• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1375-1384
• /
• 2014

Flashover of power transmission line insulators is a major threat to the reliable operation of power system. This paper deals with the flashover prediction of polymeric insulators used in power transmission line applications using the novel condition monitoring technique developed by PD signal time-frequency map and neural network technique. Laboratory experiments on polymeric insulators were carried out as per IEC 60507 under AC voltage, at different humidity and contamination levels using NaCl as a contaminant. Partial discharge signals were acquired using advanced ultra wide band detection system. Salient features from the Time-Frequency map and PRPD pattern at different pollution levels were extracted. The flashover prediction of polymeric insulators was automated using artificial neural network (ANN) with back propagation algorithm (BPA). From the results, it can be speculated that PD signal feature extraction along with back propagation classification is a well suited technique to predict flashover of polymeric insulators.

• 한국정보통신학회논문지
• /
• 제2권1호
• /
• pp.109-116
• /
• 1998

본 논문은 DS-SS 이동 통신 시스템에서 복합 다계층 퍼셉트론 신경망을 이용한 간섭 신호 제어로써 직접순차 확산 스펙트럼의 협대역 간섭 신호를 역전파 학습 알고리즘을 이용하여 억압하고, 컴퓨터 시뮬레이션을 통해 동일 채널 간섭과 협대역 간섭의 실제 톤(Tone)에서 빠른 수렴 비율과 더 좋은 성능을 가지는 복소수 역전파 알고리즘으로부터 제안된 새로운 복합 (CBPRLS)알고리즘은 기존의 RAKE 수신기보다 더 낮은 비트 에러 율을 가지는 NNAC(Neural Network Adaptive Correlator)를 통해 간섭 신호가 보다 효율적으로 제어됨을 분석 고찰한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1050-1052
• /
• 1996

This paper presents a neuro-control algorithm for the speed control of a direct drive motor without the knowledge of the dynamics of the motor and the characteristics of a nonlinear load. In the field of motor control, it is not possible to directly use the back-propagation method in order to train a network since the desired output of the network is not known. Hence, we propose an extended back-propagation algorithm to force the closed loop system to give desired results. Experimental results shown that the proposed neuro-controller can reduce the unknown load effects and have the good velocity tracking capabilities.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 D
• /
• pp.2573-2575
• /
• 2003

In this paper, we discuss a fuzzy neural network classifier with immune algorithm. The fuzzy neural network classifier is constructed with the fuzzy classifier and the neural network classifier based on fuzzy rules. To maximize performance of classifier, the immune algorithm and the back propagation algorithm are used. For the generalized classification ability, the simulation results from the iris data demonstrate superiority of the proposed classifier in comparison with other classifier.

• 정보학연구
• /
• 제9권4호
• /
• pp.65-74
• /
• 2006

The back propagation of neural networks has the problems of falling into local minimum and delay of the speed by the iterative learning. An algorithm to solve the problem and improve the speed of the learning was already proposed in[8], which updates the learning parameter related with the connection weight. In this paper, we propose the algorithm generating initial weight to improve the efficiency of the algorithm by offering the difference between the input vector and the target signal to the generating function of initial weight. The algorithm proposed here can classify more than 98.75% of the handwritten digits and this rate shows 30% more effective than the other previous methods.

• 한국항만학회지
• /
• 제12권2호
• /
• pp.225-232
• /
• 1998

Todays, the efficient management of container has not been realized in container terminal, because of the excessive quantity of container transported and manual system. For the efficient and automated management of container in terminal, the automated container identifier recognition system in terminal is a significant problem. However, the identifier recognition rate is decreased owing to the difficulty of image preprocessing caused the refraction of container surface, the change of weather and the damaged identifier characters. Therefore, this paper proposes more accurate system for container identifier recognition as suggestion of LSPRD(Line-Scan Proper Region Detection) for stronger preprocessing against external noisy element and MBP(Momentum Back-Propagation) neural network to recognize the identifier.

• 한국정보전자통신기술학회논문지
• /
• 제1권3호
• /
• pp.77-82
• /
• 2008

본 논문에서는 대중음악 코드진행 과정에 있어서 패턴 분석을 이용하여 멜로디를 추가하는 방법을 소개한다. 먼저, 멜로디를 신경망의 입력으로 사용되는 비트패턴으로 변환하는 방법을 기술한다. 멜로디 추가 방법은 역전파 신경망 학습을 통해 멜로디 작곡 패턴을 학습시키고 학습 된 데이터를 바탕으로 멜로디를 생성하도록 설계하였다. 실험결과 신경망 학습을 이용한 컴퓨터의 작곡 가능성을 확인하였다.

• 한국산학기술학회논문지
• /
• 제14권3호
• /
• pp.1372-1377
• /
• 2013

본 논문은 신경망을 이용한 간섭 신호 제어로써 합성 다층 퍼셉트론에 입각하여 셀룰라 이동 통신에서의 수신된 신호들을 역전파 학습알고리즘을 이용하여 검파하는 것에 대하여 소개하였다. 그리고 컴퓨터 시뮬레이션 결과를 통하여 공동 간섭과 협대역 간섭의 실제 음색에서 기존에 쓰여진 레이크 수신기보다 더 낮은 비트 오차 확률을 가지는 NNAC(neural network adaptive correlator)에 대하여 분석 하였다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2003년도 춘계학술대회
• /
• pp.329-337
• /
• 2003

Stock market prediction is regarded as a challenging task of financial time-series prediction. There have been many studies using artificial neural networks in this area. Recently, support vector machines (SVMs) are regarded as promising methods for the prediction of financial time-series because they me a risk function consisting the empirical ewer and a regularized term which is derived from the structural risk minimization principle. In this study, I apply SVM to predicting the Korea Composite Stock Price Index (KOSPI). In addition, this study examines the feasibility of applying SVM in financial forecasting by comparing it with back-propagation neural networks and case-based reasoning. The experimental results show that SVM provides a promising alternative to stock market prediction.

• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.26-35
• /
• 1998

This paper presents a visual inspection algorithm looking for solder joint defects of IC chips on PCBs (Printed Circuit Boards). In this algorithm, seven features are proposed in order to categorize the solder joints into four classes such as normal, insufficient, excess, and no solder, and optimal back-propagation network is determined by error evaluation which depend on the number of neurons in hidden and out-put layers and selection of the features. In the end, a good accuracy of classification performance, an optimal determination of network structure and the effectiveness of chosen seven features are examined by experiment using proposed inspection algorithm.