• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 추계학술대회 논문집 Vol.15
• /
• pp.573-577
• /
• 2002

A new estimated neural networks are proposed in order to measure nonlinear road environments in realtime. This new neural networks is Error Estimated Neural Networks. The structure of it is similar to recurrent neural networks; a delayed output as the input and a delayed error between the output of plant and neural networks as a bias input. In addition, we compute the desired value of hidden layer by an optimal method instead of transfering desired values by backpropagation and each weights are updated by RLS(Recursive Least Square). Consequently, this neural networks are not sensitive to initial weights and a learning rate, and have a faster convergence rate than conventional neural networks. We can estimate nonlinear models in realtime by the proposed networks and control nonlinear models. To show the performance of this one, we control 7 degree simulation, this controller and driver were proved to be effective to drive a car in the environments of nonlinear road systems.

• 한국지능시스템학회논문지
• /
• 제9권5호
• /
• pp.490-495
• /
• 1999

본 논문에서는 보로노이 다이아그램을 이용하여 오류 역전파 신경망의 초기값을 결정할수 있는 VoD_EBP를 제안하였다. VoD_EBP는 초기 연결 가중치와 임계값을 공학적 계산방법으로 결정함으로써 기존의 EBP에서 자주 발생하는 학습 마비 현상을 피할수 있고 초기부터 빠른 속도로 학습이 진행되므로 학습횟수를 단축시킬수 있다, 또한 VoD_EBP는 은닉층의 노드 수를 보로노이 다각형으로 구분된 클러스터들의 개수로 정할 수있어 신경망 설계에 신뢰성을 향상시켰다. 제시된 VoD_EBP의 효율성을 입증하기 위해 간단한 실험으로 2차원 입력벡터를 갖는 XOR 문제와 3차원 패리티 코드 검출 문제에 대하여 적용하여 보았다. 그 결과 임의의 초기값으로 설정하였던 EBP보다 훨씬 빠르게 학습이 종료되었고, 지역 최소치에 빠져 학습이 진행되지 못하는 현상이 발생하지 않았다.

• 한국IT서비스학회지
• /
• 제11권1호
• /
• pp.211-221
• /
• 2012

Many metric-based classification models have been proposed to predict fault-proneness of software module. This paper presents two prediction models using Bayesian classifier which is one of the most popular modern classification algorithms. Bayesian model based on Bayesian probability theory can be a promising technique for software quality prediction. This is due to the ability to represent uncertainty using probabilities and the ability to partly incorporate expert's knowledge into training data. The two models, Na$\ddot{i}$veBayes(NB) and Bayesian Belief Network(BBN), are constructed and dimensionality reduction of training data and test data are performed before model evaluation. Prediction accuracy of the model is evaluated using two prediction error measures, Type I error and Type II error, and compared with well-known prediction models, backpropagation neural network model and support vector machine model. The results show that the prediction performance of BBN model is slightly better than that of NB. For the data set with ambiguity, although the BBN model's prediction accuracy is not as good as the compared models, it achieves better performance than the compared models for the data set without ambiguity.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.693-695
• /
• 2004

Among modem control method, the observer is being used widely because it has the advantage of the guarantee of reliability on financial problem, over heating, and physical shock. However, an existing state observer and a sliding observer have such problems that an experimenter needs to know dynamics and parameters of the system. And also, the high gain observer has such a problem that it has transient state at the beginning of the observation. In this paper, the neuro observer is proposed to improve these problems. The proposed observer complement a problem that occur from increase of gain of High-gain observer in proportion to the square number of observable state variables. And also, the proposed observer can tune the gain obtained by differentiating observational error at transient state automatically by using the backpropagation training method to stabilize the observational speed. To prove a performance of the proposed observer, it is simulated that the comparison between the state estimate performance of the proposed observer and that of sliding, high gain observer is made by using a sinusoidal input to the observer which consists of four layers in stable 2nd order system.

• 전자공학회논문지C
• /
• 제35C권2호
• /
• pp.56-64
• /
• 1998

Multi-layered perceptrons that are a nonlinear neural network model, have been widely used for various applications mainly thanks to good function approximation capability for nonlinear fuctions. However, for digital hardware implementation of the multi-layere perceptrons, the quantization scheme using "look-up tables (LUTs)" is commonly employed to handle nonlinear signmoid activation functions in the neworks, and thus requires large amount of storage to prevent unacceptable quantization errors. This paper is concerned with a new effective methodology for digital hardware implementation of multi-layered perceptrons, and proposes a "piecewise affine approximation" method in which input domain is divided into (small number of) sub-intervals and nonlinear sigmoid function is linearly approximated within each sub-interval. Using the proposed method, we develop an expression and an error backpropagation type learning algorithm for a multi-layered perceptron, and compare the performance with the quantization method through Monte Carlo simulations on XOR problems. Simulation results show that, in terms of learning convergece, the proposed method with a small number of sub-intervals significantly outperforms the quantization method with a very large storage requirement. We expect from these results that the proposed method can be utilized in digital system implementation to significantly reduce the storage requirement, quantization error, and learning time of the quantization method.quantization method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.516-518
• /
• 1999

