• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.454-458
• /
• 2001

Based on a fuzzy system representation of gray scale images, we derive and edge detection algorithm whose convolution kernel is different from the known kernels such as those of Robert's Prewitt's or Sobel's gradient. Our fuzzy system representation is an exact representation of the bicubic spline function which represents the gray scale image approximately. Hence the fuzzy system is a continuous function and it provides a natural way to define the gradient and the Laplacian operator. We show that the gradient at grid points can be evaluated by taking the convolution of the image with a 3$\times$3 kernel. We also that our gradient coupled with the approximate value of the continuous function generates an edge detection method which creates edge images clearer than those by other methods. A few examples of applying our methods are included.

• Journal of Power System Engineering
• /
• v.9 no.4
• /
• pp.202-208
• /
• 2005

The genetic algorithm (GA) which is one of the popular optimum algorithm has been used to solve a variety of optimum problems. Because it need not require the gradient of objective function and is easier to find global solution than gradient-based optimum algorithm using the gradient of objective function. However optimum method using the GA and the finite element method (FEM) takes many computational time to solve the optimum structural design problem which has a great number of design variables, constraints, and system with many degrees of freedom. In order to overcome the drawback of the optimum structural design using the GA and the FEM, the author developed a computer program which can optimize frame structures by using the GA and the generalized transfer stiffness coefficient method. In order to confirm the effectiveness of the developed program, it is applied to optimum design of plane frame structures. The computational results by the developed program were compared with those of iterative design.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.503-511
• /
• 1995

A batch-mode algorithm is proposed to increase the speed of learning in the error backpropagation algorithm with variable learning rate and variable momentum parameters in classification problems. The objective function is normalized with respect to the number of patterns and output nodes. Also the gradient of the objective function is normalized in updating the connection weights to increase the effect of its backpropagated error. The learning rate and momentum parameters are determined from a function of the gradient norm and the number of weights. The learning rate depends on the square rott of the gradient norm while the momentum parameters depend on the gradient norm. In the two typical classification problems, simulation results demonstrate the effectiveness of the proposed algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.152-159
• /
• 2005

For high-speed data communication in band-limited channels, main of the bit error are fading and ISI(Inter-Symbol Interference). The common way of dealing with ISI is using equalization in the receiver. In this thesis, channel adaptive equalizer which uses Fuzzy Stochastic Gradient(FSG) and Constant Modulus Algorithm(CMA) is nonlinear equalizer, or Blind equalizer, that works directly on the signals with no training sequences required. This equalizer employs Takagi-Sugeno's fuzzy model that uses the FSG algorithm, to automatically regulate the step size of the descent gradient vector, combining fast convergence rate and low mean square error(MSE), and the CMA which is a special case of Godard's algorithm, to having multiple dispersion constants($R_p$).

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.36-43
• /
• 1999

This paper proposes a new hybrid genetic algorithm for auto-tuning fuzzy controllers improving the performance. In general, fuzzy controllers use pre-determined moderate membership functions, fuzzy rules, and scaling factors, by trial and error. The presented algorithm estimates automatically the optimal values of membership functions, fuzzy rules, and scaling factors for fuzzy controllers, using a hybrid genetic algorithm. The object of the proposed algorithm is to promote search efficiency by the hybrid optimization technique. The proposed hybrid genetic algorithm is based on both the standard genetic algorithm and a modified gradient method. If a maximum point is not be changed around an optimal value at the end of performance during given generation, the hybrid genetic algorithm searches for an optimal value using the the initial value which has maximum point by converting the genetic algorithms into the MGM(Modified Gradient Method) algorithms that reduced the number of variables. Using this algorithm is not only that the computing time is faster than genetic algorithm as reducing the number of variables, but also that can overcome the disadvantage of genetic algoritms. Simulation results verify the validity of the presented method.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1023-1033
• /
• 2014

In this paper, performance improved hole-filling algorithm which includes the boundary noise removing pre-process that can be used for an arbitrary virtual view synthesis has been proposed. Boundary noise occurs due to the boundary mismatch between depth and texture images during the 3D warping process and it usually causes unusual defects in a generated virtual view. Common-hole is impossible to recover by using only a given original view as a reference and most of the conventional algorithms generate unnatural views that include constrained parts of the texture. To remove the boundary noise, we first find occlusion regions and expand these regions to the common-hole region in the synthesized view. Then, we fill the common-hole using the spiral weighted average algorithm and the gradient searching algorithm. The spiral weighted average algorithm keeps the boundary of each object well by using depth information and the gradient searching algorithm preserves the details. We tried to combine strong points of both the spiral weighted average algorithm and the gradient searching algorithm. We also tried to reduce the flickering defect that exists around the filled common-hole region by using a probability mask. The experimental results show that the proposed algorithm performs much better than the conventional algorithms.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.3
• /
• pp.39-46
• /
• 1994

In this paper, three types of parameter update law which can be used in model reference adaptive control are suggested based on speed-gradient algorithm which was introduced by Fradkov. It is shown that the parameter update law which was proposed by Narendra is a special from of these laws and that proposed parameter update laws can insure the global stability under some conditions such as attainability and convexity. We also comment that the transfer function of reference model shoud be positive real for the realization of parameter update law.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.4
• /
• pp.91-101
• /
• 2005

To determine stream network and watershed boundary using DEM, it is necessary to remove sink and flat area in proper way. There are filling algorithm and breaching algorithm to remove sink and Jenson and Domingue algorithm, relief algorithm and combined gradient algorithm to determine flow direction in flat area. In this study, the algorithms are reviewed. The computer program which uses filling algorithm with breaching algorithm and combined gradient algorithm to remove errors in DEM is developed. The results from this program are compared with Arc/Info which uses filling algorithm and Jenson and Domingue algorithm. The characteristics of stream network extracted from the DEM are analyzed. They are compared with the stream from NGIS map for stream morphology and characters by stream order to examine the value of this study.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3C
• /
• pp.141-146
• /
• 2005

The authors investigate the convergence speed problem of nonlinear adaptive equalization. Convergence constraints and time constant of radial basis function network using stochastic gradient (RBF-SG) algorithm is analyzed and a method of making time constant independent of hidden-node output power by using sample-by-sample node output power estimation is derived. The method for estimating the node power is to use a single-pole low-pass filter. It is shown by simulation that the proposed algorithm gives faster convergence and lower minimum MSE than the RBF-SG algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.911-923
• /
• 2016

Machine learning becomes increasingly important in the big data era. Logistic regression is a type of classification in machine leaning, and has been widely used in various fields, including medicine, economics, marketing, and social sciences. Rhipe that integrates R and Hadoop environment, has not been discussed by many researchers owing to the difficulty of its installation and MapReduce implementation. In this paper, we present the MapReduce implementation of Gradient Descent algorithm and Newton-Raphson algorithm for logistic regression using Rhipe. The Newton-Raphson algorithm does not require a learning rate, while Gradient Descent algorithm needs to manually pick a learning rate. We choose the learning rate by performing the mixed procedure of grid search and binary search for processing big data efficiently. In the performance study, our Newton-Raphson algorithm outpeforms Gradient Descent algorithm in all the tested data.