• 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 the Korean Society for Nondestructive Testing
• /
• v.19 no.4
• /
• pp.277-287
• /
• 1999

Quasi-static tests such as monotonic tension and loading/unloading tension were performed to investigate the bond characteristics and the failure processes for the T-joint specimens made from fiber/epoxy composite material. Two types of specimens, each consists of two components, e. g. skin and frame. were manufactured by co-curing and secondary bonding. During the monotonic tension test, AE instrument was used to predict AE signal at the initial and middle stage of the damage propagation. The damage initiation and progression were monitored optically using m (Charge Coupled Device) camera. And the internal crack front profile was examined using ultrasonic C-scan. The results indicate that the loads representing the abrupt increase of the AE signal are within the error range of 5 percent comparing to the loads shown in the load-time curve. Also it is shown that the initiation of crack occurred in the noodle region for both co-cured and secondarily bonded specimen. The final failure occurred in the noodle region for the co-cured specimen. but at the skin/frame termination point for the secondarily bonded specimen. Based on the results, it was found that two kinds of specimen show different failure modes depending on the manufacturing methods.

• 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 Advanced Marine Engineering and Technology
• /
• v.40 no.1
• /
• pp.45-49
• /
• 2016

The performance of underwater acoustic communication systems is sensitive to inter-symbol interference caused by delay spread developed from multipath signal propagation. The multipath nature of underwater channels causes signal distortion and error floor. In order to improve the performance, it is necessary to employ an iterative coding scheme. Of the various iterative coding schemes, turbo code and convolutional code based on the BCJR algorithm have recently dominated this application. In this study, the performance of iterative codes based on turbo equalizers with equivalent coding rates and similar code word lengths were analyzed. Underwater acoustic communication system experiments using these two coding techniques were conducted on Kyeong-chun Lake in Munkyeong City. The distance between the transmitter and receiver was 400 m, and the data transfer rate was 1 Kbps. The experimental results revealed that the performance of turbo codes is better for channeling than that of convolutional codes that use a BCJR decoding algorithm.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.12
• /
• pp.48-58
• /
• 2006

The spray and combustion characteristics of liquid jet in cross flow with variation of injection angle are numerically studied. Numerical analysis was carried out using KIVA code, which may be used to generate numerical solutions to spray and chemical reactive fluid problem in three space dimensions and modified to be suitable for simulating liquid jet ejected into the cross flow. Wave model and Kelvin- Helmholtz(KH) /Rayleigh-Taylor(RT) hybrid model were used for the purpose of analyzing liquid column, ligament, and the breakup of droplet. Penetration length increases as flow velocity decreases and injection velocity increases. Numerical error increases as inflow velocity increases. The results of flame propagation contour in combustion chamber and local temperature distribution, combustion emissions were obtained.

• 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.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of Sensor Science and Technology
• /
• v.7 no.6
• /
• pp.418-425
• /
• 1998

Stereo cameras are the most widely used sensing systems for automated machines including robots to interact with their three-dimensional(3D) working environments. The position of a target point in the 3D world coordinates can be measured by the use of stereo cameras and the camera calibration is an important preliminary step for the task. Existing camera calibration techniques can be classified into two large categories - linear and nonlinear techniques. While linear techniques are simple but somewhat inaccurate, the nonlinear ones require a modeling process to compensate for the lens distortion and a rather complicated procedure to solve the nonlinear equations. In this paper, a method employing a neural network for the calibration problem is described for tackling the problems arisen when existing techniques are applied and the results are reported. Particularly, it is shown experimentally that by utilizing the function approximation capability of multi-layer neural networks trained by the back-propagation(BP) algorithm to learn the error pattern of a linear technique, the measurement accuracy can be simply and efficiently increased.