• Journal of radiological science and technology
• /
• v.30 no.4
• /
• pp.419-426
• /
• 2007

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize taste(bitter, sweet, sour and salty) pattern vectors. The signal intensity of taste are used to compose the input pattern vectors. The SOM(Self Organizing Maps) algorithm for taste pattern recognition is used to learn initial reference vectors and the ot-star learning algorithm is used to determine the class of the output neurons of the sunclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ(Learning Vector Quantization) algorithm. The pattern vectors are classified into subclasses by neurons in the subclass layer, and the weights between subclass layer and output layer are learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors, the proposed algorithm is simulated with ones of the conventional LVQ, and it is confirmed that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.95-103
• /
• 2006

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize EEG pattern vectors. The frequency and amplitude of alpha rhythms and beta rhythms are used to compose the input pattern vectors. And the algorithm for EEG pattern recognition is used SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of the subclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights between subclass layer and output layer is learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors of EEG, the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.5
• /
• pp.187-196
• /
• 2003

Effects of Airgap and anisotropy substrate on input impedance and radiation pattern of rectangular microstrip patch antenna are studied in terms of an integral equation formulation. The input impedance and radiation pattern of microstrip patch antenna is investigated by using Galerkin's moment method in solving the integral equation. Sinusoidal functions are selected as basis functions, which resemble in the actual standing wave on the Patch. From the numerical results, the variation of input impedance and radiation patterns in the variation of air gap thickness, anisotropy ratio of substrate, and relative permittivity of anisotropy substrate are presented.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.129-131
• /
• 2006

The performances of neural network systems mainly depend on the kind and the number of input patterns for its training. Hence, the kind of input patterns as well as its number is very important for the character recognition system using back-propagation network. The more input patters are used, the better the system recognizes various characters. However, training is not always successful as the number of input patters increases. Moreover, there exists a limit to consider many input patterns of the recognition system for cursive script characters. In this paper we present a new character recognition system using the back-propagation neural networks. By using an additional neural network, an input pattern generation method is provided for increasing the recognition ratio and a successful training. We firstly introduce the structure of the proposed system. Then, the character recognition system is investigated through some experiments.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.12
• /
• pp.1956-1964
• /
• 1989

In this paper, a new method of Hangul recognition is proposed to solve the problems of misrecognition owing to the contacts of FCEs (Fundamental Character Elements) in a Hangul pattern. Structures of FCFs are represented with PAG(Programmed Array Grammar) to recognize an input pattern on 2-D. array of pels., and the unnecessary deformation of the conventional approach can be eliminated by using PEACE parsing which extracts primitives and computes attributes in the course of analyzing the structure of an input pattern. Also, primitive transformation at contacts can afford to confirm all the possible structures of an input pattern and solve the problem of misrecognition owing to the contacts of FCEs. The recognition rate of proposed method for printed Hangul characters shows 96.2% for 1978 Gothic-letters and 92.0% for 1920 Myng-style-letters, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.1 no.3
• /
• pp.4-19
• /
• 1991

In this paper, we propose a fuzzy neural network pattern classifier utilizing fuzzy information. This system works without any a priori information about the number of clusters or cluster centers. It classifies each input according to the distance between the weights and the normalized input using Bezdek's [1] fuzzy membership value equation. This model returns the correct membership value for each input vector and find several cluster centers. Some experimental studies of comparison with other algorithms will be presented for sample data sets.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.594-600
• /
• 2017

The new design methodology of prediction model and pattern classification, which is based on the dimension reduction algorithm called principal component analysis, is introduced in this paper. Principal component analysis is one of dimension reduction techniques which are used to reduce the dimension of the input space and extract some good features from the original input variables. The extracted input variables are applied to the prediction model and pattern classifier as the input variables. The introduced prediction model and pattern classifier are based on the very simple regression which is the key point of the paper. The structural simplicity of the prediction model and pattern classifier leads to reducing the over-fitting problem. In order to validate the proposed prediction model and pattern classifier, several machine learning data sets are used.

• Korean Journal of Optics and Photonics
• /
• v.12 no.1
• /
• pp.55-60
• /
• 2001

We propose a method to extract features optically from the input pattern by use of an array of Hough transfOllli filters. Here the subparts of the input pattern are Hough-transformed by. their cOlTesponding elements of the filter array independently and simultaneously. Compared with the conventional method, in which the whole input pattern is Hough-transformed by a single optical filter, the proposed method not only provides the improved optical transform results when the input pattern becomes complex but also extracts the approximate position information of the line segment features. To show the feasibility of this approach, we fabricated a $5\times5$ filter array and performed preliminary experiments.iments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.181-189
• /
• 2013

In this paper, we introduce the fuzzy neural network based on the individual input space to design the pattern recognizer. The proposed networks configure the network by individually dividing each input space. The premise part of the networks is independently composed of the fuzzy partition of individual input spaces and the consequence part of the networks is represented by polynomial functions. The learning of fuzzy neural networks is realized by adjusting connection weights of the neurons in the consequent part of the fuzzy rules and it follows a back-propagation algorithm. In addition, in order to optimize the parameters of the proposed network, we use real-coded genetic algorithms. Finally, we design the optimized pattern recognizer using the experimental data for pattern recognition.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.