• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.963-965
• /
• 1999

A linear chromosome combined with a grid-based representation of the network and a new crossover operator allow the evolution of the architecture and the weights simultaneously. In our approach there is no need for a separate weight optimization procedure and networks with more than one type of activation function can be evolved. In this paper one evolutionary' strategy of a given dual neural controller was introduced and the simulation results were described in detail through applications to a stabilization control of an Inverted Pendulum System.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.433-439
• /
• 1998

In this paper, we present an approach to the structure identification based on the input space partition methods and to the parameter identification by hybrid learning method in neuro-fuzzy system. The structure identification can automatically estimate the number of membership function and fuzzy rule using grid partition, tree partition, scatter partition from numerical input-output data. And then the parameter identification is carried out by the hybrid learning scheme using back-propagation and least squares estimate. Finally, we sill show its usefulness for neuro-fuzzy modeling to truck backer-upper control.

• 한국멀티미디어학회논문지
• /
• 제8권10호
• /
• pp.1369-1382
• /
• 2005

도로 영상에서 차량 영역을 분할하는 차량 영역 분할(vehicle segmentation) 문제는 지능형 교통 시스템을 비롯한 다양한 응용 분야들에서 중요하게 사용되는 기본 연산(fundamental operation)이다. 본 연구에서는 야외의 도로 상에 설치된 CCD카메라에서 촬영된 정지 영상으로부터 차량 영역을 찾아내는 효율적인 방법을 제안한다 제안하는 방법은 입력되는 영상들을 격자 단위로 분할하여 각 격자에서의 에지 검출 결과를 대표하는 특징값(feature value)들을 통계적으로 분석한 후, 이를 바탕으로 최적해를 구한다. 전처리 과정에서는 다양한 외부 환경에서 촬영한 배경 영상들에 대해서 각 격자에서의 특징값들을 통계 처리한다. 입력된 차량 영상에서는 각 격자의 특징값이 배경 영상의 대응되는 격자에서의 특징값과 통계적으로 얼마나 오차를 보이냐에 따라, 배경 영역인지 차량 영역인지를 판단한다. 격자 별로 차량 영역에 해당하는 지를 판정한 뒤, 이 결과에 동적 프로그래밍(dynamic Programming) 기법을 이용하여 차량을 포함하는 최적의 직사각형 영역을 찾아낸다. 본 논문에서 제안하는 방법은 통계 처리와 전역 탐색 기법을 사용하므로 휴리스틱에 주로 의존하는 기존 연구들에 비해 좀더 체계적이다. 또한, 배경 영상에 대한 통계 처리는 흐리거나 맑은 등의 날씨 변화 및 바람이나 진동에 의한 카메라의 흔들림과 같은 다양한 외부 요인들이 가져올 수 있는 노이즈나 오차에 대해서도 높은 신뢰성을 보여준다. 제안하는 방법을 구현한 프로토타입 시스템은 $1280\times960$ 크기의 차량 영상들을 장당 평균 0.150초의 수행 시간에 처리하였으며, 총 270장의 다양한 노이즈를 가지는 차량 영상들에 대해 $97.03\%$의 성공률을 보였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제12권1호
• /
• pp.43-56
• /
• 2011

An integrated system composed of guidance, navigation and control (GNC) system for autonomous proximity operations and the docking of two spacecraft was developed. The position maneuvers were determined through the integration of the state-dependent Riccati equation formulated from nonlinear relative motion dynamics and relative navigation using rendezvous laser vision (Lidar) and a vision sensor system. In the vision sensor system, a switch between sensors was made along the approach phase in order to provide continuously effective navigation. As an extension of the rendezvous laser vision system, an automated terminal guidance scheme based on the Clohessy-Wiltshire state transition matrix was used to formulate a "V-bar hopping approach" reference trajectory. A proximity operations strategy was then adapted from the approach strategy used with the automated transfer vehicle. The attitude maneuvers, determined from a linear quadratic Gaussian-type control including quaternion based attitude estimation using star trackers or a vision sensor system, provided precise attitude control and robustness under uncertainties in the moments of inertia and external disturbances. These functions were then integrated into an autonomous GNC system that can perform proximity operations and meet all conditions for successful docking. A six-degree of freedom simulation was used to demonstrate the effectiveness of the integrated system.

• 한국조리학회지
• /
• 제15권4호
• /
• pp.227-244
• /
• 2009

본 연구는 레스토랑 산업에 널리 적용할 수 있는 외식 서비스 품질 측정을 위한 다문항 척도를 개발하였다. 척도 개발을 위해 Kelly Repertory Grid 방법을 이용하여 중요하게 생각하는 레스토랑 품질 속성을 파악한 후 전문가 토론을 수차례 거쳐 유사 중복 항목을 통합하고, 핵심 차원별 주요 속성을 도출하였다. 척도 정제를 위해 신뢰도 분석과 탐색적 요인 분석을 실시하였으며, 이후 각 구성 개념에 대한 중복성 여부를 확인하기 위하여 3차 확인 요인 분석을 실시하였다. 본 연구에서는 Brady & Cronin(2001)이 제안한 위계적 서비스 품질 모형을 바탕으로 외식 서비스 품질 척도를 개발하였다. 본 연구의 위계적 외식 서비스 품질 모형은 외식 서비스 품질 차원 및 측정 요인을 물리적 환경 품질, 상호 작용 품질, 음식 품질이라는 핵심 차원으로 설명함으로써 요인간의 중복성 완화, 결과와 과정 품질의 균형적 고려, 세 가지 핵심 차원별 관리포인트 명확화, 위계적 모형에 의한 핵심 차원과 하위 차원의 구분 등 이론적 기여 측면에서 뿐만 아니라 관리적 시사점 도출 측면에서도 우위성을 갖는다고 할 수 있다.

