• 한국정밀공학회지
• /
• 제20권7호
• /
• pp.155-162
• /
• 2003

We propose a new technique far real-tine controller design of a autonomous cruise mobile robot with three drive wheels. The proposed control scheme uses a Caussian function as a unit function in the fuzzy neural network. and a back propagation algorithm to train the fuzzy neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-foray. The control performance of the proposed controller is illustrated by performing the computer simulation for trajectory tracking of the speed and azimuth of a autonomous cruise mobile robot driven by three independent wheels.

• KIEE International Transactions on Power Engineering
• /
• 제4A권2호
• /
• pp.58-68
• /
• 2004

This paper presents an optimal routing algorithm (ORA) for maximizing voltage stability as well as for minimizing power loss in radial power systems. In the proposed ORA, a novel voltage stability index (VSI) for real-time assessment is newly introduced based on the conventional critical transmission path framework. In addition, the suggested algorithm can automatically detect the critical transmission paths resulting in voltage collapse when additional real or reactive loads are added. To implement an effective ORA, we have developed an improved branch exchange (IBE) method based on a loss calculation index and tie-branch power flow equations, which are suggested for real-time applications. The proposed algorithm has been tested with IEEE test systems as well as a large-scale power system in Korea to demonstrate its effectiveness and efficiency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2148-2161
• /
• 2019

In this paper, we present a real-time cattle action recognition algorithm to detect the estrus phase of cattle from a live video stream. In order to classify cattle movement, specifically, to detect the mounting action, the most observable sign of the estrus phase, a simple yet effective feature description exploiting motion history images (MHI) is designed. By learning the proposed features using the support vector machine framework, various representative cattle actions, such as mounting, walking, tail wagging, and foot stamping, can be recognized robustly in complex scenes. Thanks to low complexity of the proposed action recognition algorithm, multiple cattle in three enclosures can be monitored simultaneously using a single fisheye camera. Through extensive experiments with real video streams, we confirmed that the proposed algorithm outperforms a conventional human action recognition algorithm by 18% in terms of recognition accuracy even with much smaller dimensional feature description.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.11-15
• /
• 2001

The explosion of the Internet, and most recently e-commerce, has caused great interest in agent technologies. The development of virtual environments has also increased in the last few years. A growing number of real-time applications use graphics with photorealistic quality, especially in the field of training, but also in the areas of design and ergonomic research. We describe an attempt to develop a framework that provides customers with multimedia information and interactive experiences with a virtual shopping environment. The application presented consists on a virtual visit to a music -store where the user is guided by an intelligent agent named Lizeth which responds in real-time to user's requests with precise information about music, artist's biographies, prices and related products to help the user to make decisions. The potential of UML and the Java programming language is discussed to show their application in the field of intelligent agents as mediators on shopping processes. We conclude that the proposed framework leads to the creation of application with a potentially significant impact in the development of e-commerce systems embedded in virtual environments.

• 한국통신학회논문지
• /
• 제38C권4호
• /
• pp.344-350
• /
• 2013

초기 디자인 단계에서 효율적인 디자인 의사결정을 위해서는 지오메트리에 대한 고려가 필수적이다. 하지만 중요한 의사결정은 지오메트리에 대한 효율적 분석이 가능한 BIM모델 보다는 여전히 대화나 물리적 모델, 제스처를 통해 이루어진다. 본 논문은 실시간 BIM분석을 위한 BIM 모델과 물리적 모델의 연동을 제안한다. 두 모델이 실시간으로 연결되는 시스템 프레임워크를 통해 건축가는 디자인 초기 단계에서 부터 BIM 모델을 효율적으로 활용할 수 있다. 이 프레임워크는 건축가들이 설계 초기 단계에서부터 마지막 단계까지 컴퓨터의 기술을 활용한 동적인 의사결정을 가능하게 한다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 춘계종합학술대회논문집
• /
• pp.461-465
• /
• 2003

