• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• Journal of the Korean Data and Information Science Society
• /
• 제9권2호
• /
• pp.345-355
• /
• 1998

다층전방향 신경망을 학습시키기 위해 역전파 알고리즘이 널리 사용되고 있으나 이 알고리즘은 긴 훈련시간, 극소점 문제, 이상치에 민감하다는 단점을 가지고 있다. 한편 실제문제에서는 많은 경우에 자료에 과대오차와 이상치가 포함되게 된다. 따라서 과대 오차에 민감하지 않고, 이상치의 영향을 최소화시키는 로버스트 역전파 알고리즘의 필요성이 대두되었다. 본 논문에서는 기존의 두종류의 로버스트 역전파 알고리즘을 이론적으로 비교하고 비선형 회귀 함수추정과 문자인식과 같은 패턴인식 문제에 적용하여 실험결과를 분석한다. 그리고 향후 연구과제로 신경망 학습을 위해 베이지안 기법의 사용을 제안한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.387-392
• /
• 2005

Double-deck train have studied in the next generation train in KRRI. Double-deck train have more seat capacities compared with single deck vehicles and is a efficient, reliable and comfortable alternative train. Because of heavy weight, weight minimization of double-deck train carbody is imperative to reduce cost and extend life-time of train. Weight minimization problem of the double-deck train car-body is required to decide 66 design variables of thicknesses for large aluminum extruded panel while satisfying stress constraints. Design variables are too many and one execution of structural analysis of double-deck train carbody is time-consuming. Therefore, we adopt approximation technique to save computational cost of optimization process. Metamodels such as response surface model (RSM) and kriging model are used to approximate model-based optimization is described. RSM is easy to obtain and expressed explicit function, but this is not suitable for highly nonlinear and large scaled problems. Kriging model employs an interpolation scheme and is developed in the fields of spatial statistics and geostatistics. Target of this design is to find optimum thickness of AEP to minimize weight of doulbe-deck train carbody. In this study, meta model techniques are introduced to carry out weight minimization of a double-deck train car-body.

• 한국정보통신학회논문지
• /
• 제9권6호
• /
• pp.1174-1181
• /
• 2005

대량의 데이터를 빠르게 전송할 수 있는 UWB(Ultra-widebandwidth) 시간 도약(time hopping : TH) 펄스 위치 변조(pulse position modulation : PPM) 다중 통신 시스템의 비트 오율을 정확히 계산할 수 있는 방법을 소개한다. 본 논문에서 다중 접근 간섭(multiple access interference : MAI)의 통계적 성질을 특성함수 기법을 이용하여 정확히 모델링 하였고 이를 바탕으로 TH-PPM 시스템의 비트 오율을 정확하게 계산할 수 있는 해석 식을 제시하였다. 또한, 기존의 MAI에 대한 가우시안 근사에 비하여 상당히 개선된 정확성을 갖는 근사식을 함께 소개하였다. 본 논문에서 제시한 모델에 의해서 계산된 비트 오율을 Monte-Carlo 시뮬레이션 한 결과와 비교함으로써 제안한 BER 식의 정확성 및 타당성을 검증하였다.

• 한국정밀공학회지
• /
• 제12권10호
• /
• pp.40-49
• /
• 1995

This paper presents the performance and problems in analysis method and testing system of Electronic Speckle Pattern Interferometry (ESPI) method, in measuring two - dimensional in-plane displacement. The anyalysis result of measurement by ESPE is quite comparable to that tof measurement by strain gauge method. This implies that the method of ESPE is a very effective tool in non-contact two-dimensional in-plane strain analysis. But there is a controversal point, measurment error. This error is discussed to be affected not by ESPE method itself, but by its analysis scheme of the interference fringe, where the first-order interpolation has been applied to the points of strain measured. In this case, it is turned out that the more errors would be occurred in the large interval of fringe. And so this paper describes a computer method for drawing when the height is available only for some arbitrary collection of points. The method is based on a distance-weighted, last- squares approximation technique with the weight varying with the distance of the data points.

• Structural Engineering and Mechanics
• /
• 제45권6호
• /
• pp.759-777
• /
• 2013

In this paper, a topology optimization method based on the element independent nodal density (EIND) is developed for continuum solids with multiple load cases and multiple constraints. The optimization problem is formulated ad minimizing the volume subject to displacement constraints. Nodal densities of the finite element mesh are used a the design variable. The nodal densities are interpolated into any point in the design domain by the Shepard interpolation scheme and the Heaviside function. Without using additional constraints (such ad the filtering technique), mesh-independent, checkerboard-free, distinct optimal topology can be obtained. Adopting the rational approximation for material properties (RAMP), the topology optimization procedure is implemented using a solid isotropic material with penalization (SIMP) method and a dual programming optimization algorithm. The computational efficiency is greatly improved by multithread parallel computing with OpenMP to run parallel programs for the shared-memory model of parallel computation. Finally, several examples are presented to demonstrate the effectiveness of the developed techniques.

