• Structural Engineering and Mechanics
• /
• v.52 no.1
• /
• pp.97-113
• /
• 2014

In the present work appropriate concrete material models have been proposed to predict drying shrinkage and specific creep of High-performance concrete (HPC) using Artificial Neural Network (ANN). The ANN models are trained, tested and validated using 106 different experimental measured set of data collected from different literatures. The developed models consist of 12 input parameters which include quantities of ingredients namely ordinary Portland cement, fly ash, silica fume, ground granulated blast-furnace slag, water, and other aggregate to cement ratio, volume to surface area ratio, compressive strength at age of loading, relative humidity, age of drying commencement and age of concrete. The Feed-forward backpropagation networks with Levenberg-Marquardt training function are chosen for proposed ANN models and same implemented on MATLAB platform. The results shows that the proposed ANN models are more rational as well as computationally more efficient to predict time-dependent properties of drying shrinkage and specific creep of HPC with high level accuracy.

• Journal of Magnetics
• /
• v.5 no.2
• /
• pp.27-34
• /
• 2000

The structure of a series of Cu/Ni is characterized by using a program, SUPREX, to model the x-ray diffraction patterns, multilayers. The samples had nominal layer thickness of 3/3, 7/7, 13.5/13.5, 20/20, 30/30, 50/50, 80/80, 100/100, and 200/200 Angstroms. The diffraction patterns were taken around the (111) peak for the two constituent materials. A kinematical model is used to characterize the diffraction patterns and the parameters for the model are described. An initial model is calculated using initial guesses for the parameters. The model is then fit to the data by reducing $x^2$using the Levenberg-Marquardt algorithm. The samples are shown to be high quality supperlattices.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.143-148
• /
• 2008

A real-time face detection is to find human faces robustly under the cluttered background free from the effect of occlusion by other objects or various lightening conditions. We propose a face detection system for real-time applications using wavelet decomposition method based on Gabor features. Firstly, skin candidate regions are extracted from the given image by skin color filtering and projection method. Then Gabor-feature based template matching is performed to choose face cadidate from the skin candidate regions. The chosen face candidate region is transformed into 2-level wavelet decomposition images, from which feature vectors are extracted for classification. Based on the extracted feature vectors, the face candidate region is finally classified into either face or nonface class by the Levenberg-Marguardt back-propagation neural network.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.1606-1609
• /
• 2008

In this paper, we present a novel process for the realization of large area, low cost field emission cathodes. The process makes use of alumina substrates, which are anodically oxidized in order to yield porous structures capable of hosting metal catalyst nanoparticles. By carefully controlling the final stage of the anodisation as well as the electrodeposition conditions, it is possible to fine tune the density of such catalysts in the range of $10^8-10^9/cm^2$. The catalytic growth of CNTs is subsequently performed at low temperature (${\sim}\;600^{\circ}C$ or below, thanks to the use of $H_2O$), using plasma enhanced chemical vapour deposition. There is no lithography need to make the cathode and current densities of ${\sim}\;1mA/cm^2$ are easily obtained.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.08a
• /
• pp.37-44
• /
• 2004

Continuous depth data are often required in applications of both onboard systems and maritime simulation. But data available are usually discrete and irregularly distributed. Based on the neuron network technique, methods of interpolation to the charted depth are suggested in this paper. Two algorithms based on Levenberg-Marquardt back-propaganda and radial-basis function networks are investigated respectively. A dynamic neuron network system is developed which satisfies both real time and mass processing applications. Using hyperbolic paraboloid and typical chart area, effectiveness of the algorithms is tested and error analysis presented. Special process in practical applications such as partition of lager areas, normalization and selection of depth contour data are also illustrated.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2003.07a
• /
• pp.32-35
• /
• 2003

Nonlinear parameterization of OLED device from measurements of bias dependence of impedance spectra and parameter extraction using Levenberg-Marquardt complex nonlinear least square regression algorithm based on resistor-capacitor equivalent circuit model enables computer simulation of OLED power driving characteristics in forms of square-wave or sinusoidal output signal at arbitrary conditions. We introduce developed OLED power driving simulation software and discuss transient responses in voltage-or current-controlled operations as well as nonlinear characteristics of OLED, by presenting both the simulation and experimental results. This OLED simulation technique using impedance spectroscopy is extremely useful in predicting performance of the nonlinear device, especially in time-domain analysis of device operation.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.849-856
• /
• 2003

본 논문에서는 다층 퍼셉트론의 학습을 위한 새로운 두 단계 학습방법을 제안하였다. 첫 번째 단계는 국소최적해로 빨리 수렴하기 위해 Levenberg-Marquardt 알고리즘을 이용한 국소 탐색 단계이다. 두 번째 단계는 첫 번째 단계에서 찾은 국소최적해가 원하는 수준에 미치지 못할 경우 새로운 국소최적해로 벗어나기 위한 선형탐색을 기반의 터널링 단계이다. 이 방법은 연결가중치 공간에서 전역최적해를 빠르게 찾을 수 잇는 새로운 방법을 제공한다. 4가지 벤치마크 문제에 기존의 다층 퍼셉트론의 학습 알고리즘과 비교 실험을 통해, 제안된 알고리즘이 빠른 수렴 속도와 낮은 오차값을 가짐을 알 수 있었다.

• ETRI Journal
• /
• v.34 no.5
• /
• pp.696-705
• /
• 2012

Accurate synthesis models based on artificial neural networks (ANNs) are proposed to directly obtain the physical dimensions of an asymmetric coplanar waveguide with conductor backing and substrate overlaying (ACPWCBSO). First, the ACPWCBSO is analyzed with the conformal mapping technique (CMT) to obtain the training data. Then, a modified genetic-algorithm-Levenberg-Marquardt (GA-LM) algorithm is adopted to train ANNs. In the algorithm, the maximal relative error (MRE) is used as the fitness function of the chromosomes to guarantee that the MRE is small, while the mean square error is used as the error function in LM training to ensure that the average relative error is small. The MRE of ANNs trained with the modified GA-LM algorithm is less than 8.1%, which is smaller than those trained with the existing GA-LM algorithm and the LM algorithm (greater than 15%). Lastly, the ANN synthesis models are validated by the CMT analysis, electromagnetic simulation, and measurements.

• Journal of the Korean Society for Precision Engineering
• /
• v.34 no.1
• /
• pp.23-27
• /
• 2017

This paper aims to develop a prediction model for the product quality of a casting process. Prediction of the product quality utilizes an artificial neural network (ANN) in order to renovate the manufacturing technology of the root industry. Various aspects of the research on the prediction algorithm for the casting process using an ANN have been investigated. First, the key process parameters have been selected by means of a statistics analysis of the process data. Then, the optimal number of the layers and neurons in the ANN structure is established. Next, feed-forward back propagation and the Levenberg-Marquardt algorithm are selected to be used for training. Simulation of the predicted product quality shows that the prediction is accurate. Finally, the proposed method shows that use of the ANN can be an effective tool for predicting the results of the casting process.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.4
• /
• pp.1017-1026
• /
• 2005

We consider the problem of modeling count data where the observation period is determined by the survival time of the individual under study. We assume random effects or frailty model to allow for a possible association between the death times and the counts. We assume that, given a random effect, the death times follow a Weibull distribution with a rate that depends on some covariates. For the counts, given the random effect, a Poisson process is assumed with the intensity depending on time and the covariates. A gamma model is assumed for the random effect. Maximum likelihood estimators of the model parameters are obtained. The model is applied to data set of patients with breast cancer who received a bone marrow transplant. A model for the time to death and the number of supportive transfusions a patient received is constructed and consequences of the model are examined.