• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.1
• /
• pp.27-33
• /
• 1997

This project is dedicated to the elaboration of a man-machine system for monitoring the non spread of nuclear weapons, technologies, raw materials. The main purpose of such a system depends on the customer requirements and may be : - control of non proliferation of nuclear technologies, especially those that can be used to manufacture a nuclear explosive device; - the appraisal of the possibility of production of nuclear weapons by a certain country on the basic of its intellectual and scientific-technical potential, its raw material resources, its export-import potential and other parameters.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.4
• /
• pp.267-274
• /
• 2011

Recently, actor-critic methods have drawn significant interests in the area of reinforcement learning, and several algorithms have been studied along the line of the actor-critic strategy. In this paper, we consider a new type of actor-critic algorithms employing the kernel methods, which have recently shown to be very effective tools in the various fields of machine learning, and have performed investigations on combining the actor-critic strategy together with kernel methods. More specifically, this paper studies actor-critic algorithms utilizing the kernel-based least-squares estimation and policy gradient, and in its critic's part, the study uses a sliding-window-based kernel least-squares method, which leads to a fast and efficient value-function-estimation in a nonparametric setting. The applicability of the considered algorithms is illustrated via a robot locomotion problem and a tunnel ventilation control problem.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.48-51
• /
• 2004

'유비쿼터스'라는 신조어를 통해 우리의 현재 IT 분야에 큰 영향을 주고 있으며, 이 개념과 맞물려 우리 일상생활에도 많은 변화가 일어나고 있다. 현재 인터넷은 우리 생활치 일부가 되었고 다음은 로봇의 시대가 될 것이라 생각된다. 많은 국가와 연구실에 로봇에 관한 많은 연구를 하고 있으며 성과를 거두고 있다. 본 논문에서는 지능을 지니고 휴대가 간편한 휴대용기기를 이용하여 가정에서 여러 가지 기능을 수행하는 서비스 로봇을 제어하고자 한다 유비쿼터스 개념과 같이 언제 어디서든지 연결이 가능하도록 무선랜 통신을 사용하여 휴대용 기기와 가정용 서비스 로봇은 정보를 상호 교환 할 수 있다. 지능형 휴대용 기기는 가정용 서비스 로봇이 가정에서 여러 가지 임무를 수행할 수 있도록 소프트 컴퓨팅 기법을 사용한 알고리즘을 이용한다. 또 한 로봇은 환경을 파악할 수 있도록 다종의 센서를 부착하고 있으며 이를 통해 환경에 맞는 임무를 수행 할 수 있도록 정보를 수집한다. 본 논문은 지능형 휴대용 기기를 이용하여 인간 친화적인 가정용 서비스 로봇이 될 수 일도록 기능을 제어하는 것이다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.5
• /
• pp.651-657
• /
• 1998

In this study, an intelligent scheduling with hybrid architecture, which integrates expert system and neural network, is proposed. Neural network is trained with the data acquired from simulation model of FMC to obtain the knowledge about the relationship between the state of the FMC and its best dispatching rule. Expert system controls the scheduling of FMC by integrating the output of neural network, the states of FMS, and user input. By applying the hybrid system to a scheduling problem, the human knowledge on scheduling and the generation of non-logical knowledge by machine teaming, can be processed in one scheduler. The computer simulation shows that comparing with MST(Minimum Slack Time), there is a little increment in tardness, 5% growth in flow time. And at breakdown, tardness is not increased by expert system comparing with EDD(Earliest Due Date).

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.370-376
• /
• 2002

인터넷 환경에서 발생되는 수많은 데이터를 지능적으로 처리할 수 있는 자동화된 분석 시스템의 필요성이 제기된다. 이러한 시스템의 데이터 분석은 크게 지도 학습과 자율 학습으로 나된다. 본 논문에서는 특히 자율학습 군집화에 대한 자동화된 시스템으로서 지능화된 데이터 마이닝 에이전트를 제안한다. 군집화 과정에서는 데이터를 분석하는 분석가가 군집화의 방법과 결과 해석에 실시간으로 관여하기 어렵기 때문에 이러한 작업을 담당하는 지능화된 에이전트가 자동화된 군집화를 담당하면 효과적인 군집화 전략이 될 수 있다. 본 논문의 자동 군집화를 위한 지능화된 데이터 마이닝 에이전트 시스템은 군집화 수행 에이전트와 군집화 성능 평가 에이전트로 구성된 다중 에이전트로서 두 개의 에이전트가 서로 정보를 교환하면서 최적의 군집화를 수행한다. UCI Machine Repository 데이터를 이용한 실험을 통해 제안 시스템의 성능 평가를 수행하였다.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.5
• /
• pp.27-34
• /
• 2005

To accomplish various and complex tasks by intelligent robots, improvement is needed not only in mechanical system architecture but also in control system architecture. Hybrid control architecture has been suggested as a mutually complementing architecture of the weak points of a deliberative and a reactive control. This paper addresses a control architecture of robots, and a behavior representation methodology. The suggested control architecture consists of three layers of deliberative, sequencing, and reactive as hybrid control architecture. Multi-layer behavior model is employed to represent desired tasks. 3D simulation will be conducted to verify the applicability of suggested control architecture and behavior representation method.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.10a
• /
• pp.483-488
• /
• 2000

This study aims at developing the high speed/intelligent machining system using the plug/play method of an open architecture controller. The plug/play technology by the application Specific Function (ASF), can readily implement the open architecture controller into various machining system or other automatic devices. The plug/play method integrates the ASF, visual builder, controller OS technology. This study, as an example, presents a schematic diagram for integration of an open architecture CNC and individual component technology for the high speed/intelligent machining system.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.2
• /
• pp.72-78
• /
• 2001

Roundness measurement method using three displacement sensors makes in-process roundness measurement possible on the NC machine because it eliminates the vibration signal and eccentricity signal from measured roundness signal from the workpiece. But there are noises in measured signals, it isn't possible to measure the roundness with high precision. In this study, a high precision in-process roundness measurement system is development, which can eliminate vibrations of the spindle by using three displacement sensors and which can also estimate the noisy roundness measurement signals by applying Kalman filter.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.12
• /
• pp.1186-1191
• /
• 2007

Human driver monitoring system is one of the most important systems for the safety in driving vehicles, and therefore driver assistance system has gained much attention during the last decade. This paper proposed an intelligent driver assistance system which monitors human driver's states from bio-signals such as ECG and Blood Pressure. The proposed system used mamdani fuzzy inference to evaluate the driver's mental strain and generated warning signals to the driver. The approach using bio-signals in driver assistance system is the main issue of the related systems and the preliminary results showed the possibility of further research topics in developing more intelligent embedded systems with bio-signal feedback.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.1 no.1
• /
• pp.135-142
• /
• 2012

In this paper, optimal selection of the unified power flow controller (UPFC) damping controller parameters in order to improve the power system dynamic response and its stability based on two modified intelligent algorithms have been proposed. These algorithms are based on a modified intelligent particle swarm optimization (PSO) and continuous genetic algorithm (GA). After extraction of UPFC dynamic model, intelligent PSO and genetic algorithms are used to select the effective feedback signal of the damping controller; then, to compare the performance of the proposed UPFC controller in damping the critical modes of a single-machine infinite-bus (SMIB) power system, the simulation results are presented. The comparison shows the good performance of both presented PSO and genetic algorithms in an optimal selection of UPFC damping controller parameters and damping oscillations.