• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.258-261
• /
• 2007

본 논문에서는 신경회로망 알고리즘 중 하나인 Backpropagation Network을 이용한 악보인식 기법과 그에 필요한 악보 이미지에 대한 전처리 기법을 제안한다. 전처리과정으로 이진화, 기울기 보정, 오선제거 등의 과정을 수행하여 인식에 필요한 음악 기호와 음표를 분리한다. 분리된 음악 기호와 음표들은 Backpropagation 알고리즘을 사용하여 구성된 음표 인식 신경망과 비음표 인식 신경망을 통해 각각 음표와 비음표 인식과정을 거친다. 다양한 복잡도를 가진 악보를 대상으로 한 실험 및 분석 결과를 통해 제안한 악보 인식 기법의 정확도를 기술하였다.

• 한국지능시스템학회논문지
• /
• 제12권5호
• /
• pp.397-404
• /
• 2002

본 논문에서는 퍼지와 웨이브렛 변환의 다해상도 분해(MRA)를 가진 퍼지 개념을 이용한 웨이브렛 신경망을 제안하고, 또한 이 시스템을 이용하여 임의의 비선형 함수 학습 근사화를 개선하고자 한다. 여기에서 퍼지 개념은 벨(bell)형 퍼지 소속함수를 사용하였다. 그리고 웨이브렛의 구성은 단일 크기를 가지고 있으며, 퍼지 개념을 이용한 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 웨이브렛 변환의 다해상도 분해, 벨형 퍼지 소속 함수 그리고 학습을 위한 역전파 알고리즘을 이용한 이 구조는 기존의 알고리즘보다 근사화 성능이 개선됨을 모의 실험을 통하여 1차원, 2차원 함수에서 확인하였다.

• 지구물리와물리탐사
• /
• 제3권3호
• /
• pp.83-87
• /
• 2000

송신원의 파워 증가가 제한되고 인공잡음이 존재하는 지역에서 양질의 탄성파 자료를 획득하기 위하여 근/원기준점(reference)을 이용한 탄성파 잡음예측필터를 개발하였다. 잡음예측필터에 사용된 방법은 backpropagation 알고리즘을 이용한 3층의 인공신경망(neural network)으로서, 훈련자료(training data) 및 검증자료(testing data)에 훈련된 잡음예측필터를 적용시 신호대잡음비(signal-to-noise ration)를 약 3배 정도 증가시켰다. 그러나, 일반적으로 전기, 전자탐사 자료의 질을 향상하기 위해 사용되는 스케일링(scaling)기법으로는 전혀 탄성파의 잡음을 제거할 수 없었다.

• 한국공작기계학회논문집
• /
• 제15권3호
• /
• pp.39-44
• /
• 2006

In this study, we nodestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of welding flasw. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from welding flaws in time domain. Through this process, we confirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 B
• /
• pp.1159-1161
• /
• 2000

This paper presents a speed control system of induction motor using neural network The speed control of induction motor was designed to NNC(Neural Network Controller) and NNE(Neural Network Estimator) used backpropagation, the NNE was constituted to be get an error value of output of an induction motor and conspire an input/output. NNC is controled to be made the error of reference speed and actual speed decrease, and in order to determine the weighting of NNC can be back propagated through the NNE, and it is adapted to the outside circumstances and system characters with learning ability.

• 한국생산제조학회지
• /
• 제9권6호
• /
• pp.89-95
• /
• 2000

In order to achieve effective prediction of residual stresses, the series experiment were carried out and the residual stresses were measured using the backgpropagation algorithm from the neural network and the sectional method. Using the experimental results, the optimal control algorithms using a neural network should be developed in order to reduce the effect of the external disturbances on residual stresses during GMA welding processes. The results obtained from the comparison between the measured and calculated results, showed that the neural network based on backpropagation algorithm can be sued in order to control weld quality. This system can not only help to understand the interaction between the process parameters and residual stress, but also, improve the quantity control for welded structures. The development of the system is goal in this study.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.543-556
• /
• 2001

This study suggests integrated neural network modes for he stock price index forecasting using change-point detection. The basic concept of this proposed model is to obtain significant intervals occurred by change points, identify them as change-point groups, and reflect them in stock price index forecasting. The model is composed of three phases. The first phase is to detect successive structural changes in stock price index dataset. The second phase is to forecast change-point group with various data mining classifiers. The final phase is to forecast the stock price index with backpropagation neural networks. The proposed model is applied to the stock price index forecasting. This study then examines the predictability of integrated neural network models and compares the performance of data mining classifiers.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 봄 학술발표회 논문집
• /
• pp.216-225
• /
• 1998

Although artificial neural network based on backpropagation algorithm is an excellent system simulator, it has still unsolved problems of its structure-decision and learning method. That is, we cannot find a general approach to decide the structure of the neural network and cannot train it satisfactorily because of the local optimum point which it frequently falls into. In addition, although there are many successful applications using backpropagation learning algorithm, there are few efforts to improve the learning algorithm itself. In this study, we suggest a general way to construct the hidden layer of the neural network using binary genetic algorithm and also propose the various learning methods by which the global minimum value of the teaming error can be obtained. A XOR problem and line heating problems are investigated as examples.

• 전자공학회논문지B
• /
• 제31B권10호
• /
• pp.149-157
• /
• 1994

A method of applying a recurrent backpropagation network to identifying or modelling a dynamic system is proposed. After the recurrent backpropagation network having both the characteristicsof interpolative network and associative network is applied to XOR problem, a new model of recurrent backpropagation network is proposed and compared with the original recurrent backpropagation network by applying them to XOR problem. based on the observation thata function can be approximated with polynomials to arbitrary accuracy, the new model is developed so that it may generate higher-order terms in the internal states Moreover, it is shown that the new network is succesfully applied to recognizing noisy patterns of numbers.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.625-628
• /
• 1997

In this paper the new neural network and sliding mode suspension controller is proposed. That neural network is error self-recurrent neural network. For fast on-line learning, this paper use recursive least squares method. A new neural networks converges considerably faster than the backpropagation algorithm and has advantages of being less affected by the poor initial weights and learning rate. The controller for suspension systems is designed according to sliding mode technique based on new proposed neural network.