• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.530-537
• /
• 2001

본 논문은 자연어 인터페이스에 기반한 관계형 데이터베이스 상에서의 질의 응답 시스템에 대해 기술한다. 본 시스템은 다국어, 다중 도메인, 다중 DBMS를 지원하는 시스템으로, 주로 오디오와 비디오 관련 제품들에 대한 정보를 다룬다. Lexico-semantic pattern (LSP) 문법을 관계형 데이터베이스 상에서의 질의 응답 시스템에 최초로 도입하여 기존의 시스템들에 비해 높은 성능을 보이며, linguistic front-end (LFE)와 database back-end (DBE)를 명확히 구분하고 각종 리소스들을 엔진과 분리함으로써 높은 이식성을 가지도록 한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.419-421
• /
• 2022

어선은 어획물로 인한 무게 변화 및 어구 사용에 의한 외력으로 GM이 변화한다. 하지만 실시간으로 변화하는 GM을 추정하는 것은 어려우며, 현재 적용되는 추정식은 어선에 대입하기에 정확성이 떨어진다. 이에 본 논문은 어선의 GM 추정식 개발에 기여하기 위해 어선의 Roll 운동응답을 분석하고, 실험과 시뮬레이션의 GM과 파경사 관계를 밝히고자 한다. 7톤 급의 실제 운항 중인 어선의 모델선 GM을 변화시키면서 파경사별 Roll 운동응답 데이터를 수집한다. GM 변화의 경우 선박 무게중심부에 높이 방향으로 추를 조절할 수 있도록 했으며, 파경사는 동일 주기 4가지 파경사를 선정하였다. GM과 파경사가 커질수록 Roll 응답이 증가하는 경향을 보이며, GM과 파경사가 커짐에 따라 기울기가 비선형성을 보이며 증가하는 것을 확인하였다. 본 연구를 통해서 어선의 GM과 파경사의 관계를 파악하고, GM추정에 사용할 수 있느 보정 계수를 도출할 수 있다. 추후에 본 연구 내용을 활용하여 운항 중인 어선의 실시간 GM 추정시스템 개발에 기여가 가능할 것으로 생각한다.

• Journal of dental hygiene science
• /
• v.7 no.2
• /
• pp.107-112
• /
• 2007

The purpose of this study was to investigate the job value type of dental hygiene students. The questionaire given to 823 dental hygiene students from three college in Gwangju and Chunnam Colleges. The results of this study were as follows: 1. dental hygiene students, job value type were divided 6 categories: Competency, Contribution, Achievement, Reward, status, stability. 2. The higher status was at c college and at good relationship group and more perceived bad health and at work experience group. 3. The higher was reward at c college and lower grade and at good relationship group and more perceived good health and at work experience group. 4. The higher was status at c college and lower grade and lower age and at work experience group. 5. The higher was competency at c college and at good relationship group and more perceived bad health and .at work experience group. 6. The higher was contribution lower grade and more perceived bad health and at work experience group. 7. The higher was achievement at c college and at good relationship group and more perceived good health group.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.339-346
• /
• 2023

The uncertainties of microstructural features affect the properties of materials. Numerous pores that are randomly distributed in materials make it difficult to predict the properties of the materials. The distribution of pores in cementitious materials has a great influence on their mechanical properties. Existing studies focus on analyzing the statistical relationship between pore distribution and material responses, and the correlation between them is not yet fully determined. In this study, the mechanical response of cementitious materials is predicted through an image-based data approach using a convolutional neural network (CNN), and the correlation between pore distribution and material response is analyzed. The dataset for machine learning consists of high-resolution micro-CT images and the properties (tensile strength) of cementitious materials. The microstructures are characterized, and the mechanical properties are evaluated through 2D direct tension simulations using the phase-field fracture model. The attributes of input images are analyzed to identify the spot with the greatest influence on the prediction of material response through CNN. The correlation between pore distribution characteristics and material response is analyzed by comparing the active regions during the CNN process and the pore distribution.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.2
• /
• pp.179-193
• /
• 2022