This paper presents an feed-forward neural network design instead PI controller for the speed control of an Induction Motor. The design employs the training strategy with Neural Network Controller(NNC) and Neural Network Emulator(NNE). Emulator identifies the motor by simulating the input and output map. In order to update the weights of the Controller. Emulator supplies the error path to the output stage of the controller using backpropagation algorithm. and then Controller produces an adequate output to the system due to neural networks learning capability. Therefore it becomes adjustable to the system with changing characteristics caused by a load. The speed control based on neural networks for induction motor is implemented by a vector controlled induction motor. The simulation results demonstrate that actual motor speed with neural network system well follows the reference speed minimizing the error and is available to implement on the vector control theory.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권5호
• /
• pp.285-290
• /
• 2005

The state observer is being used widely because it has the advantage of the guarantee of reliability on financial problem, over heating, and physical shock. However, an Luenberger observer and a Sliding observer have such problems that an experimenter needs to know dynamics and parameters of the system. And also, the high gain observer has such a problem that it has transient state at the beginning of the observation. In this paper, the Neuro observer is proposed to improve these problems. The proposed Neuro observer complement a problem that occur from increase of gain of High-gain observer in proportion to the square number of observable state variables. And also, the proposed Neuro observer can tune the gain obtained by differentiating observational error at transient state automatically by using the backpropagation training method to stabilize the observational speed. To prove a performance of the proposed observer, it is simulated that the comparison between the state estimate performance of the proposed observer and that of Sliding, High gain observer is made by using a sinusoidal input to the observer which consists of four layers in stable 2nd order system.

• 한국통신학회논문지
• /
• 제19권12호
• /
• pp.2418-2425
• /
• 1994

기울기를 따라가는 방식(gradient descent method)에 바탕을 둔 오류 역전파(EBP : Error Back Propagation) 방법이 가장 널리 사용되는 신경회로망의 학습 방법에서 문제가 되는 지역 최소값(local minima), 느린 학습 시간, 신경망 구조(structure), 그리고 초기의 연결 강도(interconnection weight) 등을 기존의 다층 신경 회로망에 지역적인 학습 능력을 가진 가우시안 포텔샵 네트워크(GPFN : Gaussian Potential Function Networks)를 병렬적으로 부가하여 해결함으로써 지역화된 오류 학습 패턴들이 나타내는 문제에 대하여 학습 성능을 향상시킬 수 잇는 새로운 학습 방법을 제시한다. 함수 근사화 문제에서 기존의 EBP 학습 방법과의 비교 실험으로 제안된 학습 방법이 보다 개선된 일반화 능력과 빠른 학습 속도를 가짐을 보여 그 효율성을 입증한다.

• Journal of Mechanical Science and Technology
• /
• 제19권7호
• /
• pp.1393-1404
• /
• 2005

Fatigue crack growth and life have been estimated based on established empirical equations. In this paper, an alternative method using artificial neural network (ANN) -based model developed to predict fatigue damages simultaneously. To learn and generalize the ANN, fatigue crack growth rate and life data were built up using in-plane bending fatigue test results. Single fracture mechanical parameter or nondestructive parameter can't predict fatigue damage accurately but multiple fracture mechanical parameters or nondestructive parameters can. Existing fatigue damage modeling used this merit but limited real-time damage monitoring. Therefore, this study shows fatigue damage model using backpropagation neural networks on the basis of X -ray half breadth ratio B / $B_o$, fractal dimension $D_f$ and fracture mechanical parameters can estimate fatigue crack growth rate da/ dN and cycle ratio N / $N_f$ at the same time within engineering limit error ($5\%$).

• 한국컴퓨터정보학회논문지
• /
• 제3권1호
• /
• pp.95-112
• /
• 1998

역전도 알고리즘은 연관 기억장치, 음성 인식, 패턴인식, 로보틱스등 여러 응용 분야에 다양하게 사용되고 있다. 그러나 새로운 학습 패턴을 추가적으로 학습시키려면 이전에학습했던 모든 패턴과 추가되는 패턴을 갖고 처음부터 새로운 학습을 수행하여야 한다. 이는 패턴의 개수가 점차 늘어날수록 학습에 소요되는 시간이 기하 급수적으로 길어지는 결과를 초래하게 된다. 따라서 주기적으로 다량의 데이터를 추가로 학습을 할 경우에 이러한 점진적 학습은 반드시 해결해야 할 문제점으로 간주된다. 본 논문에서는 기존의 신경망 구조는 그대로 유지하면서 대표 패턴을 추출해 추가 학습을 수행하는 방법을 제안하고 제안된 기법의 효율성을 위해 기계 학습 분야의 벤치마크로 많이 사용되는 Monk's data와 Iris data에 적용해 보았다.