• Journal of Korean Association for Spatial Structures
• /
• v.18 no.4
• /
• pp.69-80
• /
• 2018

In this study, an algorithm applying deep learning to the truss structures was proposed. Deep learning is a method of raising the accuracy of machine learning by creating a neural networks in a computer. Neural networks consist of input layers, hidden layers and output layers. Numerous studies have focused on the introduction of neural networks and performed under limited examples and conditions, but this study focused on two- and three-dimensional truss structures to prove the effectiveness of algorithms. and the training phase was divided into training model based on the dataset size and epochs. At these case, a specific data value was selected and the error rate was shown by comparing the actual data value with the predicted value, and the error rate decreases as the data set and the number of hidden layers increases. In consequence, it showed that it is possible to predict the result quickly and accurately without using a numerical analysis program when applying the deep learning technique to the field of structural analysis.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2011.04a
• /
• pp.308-314
• /
• 2011

The research which sees, the parameters inputs and acoustic measurement result in simulation error most on a large scale concreteness of 3D models which affect number of effective surface. Therefore DATA of above the comparison which will listen, analyzed and investigated.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.3
• /
• pp.29-34
• /
• 2001

In this paper, a new associative memory system for analog time-sequential data processing is proposed. This system effectively associate time-sequential data using not only matching with present data but also matching with past data. Furthermore in order to improve error correction ability, weight varying in time domain is introduced in this system. The network is simulated with several periodic time-sequential input patterns including noise. The results show that the proposed system has ability to correct input errors. We expect that the proposed system may be applied for a real time processing of analog time-sequential information.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.827-833
• /
• 2016

In this paper, we propose a deep least squares support vector machine (LS-SVM) for regression problems, which consists of the input layer and the hidden layer. In the hidden layer, LS-SVMs are trained with the original input variables and the perturbed responses. For the final output, the main LS-SVM is trained with the outputs from LS-SVMs of the hidden layer as input variables and the original responses. In contrast to the multilayer neural network (MNN), LS-SVMs in the deep LS-SVM are trained to minimize the penalized objective function. Thus, the learning dynamics of the deep LS-SVM are entirely different from MNN in which all weights and biases are trained to minimize one final error function. When compared to MNN approaches, the deep LS-SVM does not make use of any combination weights, but trains all LS-SVMs in the architecture. Experimental results from real datasets illustrate that the deep LS-SVM significantly outperforms state of the art machine learning methods on regression problems.

• Journal of the Korean Society of Safety
• /
• v.26 no.4
• /
• pp.96-101
• /
• 2011

In previous studies, a system was developed for classifying items of uninsured cost and for generating factors and formulas by item for calculating accident loss costs. However, the loss cost of stopped production was not considered when the system was being developed. In addition, the system which was developed in previous studies had problems such as input error and data collection, owing to numerous input items. Therefore, this study developed a Revised system which considers the loss cost of stopped production, and a Simple system for improving the problems in input errors and data collection. In this study, unquantifiable factors were not considered. Further study that takes these factors into consideration is necessary.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.23-30
• /
• 2021

This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.664-667
• /
• 1997

For higher component density per chip, it is necessary to identify and control the semiconductor manufacturing process more stringently. Recently, neural networks have been identified as one of the most promising techniques for modeling and control of complicated processes such as plasma etching process. Since wafer states after each run using identical recipe may differ from each other, conventional neural network models utilizing input factors only cannot represent the actual state of process and equipment. In this paper, in addition to the input factors of the recipe, real-time tool data are utilized for modeling of 64M DRAM s-poly plasma etching process to reflect the actual state of process and equipment. For real-time tool data, we collect optical emission spectroscopy (OES) data. Through principal component analysis (PCA), we extract principal components from entire OES data. And then these principal components are included to input parameters of neural network model. Finally neural network model is trained using feed forward error back propagation (FFEBP) algorithm. As a results, simulation results exhibit good wafer state prediction capability after plasma etching process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.360-365
• /
• 2003

In this paper, GMDH(Croup Method of Data Handling) algorithm which is proved to be more excellent in efficiency and accuracy of practical use of data is applied to electric power demand forecasting. As a result, it became much easier to make a choice of input data and make an exact prediction based on a lot of data. Also, we considered both economy factors(GDP, export, import, number of employee, number of economically active population and consumption of oil) and climate factors(average temperature) when forecasting. We assumed target forecast period from first quarter 1999 to first quarter 2001, and suggested more accurate forecasting method of electric power demand by using 3-step computer simulation processes(first process for selecting optimum input period, second for analyzing time relation of input data and forecast value, and third for optimizing input data) for improvement of forecast precision. The proposed method can get 0.96 percent of mean error rate at target forecast period.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.10
• /
• pp.46-55
• /
• 1996

As industrial standard data, the STL format which approximates three dimensional CAD model to triangular facets, is used for RP(Rapid Prototyping) system in recent days. Because most RP system take the only form of two dimensional line segments as an input stream inspite of its imperfectness while converting into STL format, a CAD model is converted into a standard industrial format which is composed of many triangular facets. The error verifying process is composed of four main steps, and these are 1) Remove facets with two or more vertices equal to each other. 2) Fix overlapping error such as more than three facets adjacent to anedge. 3) Fill holes in the mesh by using Delaunay triangulation method. 4) Correct the wrong direction and normal vectors. This paper is concerned with serching the mentioned errors in advance and modifying them.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.367-368
• /
• 2006

This paper presents an analytic derivation of phase measurement error. The analysis derives the measurement error caused by the finite-bit quantization of both input signals and twiddle factors used in the recursive implementation of the phasor measurement algorithm. The derivation is based on the statistical exploration of the error dynamic equations. The effect of frequency deviation and the number of DFT points are also included in the study. The analysis results are verified with the data obtained from the computer simulation by widely varying the values of error causing factors.