This study aims to identify the relationship marketing factors and examine the mediating factors of perceived customer value on the relationship between relationship marketing factors and loyal on rural tourism. We collected and analyzed the survey data from the customers who had experienced rural tourism before. The results from the empirical analysis are as follows. First, through the exploratory factor analysis, four factors such as customer orientation, responsive attraction, professionalism, and ties were derived. Second, it was found all four factors have significant positive effects on loyalty. Third, both responsive attraction and professionalism have significant positive effects on perceived customer value. However, customer orientation and ties do not have significant effects. Fourth, the perceived customer value showed a full mediating effect between responsive attraction and loyalty, whereas it showed a partial mediating effect between professionalism and loyalty. Additionally, it was found that gender did not affect loyalty but significantly affected perceived customer value. This means that women had lower perceived value for rural tourism than men. To improve the loyalty of rural tourism, it is necessary to improve customer orientation, professionalism, ties, and perceived customer value.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1301-1313
• /
• 2009

Efficiency and sensitivity of BLS adjustment method have been studied and the method is known to provide more accurate estimate of total by using properly adjusted weights of samples. However, BLS methods provide different efficiencies according to the magnitudes of correlation coefficients and the sizes of samples in strata. In this paper we study the efficiency of the BLS adjustment according to the sample sizes and correlations in strata. For this study, 2007 monthly labor survey data is used.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.181-188
• /
• 2004

대다수의 개방영역 자연어 질의응답 시스템은 답을 선택할 수 있는 개념영역을 미리 정의하고 있기 때문에 시스템이 준비하지 못한 범주의 개념을 묻는 질의문에 대해서는 올바른 응답을 생성하지 못하거나 예외 처리 방식으로 응답을 생성해 낸다. 본 논문에서는 전형적인 범주에 속하지 않는 명사 개념에 관한 질의문에 대해 범용적으로 대응할 수 있는 개방영역 자연어 질의응답 시스템을 제안한다. 제안하는 시스템은 상위 개념 명사구(Hypernym)에 포함되는 하위 개념의 명사구(Hyponym)들을 추출할 수 있는 일반적인 패턴들을 그 신뢰도와 함께 가지고 있다. 따라서 질의문이 임의의 명사구 개념을 요청할 때 정답의 후보들을 동적으로 생성되는 가상의 is-a 의미관계 사전으로부터 신뢰 순위로 정렬하여 추출해 낼 수가 있다. 제안하는 시스템은 "What 명사구 동사구" 형태의 질의문들 중에서 개체명 인식기나 시소러스를 이용하여 정답 후보를 손쉽게 생성할 수 있는 질의문을 배제한 실험용 질의문 집합을 이용한 실험에서 42%의 재현율을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.433-436
• /
• 2020

오픈 도메인 질의응답은 주로 관련된 문서를 검색하고 문서 집합에서 정답을 찾는 방식으로 문제를 해결하는 검색 기반 질의응답 방법을 사용한다. 이러한 검색 기반 질의응답은 정답이 검색된 문서 집합에 존재하지 않는 경우 정답을 찾을 수 없다는 한계가 존재하게 된다. 본 연구에서는 NIL-Aware 방법을 이용하여 Unanswerable한 질문인 경우 문서 자원이 아닌 지식 베이스 자원을 활용하는 뉴로-심볼릭 지식 베이스 질의응답과의 결합 모델을 제안하고 한국어 질의응답 데이터에 적용함으로 제안하는 결합 방법의 유의미성을 확인한다.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.4
• /
• pp.442-449
• /
• 1986

본 연구에서는 소음원 및 진동원을 규명하기 위하여 사용되어 온 종래의 주파 수응답함수(Frequency Response Function`FRF)법과 소음원 및 진동원 간에 강한 상관 관계가 존재한 경우에 사용되는 기여도함수(coherence function)법을 이용한 다차원 스텍트럼해석(Multi-Dimensional Spectral Analysis`MDSA)법에 의하여 가속도응답 및 방사음과의 기여관계를 규명하였다.