• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.06a
• /
• pp.48-67
• /
• 2002

This paper is a report on part of the results of a research project entitled "Research and Model Development for a Multi-Lingual Lexical Database". It Is a six-year project in which we aim to construct a model of a multilingual lexical database of Korean, Chinese, Japanese, and English. Now we have finished the first two-year stage of the project In this paper, we present the goal of the project, the construction model of items in the lexical database, and the possible (semi-)automatic methods of acquisition of lexical information. As an appendix, we present some sample items of the database as an i1lustration.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.3-12
• /
• 2007

Coverage has been a constant thorn in the side of deployed deep linguistic processing applications, largely because of the difficulty in constructing, maintaining and domaintuning the complex lexicons that they rely on. This paper reviews various strands of research on deep lexical acquisition (DLA), i.e. the (semi-)automatic creation of linguistically-rich language resources, particularly from the viewpoint of DLA for precision grammars.

• Korean Journal of Radiology
• /
• v.22 no.10
• /
• pp.1597-1608
• /
• 2021

Cardiovascular computed tomography (CT) is among the most active fields with ongoing technical innovation related to image acquisition and analysis. Artificial intelligence can be incorporated into various clinical applications of cardiovascular CT, including imaging of the heart valves and coronary arteries, as well as imaging to evaluate myocardial function and congenital heart disease. This review summarizes the latest research on the application of deep learning to cardiovascular CT. The areas covered range from image quality improvement to automatic analysis of CT images, including methods such as calcium scoring, image segmentation, and coronary artery evaluation.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1993.10a
• /
• pp.11-11
• /
• 1993

도메인에 대한 전문 지식 획득(Acquisition of expert knowlegde)은 지식 제공자인 인간 전문가에 의존한다. 도메인이 복잡해 질수록 인간 전문가로부터 관련된 모든 지식을 획득하기란 어렵다. 이런 지식 획득의 어려움을 부분 흑은 완전 자동화된 지식 획득 시스템을 통해 해결하려는 많은 연구가 있어 왔다. 그러나 지식 획득을 위한 여러 시도들은 지식 제공자의 촛점이 도메인이 아닌 표현 구조나 도구- representation environment -에 보다 치우치게 하여, 잘못된 지식을 획득하게 하거나 주요지식이 생략되는 경우를 보이기도 한다. 또한 정적인 관계(relationship)에 의해서만 지식(Static Knowledge)을 생성하므로 시간흐름에 따라변화하는 지식을 나타내기는 어렵다. 본 연구에서는 시뮬레이션을 통한 자동 지식 획득(Simulation Based automatic Knowledge Acquisition) 방법을 제시한다. 이 방법은 1) 도메인에 관한 초기 인과관계 정보를 입력 받고, 2) 입력된 정보를 일정한 프레임에 따라 구조화 시켜 경험 베이스를 구성하고 이를 탐색하여 도메인과 관련된 확장된 정보를 얻은 후, 3) 위의1),2)를 통해 얻어진 정보를 분석하여 주어지는 입력에 대해 다양한 출력을 낼 수 있는 시뮬레이션 모델을 생성한다. 이 모델은 다음 단계의 지식 생성을 위한 수단(resource)이 되며, 구간값과 같은 불확실한 정보를 포함할 수 있는 구조이다. 마지막으로 4) 생성된 모델을 시뮬레이션하여 결과로 생성된 지식을 획득한다. 위의 과정에서, 지식획득을 위한 수단인 시뮬레이션 모델이 지식 제공자의 개입 없이 자동 생성됨에 따라, 지식 제공자는 도메인 관련 지식 그 자체에 집중할 수 있으며, 생성된 모델을 시뮬레이션한 결과에 의해 지식을 생성함으로써 동적인 지식이 얻어질 수 있다. DEVS 모델에 대한 타당성 검사 방법을 고찰하고 그 문제점에 대하여 자세히 설명한다. DEVS 모델의 타당성 검사에 이용하는 SPN 모델에 대한 개념과 DEVS 모델과 행위적으로 동등한 SNP 모델로 변환을 위한 관점을 제조명하다. 동일한 관점에서 두 모델의 상태표현이 같도록 DEVS 모델이 SPN 모델로 표현됨을 보이는 변환이론을 제시하고 변환이론을 바탕으로 모델 변환과정을 제시한다. 모델 변환이론과 변환고정을 기본으로 타당성 검사를 위한 새로운 동질함수(homogeneous function)를 정의하고 이와 함께 SPN 모델의 특성을 이용하여 DEVS 모델에 대한 타당성 검사 방법을 새롭게 제안한다. 에탄올투여로 증가된 유리기 해독계 효소인 GSH-Px활성을 큰 폭으로 감소시키고 에탄올투여로 감소된 비효소적 항산화작용을 나타내는 GSH함량을 다량 증가시킴으로서 지질과산화물에 대한 방어력이 증가되어 나타난 결과로 여겨지며, 또한 혈청중의 ALT, ALP 및 LDH활성을 유의성있게 감소시키므로서 감잎 phenolic compounds가 에탄올에 의한 간세포 손상에 대한 해독 및 보호작용이 있는 것으로 사료된다.반적으로 홍삼 제조시 내공의 발생은 제조공정에서 나타나는 경우가 많으며, 내백의 경우는 홍삼으로 가공되면서 발생하는 경우가 있고, 인삼이 성장될 때 부분적인 영양상태의 불충분이나 기후 등에 따른 영향을 받을 수 있기 때문에 앞으로 이에 대한 많은 연구가 이루어져야할 것으로 판단된다.태에도 불구하고 [-wh]의미의 겹의문사는 병렬적 관계의 합성어가 아니라 내부구조를 지니지 않은 단순한 단어(minimal $X^{0}$ elements)로 가정한다. 즉, [+wh] 의미의 겹의문사는 동일한 구성요 소를 지닌 병렬적 합성어([$[W1]_{XO-}$ $[W1]_{XO}$ ]$

