• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.526-530
• /
• 1999

This paper presents a newly developed speed sensorless drive using Neural Network algorithm. Neural Network algorithm can be divided into three categories. In the first one, a Back Propagation-based NN algorithm is well-known to gradient descent method. In the second scheme, a Extended Kalman Filter-based NN algorithm has just the time varying learning rate. In the last scheme, a Recursive Least Square-based NN algorithm is faster and more stable than the classical back-propagation algorithm for training multilayer perceptrons. The number of iterations required to converge and the mean-squared error between the desired and actual outputs is compared with respect to each method. The theoretical analysis and experimental results are discussed.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.27-35
• /
• 1994

It is known that a unified phase I-phase II semi-infinite optimization algorithm with a steerign parameter performs better than the original unified phase I-phase II algorithm. In this paper, the effect of the steering parameter is analized and a new algorithm is presented based on the facts that when the point x is far away from the feasible region, reaching to the feasible region is more important than minimizing the cost functio and that when the point x is near the region, it is more efficient to try to reach the feasible region and to minimize the cost function concurrently. It is also important to consider the relationship between the feasible direction and the gradient of the cost function. Even though changing the steering parameter does not change the rate of convergence of the algorithm, it is shown from examples that given new algorithm is more efficient than the previous ones.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1996.11a
• /
• pp.73-78
• /
• 1996

In this study, we proposed a fuzzy gain scheduler with intelligent learning algorithm for a reactor control. In the proposed algorithm, we used the gradient descent method to learn the rule bases of a fuzzy algorithm. These rule bases are learned toward minimizing an objective function, which is called a performance cost function. The objective of fuzzy gain scheduler with intelligent learning algorithm is the generation of adequate gains, which minimize the error of system. The condition of every plant is generally changed as time gose. That is, the initial gains obtained through the analysis of system are no longer suitable for the changed plant. And we need to set new gains, which minimize the error stemmed from changing the condition of a plant. In this paper, we applied this strategy for reactor control of nuclear power plant (NPP), and the results were compared with those of a simple PI controller, which has fixed gains. As a result, it was shown that the proposed algorithm was superior to the simple PI controller.

• Proceedings of the KIPE Conference
• /
• 1998.07a
• /
• pp.384-387
• /
• 1998

This paper presents a newly developed speed sensorless drive using RLS(Recursive Least Squares) based on Neural Network Training Algorithm. The proposed algorithm based on the RLS has just the time-varying learning rate, while the well-known back-propagation (or generalized delta rule) algorithm based on gradient descent has a constant learning rate. The number of iterations required by the new algorithm to converge is less than that of the back-propagation algorithm. The RLS based on NN is used to adjust the motor speed so that the neural model output follows the desired trajectory. This mechanism forces the estimated speed to follow precisely the actual motor speed. In this paper, a flux estimation strategy using filter concept is discussed. The theoretical analysis and experimental results to verify the effectiveness of the proposed analysis and the proposed control strategy are described.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.624-636
• /
• 2006

This paper proposes a hybrid approach involving Genetic Algorithm (GA) and Bacterial Foraging (BF) for tuning the PID controller of an AVR. Recently the social foraging behavior of E. coli bacteria has been used to solve optimization problems. We first illustrate the proposed method using four test functions and the performance of the algorithm is studied with an emphasis on mutation, crossover, variation of step sizes, chemotactic steps, and the life time of the bacteria. Further, the proposed algorithm is used for tuning the PID controller of an AVR. Simulation results are very encouraging and this approach provides us a novel hybrid model based on foraging behavior with a possible new connection between evolutionary forces in social foraging and distributed non-gradient optimization algorithm design for global optimization over noisy surfaces.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.1002-1005
• /
• 1995

This paper presents an enhanced preprocessing and recognition algorithm for automatic vehicle license plate recognition system. The algorithm first applies horizontal gradient filter followed by thresholding and mathematical morphology operation for preprocessing. The final stage of the preprocessing is the application of connected component analysis in order to estimate the license plate region. For the recognition of the serial numbers of the plates, we developed a very effective algorithm. We call this zerocrossing count algorithm. This paper presents a detail of this algorithm and compare the performance with a template matching algorithm which utilizes correlation coefficient.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.173-180
• /
• 2012

This paper proposes a novel optimization algorithm inspired by water flowing and shaking behaviors in a vessel. Water drops in our algorithm flow to the gradient descent direction and are sometimes shaken for getting out of local optimum areas when most water drops fall in local optimum areas. These flowing and shaking operations allow our algorithm to quickly approach to the global optimum without staying in local optimum areas. We experimented our algorithm with four function optimization problems and compared its results with those of particle swarm optimization. Experimental results showed that our algorithm is superior to the particle swarm optimization algorithm in terms of the speed and success ratio of finding the global optimum.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.71-77
• /
• 2014

The equalization algorithm based on the cross-information potential concept and Dirac-delta functions (CIPD) has outstanding ISI elimination performance even under impulsive noise environments. The main drawback of the CIPD algorithm is a heavy computational burden caused by the use of a block processing method for its weight update process. In this paper, for the purpose of reducing the computational complexity, a new method of the gradient calculation is proposed that can replace the double summation with a single summation for the weight update of the CIPD algorithm. In the simulation results, the proposed method produces the same gradient learning curves as the CIPD algorithm. Even under strong impulsive noise, the proposed method yields the same results while having significantly reduced computational complexity regardless of the number of block data, to which that of the e conventional algorithm is proportional.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.105-114
• /
• 2011

The snake algorithm is widely adopted to track objects by extracting the active contour of the object from background. However, it fails to track the target converging to the background if there exists background whose gradient is greater than that of the pixels on the contour. Also, the contour may shrink when the target moves fast and the snake algorithm misses the boundary of the object in its searching window. To alleviate these problems, we propose an improved algorithm that can track object contour more robustly. Firstly, we propose two external energy functions, the edge energy and the contrast energy. One is designed to give more weight to the gradient on the boundary and the other to reflect the contrast difference between the object and background. Secondly, by computing the motion vector of the contour from the difference of the two consecutive frames, we can move the snake pointers of the previous frame near the region where the object boundary is probable at the current frame. Computer experiments show that the proposed method is more robust to the complicated background than the previously known methods and can track the object with fast movement.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.1
• /
• pp.95-99
• /
• 2018

In this paper, we propose an efficient pixel value prediction algorithm that can accurately predict pixel value using neighboring pixel values scanned in reverse s-order in the image. Generally, image has similarity with similar values between adjacent pixel values, and may have directional edge characteristics. In this paper, we proposed a method to improve pixel value prediction accuracy by improving GAP(Gradient Adjacent Pixel) algorithm for predicting pixel value by using similarity between adjacent pixels and edge characteristics. The proposed method increases the accuracy of the predicted pixel value by precisely predicting the pixel value using the positional weights of the neighboring pixels. Experiments on real images confirmed the superiority of the proposed algorithm. The proposed algorithm is useful for applications such as reversible data hiding, reversible watermarking, and data compression applications.