• 한국언어정보학회지:언어와정보
• /
• 제9권1호
• /
• pp.51-68
• /
• 2005

This paper proposes an informational approach to the dative alternation in English following up on the Stochastic Optimality- Theoretic (OT) model by Bresnan and Nikitina (2003). While Bresnan and Nikitina's stochastic OT model resolves the crucial problem of 'gradience' unavoidably implicated in variation phenomena by applying the notion of probability to linguistic problems, it fails to account for the details of the unusually alternating examples, which normally would not alternate. More importantly, it fails to capture the focus effect involved in the alternation. This paper has worked out all the problematic examples by modifying the Bresnan and Nikitina model. This new account captures not only the unusual behavior of the less-alternating verbs and idioms but also the special focus effect of the common alternating verbs.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권5호
• /
• pp.420-429
• /
• 2009

특허 문서는 과학기술 발전을 탐지하고 기존 트렌드를 이해함으로써 미래의 트렌드를 예측하는데 유용한 자원이다. 본 연구에서는 단위 기술을 "문제점"과 "해결방법"으로 구성되어 있다고 보고, 언어적 단서(linguistic clue)와 언어 모델(1anguage model)을 결합한 혼합 모델을 사용하여 이들에 해당하는 의미 핵심문구(semantic keyphrase)를 찾고, 의미 핵심문구로 표현되는 단위 기술을 추출하였다. 추출된 결과에 근거하여 비지도 학습(unsupervised learning) 방법으로 과학기술들의 트렌드를 발견하는 새로운 접근방법(Technological Trend Discovery, TTD)을 제안한다. 실험 결과에 따르면 본 연구에서 제안한 방법으로 과학 기술을 나타내는 의미적 핵심 문구를 추출하는데 77%의 R-정확률을 달성하였고 결과적으로 의미있는 과학기술 트렌드를 발견할 수 있었다.

• 품질경영학회지
• /
• 제52권1호
• /
• pp.95-113
• /
• 2024

Purpose: This study focused on the societal changes associated with the entry into an ultra-aged society and the increase in single-person households. The core objective of this research is to investigate how social intelligent robots can bring about positive changes in the lives of individuals in single-person households and how such changes influence user satisfaction and the intention to use these robots. Methods: The study employed a cross-sectional analysis using a structural equation model. A survey designed to assess the impact of social intelligent robots' characteristics, such as perceived encouragement, empathy, presence, appearance, and attachment, on user satisfaction and usage intentions was conducted. Data were collected from a total of 335 users and analyzed using the structural equation model. Results: In the characteristics of social intelligent robots for single-person households, it was found that empathy, presence, and attachment significantly influenced satisfaction, while perceived encouragement, empathy, and attachment significantly influenced usage intentions. The research results indicate differences between enhancing user satisfaction and increasing the intention to use social intelligent robots. The findings suggest the essential need for a user-centric approach in the design and development of social intelligent robots. Additionally, it was observed that emotional support plays a crucial role in users' experiences with social intelligent robots. Conclusion: This study verified the impact of social intelligent robots on satisfaction and usage intentions based on users' experiences. It examined the influence of linguistic, visual, and personal characteristics of robots on user experiences, providing insights into how technological and human aspects of social intelligent robots interact to shape user satisfaction and usage intentions. Consequently, the study confirmed that social intelligent robots can bring positive changes to human life, emphasizing the necessity for the advancement of robot technology in a human-centric direction.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.321-324
• /
• 2002

For a rule-based conversion of Hangout into the Roman alphabet rather than a word-for-word conversion, one must come up with a faultless model for the Korean standard pronunciation rules, which are the basis of the Romanization. It is on this foundation that the Korean-Roman alphabet conversion table can be created. For linguistic modeling using PetriNet, modeling boundary and notation of modeling can be defined. In order to describe PetriNet, which is a dynamic modeling tool, as a static one, one can model the standard Korean pronunciation rules and the Hangout-Roman alphabet notation by conversion into incident matrix Thus, this research attempts to develop a mathematical modeling tool for a natural language using PetriNet, and create a Korean-Roman alphabet conversion table.

• 한국지능시스템학회논문지
• /
• 제12권6호
• /
• pp.549-553
• /
• 2002

본 논문은 전문학술 인력을 자동으로 순위를 매겨 선정하는 지식기반 퍼지 다중 규칙을 제시하고 있다 이를 위하여 학술전문가 선정에 대한 추론규칙을 만들고 다중퍼지 규칙에 대한 최대-최소 추론 및 선정기준에 따라 동적으로 선정기준이 적용되는 방안을 제시하며 이를 위한 시뮬레이션 모델을 구현하고 있다. 본 제안은 학술전문가 선정의 자동화, 공정성, 신뢰성 등을 제공하여 준다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.135-138
• /
• 1997

In this paper, we proposed effective modeling method to nonlinear complex system. Fuzzy Neural Network(FNN) was used as basic model. FNN was fused of Fuzzy Inference which has linguistic property and Neural Network which has learning ability and high tolerence level. This paper, we used FNN which was proposed by Yamakawa. The FNN used Simple Inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. This structure has better property than other structure at learning speed and convergence ability. But it has difficulty at definition of membership function. We used Hard c-Mean method to overcome this difficulty. To evaluate proposed method. We applied the proposed method to waste water treatment process. We obtained better performance than conventional model.

• 공학교육연구
• /
• 제23권2호
• /
• pp.3-13
• /
• 2020

Key objective of cornerstone design is that students are able to experience developing creative design concepts through team activities, but the objective is hard to achieve. Based on a study of research materials, this paper asserts that the possibilities of creative problem solving can be promoted in question-centering ideation model if design artifacts are represented in some forms that could invoke design thinking and then the solution space is appropriately established. In particular, design problem on which divergent questions are asked should be explored and defined so that it can be a linguistic artifact represented by various visual aids. It is recommended that curriculum is modified so that students can experience creative conceptual design.

• 한국자동차공학회논문집
• /
• 제2권5호
• /
• pp.23-29
• /
• 1994

The design procedure for fuzzy logic controller depends on the expert's knowledge or trial and error. Moreover, it is very difficult to guarantee the stability and robustness of the system due to the linguistic expression of fuzzy control. However, fuzzy logic control has succeeded in many control problems that the conventional control theory has difficulties to deal with. As a result, this control theory is applied to the engine control system which a mathematical model is difficult. In this study, the fuzzy logic is applied to obtain the gain of PI control at idle speed control system, and a simple engine model is developed in order to perform simulation. Experimental results show that the response to reach the target engine speed at idle speed control system is improved by adopting the gain obtained with fuzzy logic.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 B
• /
• pp.566-568
• /
• 1998

In this paper, we suggest a optimal design method of Fuzzy-Neural Networks model for complex and nonlinear systems. FNNs have the stucture of fusion of both fuzzy inference with linguistic variables and Neural Networks. The network structure uses the simpified inference as fuzzy inference system and the BP algorithm as learning procedure. And we use a clustering algorithm to find initial parameters of membership function. The parameters such as membership functions, learning rates and momentum coefficients are easily adjusted using the genetic algorithms. Also, the performance index with weighted value is introduced to achieve a meaningful balance between approximation and generalization abilities of the model. To evaluate the performance index, we use the time series data for gas furnace and the sewage treatment process.