• Journal of Intelligence and Information Systems
• /
• v.9 no.2
• /
• pp.19-38
• /
• 2003

In this research, we propose the mechanism to develop self-evolving expert systems (SEES) based on data mining (DM), fuzzy neural networks (FNN), and relational database (RDB)-driven forward/backward inference engine. Most researchers had tried to develop a text-oriented knowledge base (KB) and inference engine (IE). However, this approach had some limitations such as 1) automatic rule extraction, 2) manipulation of ambiguousness in knowledge, 3) expandability of knowledge base, and 4) speed of inference. To overcome these limitations, knowledge engineers had tried to develop an automatic knowledge extraction mechanism. As a result, the adaptability of the expert systems was improved. Nonetheless, they didn't suggest a hybrid and generalized solution to develop self-evolving expert systems. To this purpose, we propose an automatic knowledge acquisition and composite inference mechanism based on DM, FNN, and RDB-driven inference engine. Our proposed mechanism has five advantages. First, it can extract and reduce the specific domain knowledge from incomplete database by using data mining technology. Second, our proposed mechanism can manipulate the ambiguousness in knowledge by using fuzzy membership functions. Third, it can construct the relational knowledge base and expand the knowledge base unlimitedly with RDBMS (relational database management systems) module. Fourth, our proposed hybrid data mining mechanism can reflect both association rule-based logical inference and complicate fuzzy relationships. Fifth, RDB-driven forward and backward inference time is shorter than the traditional text-oriented inference time.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.67.3-68
• /
• 2018

We plan to automatize the operation of Kyung Hee Astronomical Observatory (KHAO) 76 cm Telescope by adapting KAOS30 (KHU Automatic Observing Software for McDonald 30 inch Telescope). The software is developed to improve the efficiency of the observation system for monitoring transients and variable sources. It has installed and operated at McDonald 30 inch telescope since 2017 August. KAOS76 (KHU Automatic Observing Software for KHAO 76 cm Telescope) consists of four packages: Telescope Control Package (TCP), Data Acquisition Package (DAP), Auto Focus Package (AFP), and Script Mode Package (SMP). Most of the packages can be configured by minimized modifications of the codes because it includes common libraries for FLI instruments and also ASCOM standard. TCP, DAP, and AFP control astronomical devices. SMP supports automatic observing in a script mode. TCP of KAOS76 can communicate with the TCS via ASCOM. Also, KAOS76 has an extra function to compensate the misalignment of the polar axis. In this poster, we show the current status of the observing system with KAOS76.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.10
• /
• pp.15-21
• /
• 2015