• Bulletin of the Korean Chemical Society
• /
• 제26권5호
• /
• pp.769-775
• /
• 2005

An efficiency of Monte Carlo (MC) docking simulations was examined for the prediction of chiral discrimination by cyclodextrins. Docking simulations were performed with various computational parameters for the chiral discrimination of a series of 17 enantiomers by $\beta$-cyclodextrin ($\beta$-CD) or by 6-amino-6-deoxy-$\beta$-cyclodextrin (am-$\beta$-CD). A total of 30 sets of enantiomeric complexes were tested to find the optimal simulation parameters for accurate predictions. Rigid-body MC docking simulations gave more accurate predictions than flexible docking simulations. The accuracy was also affected by both the simulation temperature and the kind of force field. The prediction rate of chiral preference was improved by as much as 76.7% when rigid-body MC docking simulations were performed at low-temperatures (100 K) with a sugar22 parameter set in the CHARMM force field. Our approach for MC docking simulations suggested that the conformational rigidity of both the host and guest molecule, due to either the low-temperature or rigid-body docking condition, contributed greatly to the prediction of chiral discrimination.

• 대한기계학회논문집A
• /
• 제29권3호
• /
• pp.447-454
• /
• 2005

This paper presents a new paradigm for 3-axis tool path generation based on an incomplete 2-manifold mesh model, namely, an inexact polyhedron. When geometric data is transferred from one system to another system and tessellated for tool path generation, the model does not have any topological data between meshes and facets. In contrast to the existing polyhedral machining approach, the proposed method generates tool paths from an incomplete 2-manifold mesh model. In order to generate gouge-free tool paths, CL-meshes are generated by offsetting boundary edges, boundary vertices, and facets. The CL-meshes are sliced by machining planes and the calculated intersections are sorted, trimmed, and linked. The grid method is used to reduce the computing time when range searching problems arise. The method is fully implemented and verified by machining an incomplete 2-manifold mesh model.

• 응용통계연구
• /
• 제25권4호
• /
• pp.669-680
• /
• 2012

Noise removal of document images is a necessary step during preprocessing to recognize characters effectively because it has influences greatly on processing speed and performance for character recognition. We have considered using the spatial filters such as traditional mean filters and Gaussian filters, and wavelet transformed based methods for noise deduction in natural images. However, these methods are not effective for the noise removal of document images. In this paper, we present noise removal of document images using support vector regression. The proposed approach consists of two steps which are SVR training step and SVR test step. We construct an optimal prediction model using grid search with cross-validation in SVR training step, and then apply it to noisy images to remove noises in test step. We evaluate our SVR based method both quantitatively and qualitatively for noise removal in Korean, English and Chinese character documents, and compare it to some existing methods. Experimental results indicate that the proposed method is more effective and can get satisfactory removal results.

• Geomechanics and Engineering
• /
• 제32권2호
• /
• pp.209-232
• /
• 2023

A comprehensive study was conducted to design economical foundations for a number of buildings on soft cohesive soil in the southern coastal regions of Iran. Both static and seismic loads were considered in the design process. Cyclic experiments indicated that the cohesive soil of the area has potential for softening. Consequently, the major challenge in the design stages was relatively high dimensions of settlement, under both static and seismic loadings. Routine soil-improvement methods were too costly for the vast area of the project. After detailed numerical modeling of different scenarios, we concluded that, in following a performance-based design approach and applying a special time schedule of construction, most of the settlement would dissipate during the construction of the buildings. Making the foundation as rigid as possible was another way to prevent any probable differential settlement. Stiff subgrade of stone and lime mortar under the grid foundation and a reinforced concrete slab on the foundation were considered as appropriate to this effect. In favor of an economical design, in case the design earthquake strikes the site, the estimations indicate no collapse of the buildings even if considerable uniform settlements may occur. This is a considerable alternative design to costly soil-improvement methods.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.1-6
• /
• 2005

The purpose of this paper is to propose a novel modeling approach called Services Ecosystem that applies the concept of ecosystems in ecology to Service-Oriented Software Development and Integration. For this purpose, an ecological system for software systems is proposed for the emerging Service-Oriented Computing paradigm, describing how participants interact with each other within their environments. Three emerging concepts, Service-Oriented Programming, Software Factories, and Service Grid, are employed to explain biotic and abiotic environments. Based upon the Services Ecosystem model, we demonstrate Services Ecosystem Model transformations by using a case example. The Services Ecosystem model is a novel approach for envisioning the Service-Oriented Computing paradigm in terms of an ecosystem in which the roles/perspectives of each participant and their relationships/interactions to environments are clearly described with a holistic view.