• 대한조선학회논문집
• /
• 제42권5호
• /
• pp.534-541
• /
• 2005

Until now, Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how in its own. It is very useful to extract knowledge or information from the accumulated existing data by using data mining technique This paper treats an evolutionary computation based on genetic programming (GP), which can be one of the components to realize data mining. The paper deals with linear models of GP for the regression or approximation problem when given learning samples are not sufficient. The linear model, which is a function of unknown parameters, is built through extracting all possible base functions from the standard GP tree by utilizing the symbolic processing algorithm. In addition to a standard linear model consisting of mathematic functions, one variant form of a linear model, which can be built using low order Taylor series and can be converted into the standard form of a polynomial, is considered in this paper. The suggested model can be utilized as a designing tool to predict design parameters with small accumulated data.

• 한국항공우주학회지
• /
• 제41권6호
• /
• pp.465-472
• /
• 2013

본 논문에서는 요구 위치에 정밀 착륙을 위한 낙하산 전개지점 선정 기법을 제안한다. 무인기-낙하산 시스템을 위해 9-DOF 운동 모델을 구성하였고, 신경회로망을 학습시키기 위한 입출력 데이터 셋을 구성하였다. 입력 데이터 셋은 현재 항공기 위치, 속도정보 및 바람 정보로 구성되어 있고, 출력 데이터 셋은 9-DOF 운동 모델을 시뮬레이션 하여 획득한 착륙 위치 정보이다. 이를 이용하여 nonlinear function approximator를 구성함으로써 현재 위치로부터 상대적인 착륙 지점을 예측할 수 있고, 예측된 착륙 지점과 요구 착륙 지점과의 상대적인 거리 오차를 계산하여 이를 보상해줌으로써 낙하산 전개 지점을 결정할 수 있다.

• 한국통신학회논문지
• /
• 제32권7C호
• /
• pp.658-666
• /
• 2007

일반적으로 기존의 선형 위상을 갖는 저역통과 MAXFLAT FIR 필터 설계 방법들은 폐쇄형 전달함수의 특성으로 인하여 하프 주파수 대역 $(0{\leq}w{\leq}{\pi}/2)$에서 이득 응답을 갖는다. 더욱이 주파수 영역에서 MAXFLAT과 선형 위상 특성에 도달하기 위해 추정 알고리즘을 사용하기 때문에 설계 필터들은 저지대역에서의 리플 에러, 완만한 차단감쇠, 위상 및 그룹지연 그리고 부정확한 차단주파수와 같은 문제점들을 가지고 있다. 본 논문에서는 이러한 문제점들을 해결하기 위하여 제로 위상의 광대역 이득 응답을 갖는 MAXFLAT FIR 저역통과 필터 설계를 위한 새로운 수학적인 폐쇄형 전달함수를 제안하였다. 더욱이, 제안된 폐쇄형 전달함수는 임의의 차단 주파수를 포함한 MAXFLAT 조건들을 이용하여 새롭게 유도한 일반화한 공식들로 쉽게 실현됨이 증명되었다. 따라서 제안방식은 간단하고 빠른 설계에 적합하다. 결론적으로 제안된 설계 기술은 제로 위상과 광대역 이득 응답을 갖는 MAXFLAT FIR 저역통과 필터 실현이 가능하며, 설계된 필터들은 모두 250dB가 넘는 최대 차단 감쇠를 갖는 것을 알 수가 있다.

• Journal of electromagnetic engineering and science
• /
• 제16권3호
• /
• pp.169-181
• /
• 2016

This work presents a new method for enhancing the performance of a dual band Planer Inverted-F Antenna (PIFA) and its lumped equivalent circuit formulation. The performance of a PIFA in terms of return loss, bandwidth, gain, and efficiency is improved with the addition of the proposed open stub in the radiating element of the PIFA without disturbing the operating resonance frequencies of the antenna. In specific cases, various simulated and fabricated PIFA models illustrate that the return loss, bandwidth, gain, and efficiency values of antennas with longer optimum open stub lengths can be enhanced up to 4.6 dB, 17%, 1.8 dBi, and 12.4% respectively, when compared with models that do not have open stubs. The proposed open stub is small and does not interfere with the surrounding active modules; therefore, this method is extremely attractive from a practical implementation point of view. The second presented work is a simple procedure for the development of a lumped equivalent circuit model of a dual band PIFA using the rational approximation of its frequency domain response. In this method, the PIFA's measured frequency response is approximated to a rational function using a vector fitting technique and then electrical circuit parameters are extracted from it. The measured results show good agreement with the electrical circuit results. A correlation study between circuit elements and physical open stub lengths in various antenna models is also discussed in detail; this information could be useful for the enhancement of the performance of a PIFA as well as for its systematic design. The computed radiated power obtained using the electrical model is in agreement with the radiated power results obtained through the full wave electromagnetic simulations of the antenna models. The presented approach offers the advantage of saving computation time for full wave EM simulations. In addition, the electrical circuit depicting almost perfect characteristics for return loss and radiated power can be shared with antenna users without sharing the actual antenna structure in cases involving confidentiality limitations.