• 비파괴검사학회지
• /
• 제25권6호
• /
• pp.475-482
• /
• 2005

The iterative calculation by least square method was used to determine the source location of acoustic emission in rock, as so called "traditional method". The results were compared with source coordinates infered from the application of neural network system for new input data, as so called "new method". Input data of the neural network were based on the time differences of longitudinal waves arrived from acoustic emission events at each transducer, the variation of longitudinal velocities at each stress level, and the coordinates of transducer as in the traditional method. The momentum back propagation neural network system adopted to determine source location, which consists of three layers, and has twenty-seven input processing elements. Applicability of the new method were identified, since the results of source location by the application of two methods were similarly concordant.

• 한국전자통신학회논문지
• /
• 제5권2호
• /
• pp.145-151
• /
• 2010

본 논문에서는 두 개의 음으로부터 전달되어온 음장의 상태를 구하여 역 필터를 구성하는 적응필터 및 신경회로망을 사용한 음장의 역 필터링 시스템을 제안한다. 본 논문에서는 최소 2승 평균법을 사용하여 FIR 필터의 계수를 계산하여 이를 갱신함으로써 역 필터링을 구축하는 방법을 사용한다. 본 논문에서 제안한 신경회로망 및 적응필터의 기법에 의하여 비선형 왜곡이 있는 간단한 파형이 학습 가능한 것을 실험 결과로부터 확인할 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 추계학술대회
• /
• pp.695-698
• /
• 2009

본 논문에서는 음원으로부터 나온 음과 동일한 음을 들을 수 있는 시스템을 구축하는 것을 목적으로 하여 이 두 개의 음으로부터 전달되어온 음장의 상태를 구하여 이 역 필터를 구성하는 방법을 연구한다. 본 논문에서는 최소 2승 평균법(Least Mean Square, LMS)을 사용하여 FIR 필터(Finite Impulse Response)의 계수를 계산하여 이를 갱신함으로써 역 필터법을 구축하는 방법을 사용한다. 또한 이 방법과는 별도로 LMS법의 부분을 신경회로망에 대처하는 알고리즘을 제안하였다. 시뮬레이션 실험으로부터 상당히 간단한 파형에 비선형인 왜곡이 있는 것을 본 논문에서 제안한 신경회로망에 의한 학습 가능한 것을 확인하였다.

• Smart Structures and Systems
• /
• 제19권4호
• /
• pp.383-391
• /
• 2017

In this paper, we investigate the impacts of network topology on the performance of a distributed estimation algorithm, namely combine-then-adaptive (CTA) diffusion LMS, based on the data with or without the assumptions of temporal and spatial independence with noisy links. The study covers different network models, including the regular, small-world, random and scale-free whose the performance is analyzed according to the mean stability, mean-square errors, communication cost (link density) and robustness. Simulation results show that the noisy links do not cause divergence in the networks. Also, among the networks, the scale free network (heterogeneous) has the best performance in the steady state of the mean square deviation (MSD) while the regular is the worst case. The robustness of the networks against the issues like node failure and noisier node conditions is discussed as well as providing some guidelines on the design of a network in real condition such that the qualities of estimations are optimized.

• Journal of applied mathematics & informatics
• /
• 제26권5_6호
• /
• pp.911-923
• /
• 2008

The neural networks (NNs) simulation has been designed to simulate and predict the vortex wavelength ${\lambda}_x^*$, lateral vortex spacing ${\lambda}_y^*$, and normalized maximum vorticity at the vortex center near the wake of square cylinders with different corner radii. The system was trained on the available data of the three cases, although this data is very little. Therefore, we designed the system to work in automatic way for finding the best network that has the ability to have the best test and prediction. The proposed system shows an excellent agreement with that of an experimental data in these cases. The technique has been also designed to simulate the other distributions not presented in the training set and predicted them with effective matching.

• International Journal of Concrete Structures and Materials
• /
• 제5권1호
• /
• pp.29-33
• /
• 2011

This article employs Least Square Support Vector Machine (LSSVM) for determination of fracture parameters of concrete: critical stress intensity factor ($K_{Ic}^s$) and the critical crack tip opening displacement ($CTOD_c$). LSSVM that is firmly based on the theory of statistical learning theory uses regression technique. The results are compared with a widely used Artificial Neural Network (ANN) Models of LSSVM have been developed for prediction of $K_{Ic}^s$ and $CTOD_c$, and then a sensitivity analysis has been performed to investigate the importance of the input parameters. Equations have been also developed for determination of $K_{Ic}^s$ and $CTOD_c$. The developed LSSVM also gives error bar. The results show that the developed model of LSSVM is very predictable in order to determine fracture parameters of concrete.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.394-394
• /
• 2000

This Paper proposes a new nonlinear partial least square method that extends the linear PLS. Proposed nonlinear PLS uses self-organizing feature map as PLS outer relation and multilayer neural network as PLS inner regression method.

• 한국강구조학회 논문집
• /
• 제10권3호통권36호
• /
• pp.463-472
• /
• 1998

본 논문의 목적은 4각형네트워크 패턴을 가지는 단층래티스돔의 좌굴특성을 실험과 이론을 통하여 검토하고, 나아가 4각형 네트워크 단층돔에 대한 신뢰할 수 있는 이론해석법을 개발하기 위한 기초연구를 하는데 그 목적이 있다. 이론해석은 야마다의 연속체치환법과 유한요소법에 의한 프레임해석법으로 한다. 원주방향에 대한 불균일한 강성과 지붕재료의 강성이 돔전체 좌굴특성에 미치는 영향을 검토한다. 이론과 실험에 의한 결과는 불균일한 강성을 가지거나 또는 강성을 갖는 지붕재료를 사용하는 다양한 종류의 단층래티스돔에 대한 일반적인 이론해석법을 개발하기 위한 기초자료로 활용될 것이다.

• Computers and Concrete
• /
• 제5권5호
• /
• pp.461-473
• /
• 2008

The paper explores the potential of Support Vector Machines (SVM) approach in predicting 28-day compressive strength and slump flow of self-compacting concrete. Total of 80 data collected from the exiting literature were used in present work. To compare the performance of the technique, prediction was also done using a back propagation neural network model. For this data-set, RBF kernel worked well in comparison to polynomial kernel based support vector machines and provide a root mean square error of 4.688 (MPa) (correlation coefficient=0.942) for 28-day compressive strength prediction and a root mean square error of 7.825 cm (correlation coefficient=0.931) for slump flow. Results obtained for RMSE and correlation coefficient suggested a comparable performance by Support Vector Machine approach to neural network approach for both 28-day compressive strength and slump flow prediction.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.537-539
• /
• 1998

In this paper, we construct the on-line model structure for the nonlinear process systems using the adaptive fuzzy-neural network. Adaptive fuzzy-neural network usually consists of two distinct modifiable structure, with both, the premise and the consequent part. These two parts can be adapted by different optimization methods, which are the hybrid learning procedure combining gradient descent method and least square method. To achieve the on-line model structure, we use the recursive least square method for the consequent parameter identification of nonlinear process. We design the interface between PLC and main computer, and construct the monitoring and control simulator for the nonlinear process. The proposed on-line modeling to real process is carried out to obtain the effective and accurate results.