• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.118-124
• /
• 2004

In this paper, we present a indirect adaptive control method using a wavelet neural network (WNN) for the control of chaotic nonlinear systems without precise mathematical models. The proposed indirect adaptive control method includes the off-line identification and on-line control procedure for chaotic nonlinear systems. In the off-line identification procedure, the WNN based identification model identifies the chaotic nonlinear system by using the serial-parallel identification structure and is trained by the gradient-descent method. And, in the on-line control procedure, a WNN controller is designed by using the off-line identification model and is trained by the error back-propagation algorithm. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with applications to the chaotic nonlinear systems.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.2
• /
• pp.131-140
• /
• 1994

Dynamics of AUV has heavy nonlinearities and many unknown parameters due to its bluff shape and low cruising speed. Intelligent algorithms, therefore, are required to overcome these nonlinearities and unknown system dynamics. Several identification techniques have been suggested for the application of control of underwater vehicles during last decade. This paper applies the neural network to identification and motion control problem of AUVs. Nonlinear dynamic systems of an AUV are identified using feedforward neural network. Simulation results show that the learned neural network can generate the motion of AUV. This paper, also, suggest an adaptive control scheme up-dates the controller weights with reference model and feedforward neural network using error back propagation.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.1
• /
• pp.42-53
• /
• 1996

The paper presents a speed control system of vector controlled induct- ion motor using neural networks. The main feature of proposed speed control system is a Neural Network Controller(NNC) which supplies torque current to induction motor and Neural Network Emulator(NNE) which captures the forward dynamics of induction motor. A back propagation training algorithm is employed to train the NNE and NNC. In order to determine the NNC output error, plant(induction motor) output error can be back propagated through the NNE. The NNC and NNE for speed control of vector controlled induction motor is carried out by TMS320C30 DSP and IGBT current regulated PWM inverter. Through computer simulation and experimental results, it is verified that proposed speed control system is robust to the load variation. (author). refs., figs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.12A
• /
• pp.1260-1266
• /
• 2007

Error propagation of source-relay (S-R) link limits the performance of decode-and-forward (DF) relay and prohibits DF relay from achieving full diversity gain. In order to solve this problem, the proposed deployment strategy focuses on two objectives. One is to achieve full diversity gain, and the other is to minimize the used power of the DF relay system. In order to achieve full diversity, the error probability of S-R link should be lower than that of maximal ratio combining (MRC) at destination without error propagation since the error probability of the weaker link dominates the total error probability. The proposed strategy of relay positioning points out the range of the relay position for achieving full diversity, and the used power of the relay is minimized by this range. Analysis of error probability and simulation results prove that the two objectives are achieved by the proposed strategy of the relay position.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.625-632
• /
• 2021

This paper studies the effect of the number of filters in the CNN (Convolutional Neural Network) layer on the performance of a noise attenuator. Speech is estimated from a noised speech signal using a 64-neuron, 16-kernel CNN filter and an error back-propagation algorithm. In this study, in order to verify the performance of the noise attenuator with respect to the number of filters, a program using Keras library was written and simulation was performed. As a result of simulation, it can be seen that this system has the smallest MSE (Mean Squared Error) and MAE (Mean Absolute Error) values when the number of filters is 16, and the performance is the lowest when there are 4 filters. And when there are more than 8 filters, it was shown that the MSE and MAE values do not differ significantly depending on the number of filters. From these results, it can be seen that about 8 or more filters must be used to express the characteristics of the speech signal.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.737-738
• /
• 2008

An implementation of robust stereo matching algorithm under variable illumination conditions is presented in this paper. By applying window-based matchingmethod to global stereo matching algorthm using belief propagation, our implemented system shows low error rate and could efficiently cope with general radiometric disimilarities between images acquired from two different point of views.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2001.05a
• /
• pp.62-63
• /
• 2001

• The KIPS Transactions:PartC
• /
• v.9C no.3
• /
• pp.307-312
• /
• 2002

Among the various zero suppression (ZS) algorithms used in a for synchronous stream cipher system, a ZS-2 exhibits certain good properties, including the omission of the block synchronization, easy implementation, etc., yet also a weakness in channel error propagation. Accordingly, This paper proposes a new method by minimizing the bit-wide substitution in the substitution blocks of ZS-2 to improve the degenerated error property in a noisy channel. As a result, the proposed ZS-3 algorithm can decrease the mean error propagation by about 18.7% over that of ZS-2 at n=8.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.9A
• /
• pp.2365-2371
• /
• 1998

Discrete cosine transform (DCT) has wide applications in speech and image coding. In this paper, we propose a novel fast dCT scheme with the property of reduced multiplication stages and the smaller number of additions and multiplications. This exploits the symmetry property of the DCT kernel to decompose the N-point dCT to N/2 point, and can be generally applied recursively to $2^{m}$-point. The proposed algorithm has a structure that most of multiplications tend to be performed at final stage, and this reduces propagation of truncation error which could occur in the fixed-point computation. Also the minimization of the multiplication stages further decreases the error.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.9 no.2
• /
• pp.211-218
• /
• 1998

In this paper, we analyze various errors in prediction results of ray tracing propagation model for microcellular environments. It is shown that improper electrical parameters of building materials and limitations of diffraction orders can cause high errors in prediction results. Especially, the effect of errors in building database on prediction results is considered in detail. It is also shown that the prediction error increases as the resolution of building map data is getting worse, and the error is analyzed depending on LOS and NLOS domains. Based on the results obtained by the analysis developed in this paper, 5 m resolution is suitable for the building map data if the maximum prediction error is required to be below 6 dB.