• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.10
• /
• pp.884-892
• /
• 2014

In this paper, a meta model using neural network substituting for the simulator aerodynamic database is proposed to improve simulation fidelity near the critical flight area and real-time performance. It is shown that the accuracy of the meta model is relatively higher than the existing table lookup methods for arbitrary nonlinear database and the calculation speed is also improved for a specific F-16 maneuver simulation. The increase in the number of hidden nodes in the meta model for better accuracy of database representations causes a delay in function generation due to increased time required for computing exponential functions. In order to make up this drawback, we additionally study the fast exponential function method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.30-36
• /
• 2006

In this paper, we proposed the system that supports underachievers realm decision of Korean language curriculum in the middle school. Learning disability and stagnation should be minimized by using and applying the proposed system. The input layer of the system contains 36 variables, which can be specific items in the Koran language curriculum. The variables are encoded with the specific coding schemes. The number of nodes in the hidden layer was determined through a series of learning stage with best result. We assigned 4 neurons, which correspond to one realm of the curriculum to output layer respectively. We used the multilayer perceptron and the error backpropagation algorithm to develope the system. A total of 2,008 data for training and 380 for testing were used for evaluating the performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.32-43
• /
• 2002

In this paper, we propose a pattern classification system for digital signal which is based on neural networks. The proposed system consists of two models of neural network. The first part is a wavelet neural network whose role is a feature extraction. For this part, we compare existing models of wavelet networks and propose a new model for feature extraction. The other part is a wavelet network for pattern classification. We modify the structure of previous wavelet network for pattern classification and propose a learning method. The inputs of the pattern classification wavelet network is connection weights, dilation and translation parameters in hidden nodes of feature extraction network. And the output is a class of the signal which is input of feature extraction network. The proposed system is, applied to classification of EEG signal based on frequency.

• The Korean Journal of Applied Statistics
• /
• v.32 no.6
• /
• pp.899-908
• /
• 2019

Massive in-depth neural networks with numerous parameters are powerful machine learning methods, but they have overfitting problems due to the excessive flexibility of the models. Dropout is one methods to overcome the problem of oversized neural networks. It is also an effective method that randomly drops input and hidden nodes from the neural network during training. Every sample is fed to a thinned network from an exponential number of different networks. In this study, instead of feeding one sample for each thinned network, two or more samples are used in fitting for one thinned network known as a Hybrid Dropout. Simulation results using real data show that the new method improves the stability of estimates and reduces the minimum error for the verification data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.2
• /
• pp.157-168
• /
• 1993

In this paper, it is shown that neural networks trained with back propagation algorithm and dictionary can be applied to recognize handwritten English characters. To eliminate the useless data part and to minimize the variety of characters from the scanned image file, various preprocessings : that is, segmentation, centering, noise filtering, sealing and thinning are performed. After these, characteristic features are derived from thinned character pattern. The neural network is trained by using the extracted features for sample data, and all test data are classified into English alphabets according to their features through the neural network. Finally, the ways of reducing learning time and improving recognition rate, and the relationship between learning time and hidden layer nodes are considered. As a result of this study, after successful training, a high recognition rate has been obtained with this system for the trained patterns and about 93% for test patterns. Using dictionary, the recognition rate was about 97% for test pattern.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.1-10
• /
• 2001

Neural networks we increasingly being seen as an addition to the statistics toolkit which should be considered alongside both classical and modern statistical methods. Neural networks are usually useful for classification and function estimation. In this paper we concentrate on function estimation using neural networks with weight decay factor The use of weight decay seems both to help the optimization process and to avoid overfitting. In this type of neural networks, the problem to decide the number of hidden nodes, weight decay parameter and iteration number of learning is very important. It is called the optimization of weight decay neural networks. In this paper we propose a automatic optimization based on genetic algorithms. Moreover, we compare the weight decay neural network automatically learned according to automatic optimization with ordinary neural network, projection pursuit regression and support vector machines.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.2
• /
• pp.65-72
• /
• 1990

The potential of neural networks for the recognition of the printed Korean characters is examined. In spite of good classification capability of neural networks, it is difficult to train a neural network to recognize Korean characters. The difficulty is due to a large number of Korean characters, the similarities among the characters, and the large number of data from the character images. To reduce the input image data, DC components are extracted from each input images. These preprocessed data are used as input to the neural network. The output nodes are composed to represent the characteristics of Korean characters. A MLP (multilayer perceptron) with one hidden layer was trained with a modified BEP algorithm, This method gives good recognition rate for the standard positioned characters of more than 2,300. The result shows that neural networks are well suited for the recognition of printed Korean characters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.626-628
• /
• 2018

In this paper, we compare the performances of SVM (Support Vector Machine) and ANN (Artificial Neural Network) machine learning models for predicting solar energy by using meteorological data. Two machine learning models were built by using fifteen kinds of weather data such as long and short wave radiation average, precipitation and temperature. Then the RBF (Radial Basis Function) parameters in the SVM model and the number of hidden layers/nodes and the regularization parameter in the ANN model were found by experimental studies. MAPE (Mean Absolute Percentage Error) and MAE (Mean Absolute Error) were considered as metrics for evaluating the performances of the SVM and ANN models. Sjoem Simulation results showed that the SVM model achieved the performances of MAPE=21.11 and MAE=2281417.65, and the ANN model did the performances of MAPE=19.54 and MAE=2155345.10776.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2017-2024
• /
• 1997

The main focus of this paper is the recognition of printed Hangul documents in terms of typeface, character size and character slope for IICS(Intelligent Image Communication System). The fixed-size blocks extracted from documents are analyzed in frequency domain for the typeface classification. The vertical pixel counts and projection profile of bounding box are used for the character size classification and the character slope classification, respectively. The MLP with variable hidden nodes and error back-propagation algorithm is used as typeface classifier, and Mahalanobis distance is used to classify the character size and slope. The experimental results demonstrated the usefulness of proposed system with the mean rate of 95.19% in typeface classification. 97.34% in character size classification, and 89.09% in character slope classification.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.49-54
• /
• 2003

In this paper, we propose a controller with the self-organizing neural network compensator for compensating PID controller's response. PID controller has simple design method but needs a lot of trials and errors to determine coefficients. A neural network control method does not have optimal structure as the parameters are pre-specified by designers. In this paper, to solve this problem, we use a self-organizing neural network which has Back Propagation Network algorithm using a Gaussian Potential Function as an activation function of hidden layer nodes for compensating PID controller's output. Self-Organizing Neural Network's learning is proceeded by Gaussian Function's Mean, Variance and number which are automatically adjusted. As the results of simulation through the second order plant, we confirmed that the proposed controller get a good response compare with a PID controller. And we implemented the of controller performance hydraulic servo motor system using the DSP processor. Then we observed an experimental results.