• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1082-1085
• /
• 1993

In this paper, we notice the fact that a human learning process is characterized by a process under a natural language environment, and discuss an approach of learning based on indirect linguistic instructions. An instruction is interpreted through some meaning elements and each trend. Fuzzy evaluation rule are constructed for the searched meaning elements of the given instruction, and the performance of a system to be learned is improved by the evaluation rules. In this paper, we propose a framework of learning based on indirect linguistic instruction based learning using fuzzy theory: FULLINS(FUzzy-Learning based on Linguistic IN-Struction). The validity of FULLINS is shown by applying it to helicopter flight control.

• 한국정밀공학회지
• /
• 제14권9호
• /
• pp.116-123
• /
• 1997

We have already presented the constraint satisfaction algorithm which could solve the closed loop porblem in constraint network by using local constraint propagation, variable elimination and constraint modularization. With this algorithm, we have implemented a knowledge-based system (intelligent CAD) for supporting machine design interactively. In this paper, we present newer constraint satisfaction algorithm which can solve inequalities or under-constrained problems in constraint network, interactively and effi- ciently. This algorithm is a hybrid type of using both declarative description (constraint representation) and optimization algorithm (Simulated Annealing), simultaneously. The under-constrained problems are represented by constraint networks and satisfied completely with this algorithm. The usefulness of our algorithm will be illustrated by the application to a gear design.

• 반도체디스플레이기술학회지
• /
• 제14권1호
• /
• pp.19-25
• /
• 2015

Strengthened glass is widely used in the display industry for the smart phone and the tablet PC's, the market of which shows steady growth. The strengthened glass is prone to the fracture due to the machined surface defects such as crack and notch. The surface defects are caused mostly by the vibrations of the laser cutter. In this study, the vibrations of the laser cutter were investigated through the frequency response experiment and the computer simulation. The main reasons of the structural vibrations were analyzed, and further the design alterations were deduced and applied to the machine to check the effects of those alterations and to eventually improve the structural stability. The result shows that simple design modifications without major structural change can substantially suppress the vibrations, and improve the quality of the machined surface.

• 한국산학기술학회논문지
• /
• 제13권9호
• /
• pp.4193-4199
• /
• 2012

본 연구에서는 안드로이드 기반 스마트폰을 장착하여 지능형 로봇의 성능 구현이 가능하도록 스마트폰 애플리케이션과 로봇 플랫폼을 설계 및 구현하였다. 터치스크린, 사운드 입출력, 네트워크 그리고 각종 센서 기능을 갖고 있는 스마트폰을 전원부와 모터 등의 단순 기능을 갖는 로봇플랫폼에 접목시켜 원격제어, 홈오토메이션, 게임기, R-러닝 등의 기능을 수행할 수 있도록 구현하였다. 연구에 사용된 스마트폰은 블루투스 통신을 이용하여 로봇과 데이터를 송수신하며 원격지의 컴퓨터와는 WI-FI를 통해 인터넷으로 통신을 수행하도록 설계 하였다.

• Journal of Electrical Engineering and Technology
• /
• 제8권3호
• /
• pp.478-489
• /
• 2013

The controllability and stability of power systems can be increased by Flexible AC Transmission Devices (FACTs). One of the FACTs devices is Interline Power-Flow Controller (IPFC) by which the voltage stability, dynamic stability and transient stability of power systems can be improved. In the present paper, the convenient operation and control of IPFC for transient stability improvement are considered. Considering that the system's Lyapunov energy function is a relevant tool to study the stability affair. IPFC energy function optimization has been used in order to access the maximum of transient stability margin. In order to control IPFC, a Brain Emotional Learning Based Intelligent Controller (BELBIC) and PI controller have been used. The utilization of the new controller is based on the emotion-processing mechanism in the brain and is essentially an action selection, which is based on sensory inputs and emotional cues. This intelligent control is based on the limbic system of the mammalian brain. Simulation confirms the ability of BELBIC controller compared with conventional PI controller. The designing results have been studied by the simulation of a single-machine system with infinite bus (SMIB) and another standard 9-buses system (Anderson and Fouad, 1977).

