• Journal of the Korean Geotechnical Society
• /
• v.15 no.1
• /
• pp.99-112
• /
• 1999

By using 92 values of lateral earth pressure coefficient(K) measured in Korea, the tendency of K with varying depth is analyzed and compared with the range of K defined by Hoek and Brown. The horizontal stress is generally larger than the vertical stress in Korea : About 84 % of K values are above 1. In this study, the theory of elasto-plasticity is applied to analyze the variation of K values, and the results are compared with those of numerical analysis. This reveals that the erosion, sedimentation and weathering of earth crust are important factors in the determination of K values. Surface erosion, large lateral pressure and good rock mass increase the K values, but sedimentation decreases the K values. This study enable us to analyze the effects of geological processes on the K values, especially at shallow depth where underground excavation takes place. A neural network expert system using multi-layer back-propagation algorithm is developed to predict the K values. The neural network model has a correlation coefficient above 0.996 when it is compared with measured data. The comparison with 9 measured data which are not included in the back-propagation learning has shown an average inference error of 20% and the correlation coefficient above 0.95. The expert system developed in this study can be used for reliable determination of K values.

• Geotechnical Engineering
• /
• v.10 no.4
• /
• pp.17-28
• /
• 1994

It is well known that human brain has the advantage of handling disperse and parallel distributed data efficiently. On the basic of this fact, artificial neural networks theory was developed and has been applied to various fields of science successfully. In this study, error back propagation algorithm which is one of the teaching technique of artificial neural networks is applied to predict ultimate bearing capacity of pile foundations. For the verification of applicability of this system, a total of 28 data of model pile test results are used. The 9, 14 and 21 test data respectively out of the total 28 data are used for training the networks, and the others are used for the comparison between the predicted and the measured. The results show that the developed system can provide a good matching with model pile test results by training with data more than 14. These limited results show the possibility of utilizing the neural networks for pile capacity prediction problems.

• Journal of Biosystems Engineering
• /
• v.37 no.4
• /
• pp.271-278
• /
• 2012

Worldwide trends in animal welfare have resulted in an increased interest in individual management of sows housed in groups within hog barns. Estrus detection has been shown to be one of the greatest determinants of sow productivity. Purpose: We conducted this study to develop a method that can automatically detect the estrus state of a sow by selecting optimal texture parameters from images of a sow's pudendum and by optimizing the number of neurons in the hidden layer of an artificial neural network. Methods: Texture parameters were analyzed according to changes in a sow's pudendum in estrus such as mucus secretion and expansion. Of the texture parameters, eight gray level co-occurrence matrix (GLCM) parameters were used for image analysis. The image states were classified into ten grades for each GLCM parameter, and an artificial neural network was formed using the values for each grade as inputs to discriminate the estrus state of sows. The number of hidden layer neurons in the artificial neural network is an important parameter in neural network design. Therefore, we determined the optimal number of hidden layer units using a trial and error method while increasing the number of neurons. Results: Fifteen hidden layers were determined to be optimal for use in the artificial neural network designed in this study. Thirty images of 10 sows were used for learning, and then 30 different images of 10 sows were used for verification. Conclusions: For learning, the back propagation neural network (BPN) algorithm was used to successful estimate six texture parameters (homogeneity, angular second moment, energy, maximum probability, entropy, and GLCM correlation). Based on the verification results, homogeneity was determined to be the most important texture parameter, and resulted in an estrus detection rate of 70%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.4
• /
• pp.554-561
• /
• 2013

In this paper, we introduce a modeling and a process simulator developed with the aid of pRBFNNs for activated sludge process in the sewage treatment system. Activated sludge process(ASP) of sewage treatment system facilities is a process that handles biological treatment reaction and is a very complex system with non-linear characteristics. In this paper, we carry out modeling by using essential ASP factors such as water effluent quality, the manipulated value of various pumps, and water inflow quality, and so on. Intelligent algorithms used for constructing process simulator are developed by considering multi-output polynomial radial basis function Neural Networks(pRBFNNs) as well as Fuzzy C-Means clustering and Particle Swarm Optimization. Here, the apexes of the antecedent gaussian functions of fuzzy rules are decided by C-means clustering algorithm and the apexes of the consequent part of fuzzy rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The coefficients of the consequent polynomial of fuzzy rules and performance index are considered by the Least Square Estimation and Mean Squared Error. The descriptions of developed process simulator architecture and ensuing operation method are handled.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.6
• /
• pp.709-717
• /
• 2002

A new multi constant modulus algorithm (MCMA) for a blind decision feedback equalizer is proposed. In order to avoid the error propagation problem in the conventional DFE structure, Feed-Back Filter coefficients are updated only after Feed-Forward Filter coefficients are sufficiently converged to the steady state. Therefore, it has the problem of slow convergence speed characteristics. To overcome this drawback, the proposed MCMA algorithm uses not only new cost function considering the minimum distance between the received signal and the representative value containing the statistical characteristics of the transmitted signal, but also adaptive step-size according to the equalizer outputs to fast convergence speed of FBF. Simulations were carried out under the certified communication channel environment to evaluate a performance of the proposed equalizer. The simulation results show that the proposed equalizer has an improved convergence and SER performance compared with previous methods. The proposed techniques offer the possibility of practical equalization for cable modem and terrestrial HDTV broadcast (using 8-VSB or 64-QAM) applications.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.7
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• Journal of Biomedical Engineering Research
• /
• v.24 no.2
• /
• pp.99-106
• /
• 2003

In this paper, a method of discriminating EEG for diagnoses of mental activity is proposed. The proposed method for classification of schizophrenia and normal EEG is based on the wavelet transform and the artificial neural network. The wavelet coefficients of $\alpha$ band, $\beta$ band, $\theta$ band, and $\delta$ band are obtained using the wavelet transform. The magnitude, mean, and variance of wavelet coefficients for each EEG band are applied to the input data of the system's ANN. The architecture of the ANN s a four layered feedforward network with two hidden layer which implements the error back propagation learning algorithm. Through the classification of schizophrenia composed of 19 ANNs corresponding to 19 channels, the classifying system show that it can classify the 100% of the normal EEG group and the 86.67% of the schizophrenia EEG group.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.17-33
• /
• 2005

This paper presents the proposed a classifier of liver cirrhotic step using MR(magnetic resonance) imaging and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were analysis in the number of data was 231. We extracted liver region and nodule region from T1-weight MR liver image. Then objective interpretation classifier of liver cirrhotic steps. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier learned through error back-propagation algorithm. A classifying result shows that recognition rate of normal is $100\%$, 1type is $82.8\%$, 2type is $87.1\%$, 3type is $84.2\%$. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.107-113
• /
• 2014

In this paper, controller Propose to prevent compressor surge and improve the transient response of the fuel flow control system of turbojet engine. Turbojet engine controller is designed by applying Artificial Neural Network PID control algorithm and make an inference by applying Artificial Neural Network Error Back Propagation Algorithm. To prevent any surge or a flame out event during the engine acceleration or deceleration, the ANN PID controller effectively controls the fuel flow input of the control system. ANN PID results are used as the fuel flow control inputs to prevent compressor surge and flame-out for turbo-jet engine and the controller is designed to converge to the desired speed quickly and safely. Using MATLAB to perform computer simulations verified the performance of the proposed controller. Response characteristics pursuant to the gain were analyzed by simulation.