• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.8
• /
• pp.856-867
• /
• 1990

In this paper, the convergence and the learning accuracy of the back-propagation (BP) method in neural network are investigated by 1) analyzing the reason for decelerating the convergence of BP method and examining the rapid deceleration of the convergence when the learning is executed on the part of sigmoid activation function with the very small first derivative and 2) proposing the modified logistic activation function by defining, the convergence factor based on the analysis. Learning on the output patterns of binary as well as analog forms are tested by the proposed method. In binary output patter, the test results show that the convergence is accelerated and the learning accuracy is improved, and the weights and thresholds are converged so that the stability of neural network can be enhanced. In analog output patter, the results show that with extensive initial transient phenomena the learning error is decreased according to the convergence factor, subsequently the learning accuracy is enhanced.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.4 no.2
• /
• pp.184-191
• /
• 1999

일반적으로 시스템 인식과 제어를 위해 이용하는 다층망 신경회로망은 기존의 역전파알고리즘을 이용한다. 그러나 결선강도에 대한 오차의 기울기를 구하는 방법이기 때문에 국부적 최소점에 빠지기 쉽고, 수렴속도가 매우 늦으며 초기결선강도 값들이나 학습계수에 민감하게 반응한다. 이와 같은 단점을 개선하기 위해 본 논문에서는 칼만필터링 기법을 도입하여 수렴속도를 빠르게 하고 초기 결선강도의 영향을 받지 않도록 개선하였으며, 유도전동기의 속도추정과 제어에 적용하여 좋은 결과를 보였다.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.563-565
• /
• 2005

In this study, a algorithm to estimate Equivalent earth resistivity and Earth parameter using Artificial Neural Network(ANN) was proposed. Structures of the soil are grouped by using SOM algorithm before estimation. Earth parameter and Equivalent earth resistivity are obtained by using BP algorithm. The effectiveness of the proposed algorithm was verified. In the case study. afterwards, the algorithm proposed in this study will be used in more applications and gained more reliability.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.23
• /
• pp.10539-10542
• /
• 2015

A method to predict the risk of lung cancer is proposed, based on two feature selection algorithms: Fisher and ReliefF, and BP Neural Networks. An appropriate quantity of risk factors was chosen for lung cancer risk prediction. The process featured two steps, firstly choosing the risk factors by combining two feature selection algorithms, then providing the predictive value by neural network. Based on the method framework, an algorithm LCRP (lung cancer risk prediction) is presented, to reduce the amount of risk factors collected in practical applications. The proposed method is suitable for health monitoring and self-testing. Experiments showed it can actually provide satisfactory accuracy under low dimensions of risk factors.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.441-446
• /
• 1992

We propose a control architecture for the fuzzy logic control of robot manipulators and a rule base derivation method for a fuzzy logic controller(FLC) using a neural network. The control architecture is composed of FLC and PD(positional Derivative) controller. And a neural network is designed in consideration of the FLC's structure. After the training is finished by BP(Back Propagation) and FEL(Feedback Error Learning) method, the rule base is derived from the neural network and is reduced through two stages - smoothing, logical reduction. Also, we show the performance of the control architecture through the simulation to verify the effectiveness of our proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.972-974
• /
• 1993

This paper presents a new method to automatically design fuzzy logic controller(FLC). The main problems of designing FLC are how to optimally and automatically select the control rules and the parameters of membership function (MF). Cell state space algorithms (CSS), differential competitive learning (DCL) and multialyer neural network are combined in this paper to solve the problems. When the dynamical model of a control process is known. CSS can be used to generate a group of optimal input output pairs(X, Y) used by a controller. The(X, Y) then can be used to determine the FLC rules by DCL and to determine the optimal parameters of MF by DCL and to determine the optimal parameters of MF by multilayer neural network trained by BP algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1120-1124
• /
• 1989

• Korean Journal of Cognitive Science
• /
• v.4 no.2
• /
• pp.181-200
• /
• 1994

In the learning phase of multilyer feedforword neural network,there are problems such that local minimum,learning praralysis and slow learning speed when backpropagation algorithm used.To overcome these problems, the genetic algorithm has been used as learing method in the multilayer feedforword neural network instead of backpropagation algorithm.However,because the genetic algorith, does not have any mechanism for fine-tuned local search used in backpropagation method,it takes more time that the genetic algorithm converges to a global optimal solution.In this paper,we suggest a new GA-BP method which provides a fine-tunes local search to the genetic algorithm.GA-BP method uses gradient descent method as one of genetic algorithm's operators such as mutation or crossover.To show the effciency of the developed method,we applied it to the 3-parity bit problem with analysis.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.242-244
• /
• 1992

Conventionally in the industrial control, PlD controller has been used because of its robustness, and nonlinear characteristic of a system under control. Although the PlD controller produce suitable parameter of the each system and also variable of PlD controller should be changed according to environment, disturbance, load. In this paper, the convergence and learning accuracy of the back-propagation(BP) method in neural network are investigated by analyzing the reason for decelerating the convergence of BP method. and examining the rapid deceleration of the convergence when the learning is executed on the part of sigmoid activation function with the very small first derivative. The modified logistic activation function it proposed by defining the convergence factor based on the analysis and applied to the position and speed control of a DC-servo motor. This paper revealed for experimental, a neural network and a PD controller combined off-line system using developed the position and speed characteristics of a DC-servo motor.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.447-449
• /
• 1996

This paper describes an algorithm for short term load forecasting using the Kohonen neural network. Single layer Kohonen neural network presents a lot of advantageous features for practical application. It takes less training time compared to other networks such as BP network, and moreover, its self organized feature can amend the distorted data. The originality of proposed approach is to use a Kohonen map toclassify data representing load patterns and to use directly the information stored in the weight vectors of the Kohonen map to pridict the load. Proposed method was tested with KEPCO hourly record(1993-1995) show better forecasting results compared with conventional exponential smoothing method.