In this paper, we propose a stable automatic signature verification algorithm applicable to various smart devices. The proposed algorithm uses real and forgery data all together, which can improve the verification rate dramatically. As a tool for signature acquisition in a smart device, two applications, one using touch with a finger and the other using a pressure-sensing-stylus pen, are developed. The verification core is based on SVM and some modifications are made to include the characteristics of signatures. As shown in experimental results, the minimum error rate was 1.84% in the SVM based method, which can easily defeat 4.38% error rate with the previous parametric approach. Even more, 2.43% error rate was achieved with the features excluding pressure-related features, better than the previous approach including pressure-related features and only about 0.6% more error than the best result, which means that the proposed algorithm can be applied to a smart device with or without pressure-sensing-stylus pens and used for security purposes.

• Korean Journal of Digital Imaging in Medicine
• /
• v.9 no.2
• /
• pp.23-30
• /
• 2007

This study attempts to propose an appropriate method of using digital medical imaging equipments, by studying the effects of automatic exposure control(AEC), grid ratio and the change of radiography distance on the patient dose and detertor acquisition dose during the procedure of acquiring image through a digital medical imaging detector. The change of dose following the change of grid ratio's exposure and radiography distance was measured, by using an abdominal phantom organized with tissue equivalent materials in an amorphous silicon thin film transistor detecter installed with AWC. The case to use grid ratio 12 : 1, focal distance 180cm to radiography distance 110cm in AEC, the patient dose increased rather when we used grid ration 10 : 1, focal distance 110cm. When AEC was not used,the dose necessary for image acquisition decreased as the grid ratio became higher and the distance became further. but detector acquisition dose was not reduced when in applied AEC. When purchasing digiral medical imaging equipments, optional items such as AEC and grid shall be accurately selected to satisfy the use of the equipments. Radiography error made by radiation technologist and unnenessary patient dose can be reduced by selecting equipments with a radiography distance marker equipment when it did not apply AEC. These equipments can also be helpful in maintaining high imaging quality, one of the merits of digital detectors.

• Journal of Biomedical Engineering Research
• /
• v.25 no.1
• /
• pp.77-82
• /
• 2004

The purpose of this study is to establish a reference for image acquisition for completion of a standard brain for diverse Korean population, and to develop a management system that saves and manage database of the acquired brain image and personal information of those who were tested. 3D MP-RAGE technique, which has excellent SNR and CNR and reduces the times for image acquisition, was selected for anatomical Image acquisition, and parameter values were obtained for the optimal image acquisition. The database management system was devised to obtain not only anatomical image data but also subjects' basic demographic factors, medical history, handedness inventory state-trait anxiety inventory, A-type personality inventory, self-assessment depression inventory questionnaires of Sasang Constitution Mini-Mental State Examination, intelligence test, and personality test via a survey questionnaire and to save and manage the results of the tests. In addition, this system was designed to have functions of saving, inserting, deleting, searching, and Printing of image da a and personal information of subjects, and to have accessibility to them as well as automatic connection setup with ODBC. This newly developed system may have major contribution to the completion of a standard brain of diverse Korean population in that it can save and manage their image date and personal information.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.7C
• /
• pp.735-742
• /
• 2006

In this paper, we explain the operation scheme and fixed-point design method of DFE (Digital Front End), which performs DC offset compensation, automatic frequency control, and automatic gain control over the input signal to the UE (User Equipment) receiver of IEEE 802.16e OFDMA-TDD system. Then, we analyze the performance of DFE under ITU-R M. 1225 Veh-A 60km/h channel environment. To optimize the fixed-point design of DFE, we reduce the number of bit resulted from calculation without performance degradation, leading to the decreased complexity of the operation in H/W, and design the Loop filter with considering trade-off between the Acquisition time and the Stability.