• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.163-169
• /
• 2014

A stable neural network control scheme for unknown non-linear systems is developed in this paper. While the control variable is optimised to minimize the performance index, convergence of the index is guaranteed asymptotically stable by a Lyapnov control law. The optimization is achieved using a gradient descent searching algorithm and is consequently slow. A fast convergence algorithm using an adaptive learning rate is employed to speed up the convergence. Application of the stable control to a single input single output (SISO) non-linear system is simulated. The satisfactory control performance is obtained.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.709-721
• /
• 2009

This paper discusses an efficient image segmentation using morphological watershed algorithm that is robust to noise. Morphological image segmentation consists of four steps: image simplification, computation of gradient image and watershed algorithm and region merging. Conventional watershed segmentation exhibits a serious weakness for over-segmentation of images. In this paper we present a morphological edge detection methods for detecting edges under noisy condition and apply our watershed algorithm to the resulting gradient images and merge regions using Kolmogorov-Smirnov test for eliminating irrelevant regions in the resulting segmented images. Experimental results are analyzed in both qualitative analysis through visual inspection and quantitative analysis with percentage error as well as computational time needed to segment images. The proposed algorithm can efficiently improve segmentation accuracy and significantly reduce the speed of computational time.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.57-66
• /
• 2011

In this paper, it is proposed for algorithm to detect human efficiently using a edge symmetry and gradient directional characteristics in realtime by the feature extraction in a single input image. Proposed algorithm is composed of three stages, preprocessing, region partition of human candidates, verification of candidate regions. Here, preprocessing stage is strong the image regardless of the intensity and brightness of surrounding environment, also detects a contour with characteristics of human as considering the shape features size and the condition of human for characteristic of human. And stage for region partition of human candidates has separated the region with edge symmetry for human and size in the detected contour, also divided 1st candidates region with applying the adaboost algorithm. Finally, the candidate region verification stage makes excellent the performance for the false detection by verifying the candidate region using feature vector of a gradient for divided local area and classifier. The results of the simulations, which is applying the proposed algorithm, the processing speed of the proposed algorithms is improved approximately 1.7 times, also, the FNR(False Negative Rate) is confirmed to be better 3% than the conventional algorithm which is a single structure algorithm.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.562-568
• /
• 2016

In this paper, we focus on recognition of speed-limit signs among a few types of traffic signs because speed-limit sign is closely related to safe driving of drivers. Although histogram of oriented gradient (HOG) and local binary patterns (LBP) are representative features for object recognition, these features have a weakness with respect to rotation, in that it does not consider the rotation of the target object when generating patterns. Therefore, this paper propose the fast rotation-invariant binary patterns (FRIBP) algorithm to generate a binary pattern that is robust against rotation. The proposed FRIBP algorithm deletes an unused layer of the histogram, and eliminates the shift and comparison operations in order to quickly extract the desired feature. The proposed FRIBP algorithm is successfully applied to German Traffic Sign Recognition Benchmark (GTSRB) datasets, and the results show that the recognition capabilities of the proposed method are similar to those of other methods. Moreover, its recognition speed is considerably enhanced than related works as approximately 0.47second for 12,630 test data.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.603-611
• /
• 2001

This paper proposes a novel fast layer-by-layer algorithm that has better generalization capability. In the proposed algorithm, the weights of the hidden layer are updated by the target vector of the hidden layer obtained by least squares method. The proposed algorithm improves the learning speed that can occur due to the small magnitude of the gradient vector in the hidden layer. This algorithm was tested in a handwritten digits recognition problem. The learning speed of the proposed algorithm was faster than those of error back propagation algorithm and modified error function algorithm, and similar to those of Ooyen's method and layer-by-layer algorithm. Moreover, the simulation results showed that the proposed algorithm had the best generalization capability among them regardless of the number of hidden nodes. The proposed algorithm has the advantages of the learning speed of layer-by-layer algorithm and the generalization capability of error back propagation algorithm and modified error function algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.98-106
• /
• 1998

This paper proposes an efficient learning algorithm for improving the training performance of the neural network. The proposed method improves the training performance by applying the backpropagation algorithm of a global optimization method which is a hybrid of a stochastic approximation and a conjugate gradient method. The approximate initial point for f a ~gtl obal optimization is estimated first by applying the stochastic approximation, and then the conjugate gradient method, which is the fast gradient descent method, is applied for a high speed optimization. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to those of the conventional backpropagation and the backpropagation algorithm which is a hyhrid of the stochastic approximation and steepest descent method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.105-110
• /
• 2018

This paper compare the adaptive equalization performance of NM-MMA (Novel Mixed-MMA) algorithm which using the mixed const function by scaling factor values. The mixed cost function of NM-MMA composed of the appropriate weighted addition of gradient vector in the MMA and SE-MMA cost function, and updating the tap coefficient based on these function, it is possible to improve the convergence speed and MSE value of current algorithm. The computer simulation was performed in the same channel, step size, SNR environment by changing the scaling factor, and its performance were compared appling the equalizer output constellation, residual isi, MD, MSE, SER. As a result of computer simulation, the residual values of performance index were reduced in case of the scaling factor of MMA cost function was greater than the scaling factor of SE-MMA. and the convergence speed was improved in case of the scaling factor of SE-MMA was greater than the MMA.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1281-1284
• /
• 1998

This paper proposes an efficient time series prediction of the nonlinear dynamical discrete-time systems using multilayer neural networks of a hybrid learning algorithm. The proposed learning algorithm is a hybrid backpropagation algorithm based on the steepest descent for high-speed optimization and the dynamic tunneling for global optimization. The proposed algorithm has been applied to the y00 samples of 700 sequences to predict the next 100 samples. The simulation results shows that the proposed algorithm has better performances of the convergence and the prediction, in comparision with that using backpropagation algorithm based on the gradient descent for multilayer neural network.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.4
• /
• pp.191-197
• /
• 2021

To calculate the induced charge of atoms in molecular dynamics, linear equations for the induced charges need to be solved. As induced charges are determined at each time step, the process involves considerable computational costs. Hence, an efficient method for calculating the induced charge distribution is required when analyzing large systems. This paper introduces the Uzawa method for solving saddle point problems, which occur in linear systems, for the solution of the Lagrange equation with constraints. We apply the accelerated Uzawa algorithm, which reduces computational costs noticeably using the Schur complement and preconditioned conjugate gradient methods, in order to overcome the drawback of the Uzawa parameter, which affects the convergence speed, and increase the efficiency of the matrix operation. Numerical models of molecular dynamics in which two gold nanoparticles are placed under external electric fields reveal that the proposed method provides improved results in terms of both convergence and efficiency. The computational cost was reduced by approximately 1/10 compared to that for the Gaussian elimination method, and fast convergence of the conjugate gradient, as compared to the basic Uzawa method, was verified.