• 한국정밀공학회지
• /
• 제26권4호
• /
• pp.47-54
• /
• 2009

In the last few years, lasers have found new applications as tools for ceramic machining which is laser-assisted machining(LAM). LAM process for the machining of difficult-to-machine materials such as structural ceramics, has recently been studied on silicon nitride workpiece for a wide range of operating condition. However, there have been few studies on rake angle in LAM process. In this paper we analyzed difference of machinability between positive and negative rake angle in tools. We have obtained interesting results that we could eliminate chattering, lower specific cutting and cutting ratio in case of positive rake angle. The results suggest that positive rake angled tools can make more plastic deformation and stable cutting of silicon nitride in comparison with negative rake angled one.

• 조명전기설비학회논문지
• /
• 제14권5호
• /
• pp.50-55
• /
• 2000

본 연구에서는 지능형 최대수요 전력관리 장치를 개발하였다. 전체 시스템은 지능형 최대수요전력관리장치와 원격에서 부하를 관리할 수 있는 단말처리장치 그리고 사용자의 편의와 원격관리를 위한 HMI 프로그램으로 구성되었다. 개발된 지능형 최대수요전력관리장치의 특징은 다음과 같다. 첫째, 전력회사(예: 한국전력) 거래용 전력량계와 수요시한 동기가 가능하여 정확한 전력판리가 기능하다. 두 번째로 정밀한 전력계측기능을 내장하여 시스템을 간략화 할 수 있다. 세 번째로 단말처리정치를 개발하여 통선을 이용한 원격부하 관리를 수행하므로 초기 설치비용올 저감시켰다. 마지막으로 웹(web)기반 관리시스템을 구축하여 분산된 지능형 최대수요전력관려장치의 편리를 용이하게 하였다. 여러 가지 실험을 통해서 개발된 시스템의 성능을 검증하였다.

• 한국전자통신학회논문지
• /
• 제5권3호
• /
• pp.309-314
• /
• 2010

본 논문에서는 인터넷상에서의 지능형 감시 카메라 시스템(Intelligent Security Camera: ISC)을 제안한다. ISC 방법은 워터쉐드 알고리즘에 기반하여 카메라에 입력된 영상을 분할하는 단계와 skin-color model을 사용하여 얼굴의 후보지역을 탐지하는 단계, 그리고 마지막으로 SVM(Support Vector Machine)을 사용하여 얼굴 후보영역에서 얼굴을 검증하는 단계로 구성되어 있다. Skin-color Model을 이용하여 찾아진 얼굴후보 영역으로부터 웨이블렛 변환계수들을 추출한다. 웨이블렛 변환계수들을 SVM의 입력으로 하여 실제 얼굴영역을 검증한다. SVM의 입력으로 실험결과에서 제안된 방법이 감시시스템, 화상회의 시스템과 같은 얼굴을 인식 추적하는 시스템에 적용될 수 있음을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• 한국컴퓨터정보학회논문지
• /
• 제11권4호
• /
• pp.17-25
• /
• 2006

인공지능 기법을 이용한 컴퓨터 게임에 대한 학술적 연구는 오랫동안 이루어져 왔으며 주로 게임에 대한 숙련도를 높여서 인간에게 승리하는 것이 주요 연구 목적이었다. 그러나 최근의 상업용 게임에서는 게임의 흥미를 제공하기 위해서 사용자의 적응을 목적으로 개발하고 있다. 본 논문에서는 기존의 강화학습알고리즘을 수정하여 사용자 적응에 중점을 둔 적응형 강화 학습 알고리즘을 제안하였다. 실험대상으로는 많은 상태공간을 가진 오델로 게임을 대상영역으로 하여 시스템을 설계 및 구현하였다. 시스템의 성능측정은 두개의 강화학습 알고리즘이 각각 Min-Max 알고리즘과 대결하는 방식으로 실험을 하였으며, 결과는 기존의 강화 학습 알고리즘과의 대결에서도 향상된 학습율을 나타내었다.