rules are implemented in the OO CASE tool, DEBUTO(Design By UML Tool). It supports UML1.1 notations and has visual modeling editors that enable users make their own software model.