고성능 컴퓨팅 자원에서의 그리드 컴퓨팅은 다양한 대규모 계산 문제를 해결하기 위해 적용되고 있다. 응용 프로그램 개발자들에게 분산된 컴퓨팅 자원을 제공하는 다양한 소프트웨어들이 개발되었다. 그러나, 이들 시스템들은 웹기반이 아니거나 협력작업을 위한 기능을 제공하지 않거나 실시간으로 결과를 볼 수 있는 도구를 제공하지 않는다. 네트워크 어플리케이션 개발 측면에서 보면 웹기술은 일반적으로 사용하는 기술이 되고 있다. 특히, 인터페이스가 플랫폼과 독립적이라는 특징 때문에 더욱 그렇다. 본 연구에서는 MPI를 이용해 작성된 병렬 SPMD 어플리케이션의 수행을 위한 웹기반 프레임워크를 제안한다. 또한, 실시간 가시화 기술을 이용해서 협력연구를 위한 환경을 개발하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1039-1043
• /
• 2005

Despite the many significant advances made in robot architecture, the basic approaches are deliberative and reactive methods. They are quite different in recognizing outer environment and inner operating mechanism. For this reason, they have almost opposite characteristics. Later, researchers integrate these two approaches into hybrid architecture. In such architecture, Reactive module also called low-level motion control module have advantage in real-time reacting and sensing outer environment; Deliberative module also called high-level task planning module is good at planning task using world knowledge, reasoning and intelligent computing. This paper presents a framework of the integrated planning and control for mobile robot navigation. Unlike the existing hybrid architecture, it learns topological map from the world map by using MST (Minimum Spanning Tree)-based SOFM (Self-Organizing Feature Map) algorithm. High-level planning module plans simple tasks to low-level control module and low-level control module feedbacks the environment information to high-level planning module. This method allows for a tight integration between high-level and low-level modules, which provide real-time performance and strong adaptability and reactivity to outer environment and its unforeseen changes. This proposed framework is verified by simulation.

• 한국정보통신학회논문지
• /
• 제17권12호
• /
• pp.2937-2943
• /
• 2013

본 논문은 방사기저함수(Radial Basis Function)를 이용한 실시간 군집 시뮬레이션 프레임웍을 제안한다. 제안된 프레임웍에서는 군집이 존재하는 환경을 격자 구조로 모델링 한 후, 격자 구조 각 셀에 하나의 방향 벡터를 할당한 벡터필드를 선형 방사기저함수를 이용하여 실시간으로 합성한다. 방사기저함수를 통한 벡터필드 생성 시, 마우스를 통한 제어라인(Control line)을 이용하며, 이 벡터필드 위에서 군집들은 벡터 필드 흐름에 따라, 자신의 움직임을 결정한다. 방해물과의 충돌회피는 반발벡터필드로 모델링하여, 기존의 벡터필드에 오버레이 하여 이용하고, 다른 캐릭터와의 충돌회피는 lattice-bin 알고리즘에 빠른 충돌회피를 수행한다.

• Nuclear Engineering and Technology
• /
• 제51권3호
• /
• pp.702-708
• /
• 2019

This paper deals with break size estimation of loss of coolant accidents (LOCA) using a nonlinear autoregressive with exogenous inputs (NARX) neural network. Previous studies used static approaches, requiring time-integrated parameters and independent firing algorithms. NARX neural network is able to directly deal with time-dependent signals for dynamic estimation of break sizes in real-time. The case studied is a LOCA in the primary system of Bushehr nuclear power plant (NPP). In this study, number of hidden layers, neurons, feedbacks, inputs, and training duration of transients are selected by performing parametric studies to determine the network architecture with minimum error. The developed NARX neural network is trained by error back propagation algorithm with different break sizes, covering 5% -100% of main coolant pipeline area. This database of LOCA scenarios is developed using RELAP5 thermal-hydraulic code. The results are satisfactory and indicate feasibility of implementing NARX neural network for break size estimation in NPPs. It is able to find a general solution for break size estimation problem in real-time, using a limited number of training data sets. This study has been performed in the framework of a research project, aiming to develop an appropriate accident management support tool for Bushehr NPP.

• 한국기술혁신학회:학술대회논문집
• /
• 한국기술혁신학회 2002년도 춘계학술대회
• /
• pp.181-198
• /
• 2002

This article describes a methodology for evaluating huge aerospace R&D investments using the real options pricing method. Option pricing has been proposed as a useful approach for modeling investment in R&D. Two important features of R&D investments are that an R&D project takes time to complete and that the outcome of R&D investments is highly uncertain. This makes the analysis of R&D investments difficult. Traditional tools for project evaluation, like IRR or the NPV, are inadequate for coping with the high uncertainty. Hence, In this article I propose a log-transformed binomal lattice method, and it will show that option pricing might be an adequate framework for evaluating such types of aerospace investments.