• Journal of KIISE:Software and Applications
• /
• v.27 no.11
• /
• pp.1082-1087
• /
• 2000

신경회로망 구조의 정제(精製)는 회로망의 일반화능력이나 효율성의 관점에서 중요한 문제이다. 본 논문에서는 feed-forward neural networks로부터 은닉지식을 추출하는 방법을 사용하여 네트워크 재구성을 통한 정제방법을 제안한다. 먼저, 효율적인 if-then rule 추출방법을 제시하고 그 추출된 룰들을 사용하여 룰기반 네트워크로 변환하는 과정을 보여준다. 생성된 룰기반 네트워크 fully connected network에 비하여 상당히 축소된 연결 복잡도를 가지게 되며 일반적으로 더 우수한 일반화능력을 가지게 된다. 본 연구는 도메인 지식이 없이 데이타만 사용하여 어떻게 정제된 룰기반 신경망회로를 생성하고 있는가를 보여준다. 도메인 데이타들에 대한 실험결과도 제시하였다.

• Proceedings of the KIPE Conference
• /
• 2015.11a
• /
• pp.185-186
• /
• 2015

This paper introduces general single PLL(Phase Locked Loop) algorithm and compares with proposed PLL method. The suggested PLL uses low pass filter to reduce high harmonics in real grid and uses feed forward method to compensate phase delay of the low pass filter.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.49.1-49
• /
• 2001

The skin color model is a very important concept in face detection, face recognition and face tracking. Usually, this model is obtained by estimating a probability density function of skin color distribution. In many cases, it is assumed that the underlying density function follows a Gaussian distribution. In this paper, a new method for non-parametric estimation of the probability density function, by using feed-forward neural network, is used to estimate the underlying skin color model. By using this method, the resulting skin color model is better than the Gaussian estimation and substantially approaches the real distribution. Applications to face detection and face ...

• Membrane Journal
• /
• v.33 no.6
• /
• pp.383-389
• /
• 2023

A high-performance forward osmosis (FO) membrane was prepared using polyethylene glycol diacrylate (PEGDA) hydrogel as a support layer. Through the UV-induced polymerization and subsequent phase separation of PEGDA, the crosslinked, hydrophilic, and porous PEGDA suppor layer was obtained. To achieve high FO flux and salt selectivity using the fabricated PEGDA support, a selective layer was synthesized via the toluene-assisted interfacial polymerization (TIP), in which toluene is used as an organic solvent. The prepared PEGDA-based FO membrane showed higher FO water flux and lower salt selectivity compared with commercial HTI membranes using 1.0 M NaCl draw solution and DI water feed solution. We propose the strategy to fabricate high-performance FO membranes utilizing supports formed with new hydrophilic materials and fabrication processes.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.5
• /
• pp.303-313
• /
• 2010

This paper describes an acoustic communication receiver structure, which is designed for QPSK (Quadrature Phase Shift Keying) signal with 25 kHz carrier frequency and 5 kHz symbol rate, and takes samples from received signal at 100 kHz sampling rate. Based on the described receiver structure, optimum design parameters, such as number of taps of FF (Feed-Forward) and FB (Feed-Back) filters and forgetting factor of RLS (Recursive Least-Square) algorithm, of joint equalizer are determined to minimize the BER (Bit Error Rate) performance of the joint equalizer output symbols when the acquisition data in shallow water using implemented acoustic transducers is decimated at a rate of 2:1 and then enforced to the input of receiver. The transmission distances are 1.4 km, 2.9 km, and 4.7 km. Analysis results show that the optimum number of taps of FF and FB filters are different according to the distance between source and destination, but the optimum or near optimum value of forgetting factor is 0.997. Therefore, we can reach a conclusion that the proper receiver structure could change the number of taps of FF and FB filters with the fixed forgetting factor 0.997 according to the transmission distance. Another analysis result is that there are an acceptable performance degradation when the 16-tap-length simple filter is used as a low-pass filter of receiver instead of 161-tap-length matched filter.

• Journal of Information Technology Applications and Management
• /
• v.19 no.1
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• Structural Engineering and Mechanics
• /
• v.58 no.3
• /
• pp.459-473
• /
• 2016

Various vague and unstructured problems encountered the civil engineering/designers that persuaded by their experiences. One of these problems is the structural failure of the reinforced concrete (RC) building determination. Typically, using the traditional Limit state method is time consuming and complex in designing structures that are optimized in terms of one/many parameters. Recent research has revealed the Artificial Neural Networks potentiality in solving various real life problems. Thus, the current work employed the Multilayer Perceptron Feed-Forward Network (MLP-FFN) classifier to tackle the problem of predicting structural failure of multistoried reinforced concrete buildings via detecting the failure possibility of the multistoried RC building structure in the future. In order to evaluate the proposed method performance, a database of 257 multistoried buildings RC structures has been constructed by professional engineers, from which 150 RC structures were used. From the structural design, fifteen features have been extracted, where nine features of them have been selected to perform the classification process. Various performance measures have been calculated to evaluate the proposed model. The experimental results established satisfactory performance of the proposed model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.253-260
• /
• 2018

The acoustic communication channel in shallow underwater is typically shown as time-varying multipath fading channel characteristics. The received signal through channel transmission cause inter-symbol interference (ISI) owing to multiple components of different time delay and amplitude. To compensate for this, several techniques have been used, and one of them is acoustic equalizer. In this study, we used four equalizers - feed forward equalizer (FFE), decision directed equalizer (DDE), decision feedback equalizer (DFE) and combination DDE with DFE to compensate ISI. And we applied two adaptive algorithms to adjust coefficient of equalizers - normalized least mean square algorithm and recursive least square algorithm. As result, we found that it has a significant performance improvement over 6 dB on SNR in nonlinear equalizer. By combination of DFE and DDE has almost best performance in any case.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.9 no.3
• /
• pp.275-284
• /
• 2004

This paper discusses how to control the compensation voltages in dynamic voltage restorers (DVR). On analyzing the power circuit of a DVR system, control limitations and control targets are presented for the voltage compensation in DVRs. Based on the preceded power stage analysis, a novel controller for the compensation voltages of DVRs is proposed by a feed forward control scheme. This paper discusses also the time delay problems in the control system of DVRs. Digitally controlled DVR systems normally have control delay at amount of one sampling time of the control system and a half of the switching period of the DVR inverter. The control delay in digital controllers increases the dimension of the system transfer function one degree higher, which makes the control system more complicate and more unstable. This paper proposes a guide line to design the control gain, appropriate output filter parameters and inverter switching frequency for DVRs with digital controllers. Proposed theory is verified by an experimental DVR system with a full digital controller.