• 대한기계학회논문집
• /
• 제18권9호
• /
• pp.2265-2271
• /
• 1994

With the improvement of standard of living, requirement for comfortable and quiet environment has been increased and, therefore, there has been a many researches for active noise reduction to overcome the limit of passive control method. In this study, active noise control is performed in a duct system using intelligent control technique which needs not decide the coefficients of high order filter and the mathematical modeling of a system. Back propagation algorithm is applied as an intelligent control technique and control system is organized to exclude the error microphone and high speed operational device which are indispensable for conventional active noise control techniques. Furthermore, learning is performed by organizing acoustic feedback model, and the effect of the proposed control technique is verified via computer simulation and experiment of active noise control in a duct system.

• 대한전기학회논문지
• /
• 제45권1호
• /
• pp.42-53
• /
• 1996

The paper presents a speed control system of vector controlled induct- ion motor using neural networks. The main feature of proposed speed control system is a Neural Network Controller(NNC) which supplies torque current to induction motor and Neural Network Emulator(NNE) which captures the forward dynamics of induction motor. A back propagation training algorithm is employed to train the NNE and NNC. In order to determine the NNC output error, plant(induction motor) output error can be back propagated through the NNE. The NNC and NNE for speed control of vector controlled induction motor is carried out by TMS320C30 DSP and IGBT current regulated PWM inverter. Through computer simulation and experimental results, it is verified that proposed speed control system is robust to the load variation. (author). refs., figs.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2014년도 춘계 종합학술대회 논문집
• /
• pp.31-32
• /
• 2014

• 대한전자공학회논문지TE
• /
• 제39권2호
• /
• pp.66-75
• /
• 2002

본 논문에서는 역전파 신경회로망의 학습능률을 향상시키기 위한 방법으로 발생한 오차에 따라서 학습파라미터와 은닉층의 수를 적응적으로 변경시킬 수 있는 적응 역 전파 학습알고리즘을 제안하였다. 제안한 알고리즘은 역전파 신경회로망이 국소점으로 수렴하는 문제를 해결할 수 있고 최적의 수렴환경을 만들 수 있다. 제안된 알고리즘을 평가하기 위하여 배타적 논리합, 3-패리티 및 7${\times}$5 영문자 폰트의 학습을 이용하였다. 실험결과, 기존에 제안된 알고리즘들에 비하여 국소점에 빠지게 되는 경우가 감소하였고 약 17.6%~64.7%정도 학습능률이 향상하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.671-674
• /
• 2004

We propose accurate classification method of EEG signals during mental tasks. In the experimental task, the tasks of subjects show 3 major measurements; there are mathematical tasks, color decision tasks, and Chinese phrase tasks. The classifier implemented for this work is a feed-forward neural network that trained with the error back-propagation algorithm. The new BCI system is proposed by using neural network. In this system, tr e architecture of the neural network is composed of three layers with a feed-forward network, which implements the error back propagation-learning algorithm. By applying this algorithm to 4 subjects, we achieved $95{\%}$ classification rates. The results for BCI mathematical task experiments show performance better than those of the Chinese phrase tasks. The selection time of each task depends on the mental task of subjects. We expect that the proposed detection method can be a basic technology for brain-computer interface by combining with left/right hand movement or yes/no discrimination methods.

• 한국정보처리학회논문지
• /
• 제7권2호
• /
• pp.552-557
• /
• 2000

본 논문에서는 신경망의 초기 파라미터(가중치, 바이어스) 값을 최적화 시키는 GA-BP(Genetic Algorithm-Backpropagation Network) 혼합 알고리즘을 이용하여 얼굴을 인식하는 방법을 제안하였다. 입력 영상의 각 픽셀들을 신경망의 입력으로 사용하고 고정 소수점 실수값으로 이루어진 신경망의 초기 파리미터 값은 유전자 알고리즘의 개체로 사용하기 위해 비트 스트링으로 변환한다. 신경망의 오차가 최소가 되는 값을 적합도로 정의한 뒤 새롭게 정의된 적응적 재학습 연산자를 이용하여 이를 평가해 최적의 진환된 신경망을 구성한 뒤 얼굴을 인식하는 실험을 하였다. 실험 결과 학습 수렴 속도의 비교에서는 오류 역전과 알고리즘 단독으로 실행한 수렴 속도보다 제안된 알고리즘의 수렴 속도가 향상된 결과를 보였고 인식률에서 오류 역전과 알고리즘 단독으로 실행한 방법보다 2.9% 향상된 것으로 나타났다.

• 전자공학회논문지C
• /
• 제35C권3호
• /
• pp.79-89
• /
• 1998

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently used to solve complex problems such as pattern recognition, adaptive control, and global optimization. However, the EBP is basically a gradient descent method, which may get stuck in a local minimum, leading to failure in finding the globally optimal solution. Moreover, a multi-layer perceptron suffers from locking a systematic determination of the network structure appropriate for a given problem. It is usually the case to determine the number of hidden nodes by trial and error. In this paper, we propose a new algorithm to efficiently train a multi-layer perceptron. OUr algorithm uses stochastic perturbation in the weight space to effectively escape from local minima in multi-layer perceptron learning. Stochastic perturbation probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the EGP learning gets stuck to it. Addition of new hidden nodes also can be viewed asa special case of stochastic perturbation. Using stochastic perturbation we can solve the local minima problem and the network structure design in a unified way. The results of our experiments with several benchmark test problems including theparity problem, the two-spirals problem, andthe credit-screening data show that our algorithm is very efficient.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2012년도 추계 학술논문 발표대회
• /
• pp.253-254
• /
• 2012

The purpose of this study is to suggest and verify high-strength concrete mix design model applying neural network theory, in order to minimize effort and time wasted by using trial and error method utill now. There are 7 input and 2 output to predict mix design. 40 data of mix design were learned with back-propagation algorithm. Then they are repeatedly learned back-propagation in neural network theory. Also, to verify predicted model, we analyzed and compared value predicted from 60MPa mix design with value measured by actual compressive strength test.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.839-842
• /
• 2000

A new and modified neural network model Is proposed for CT image reconstruction from four projection directions only. The model uses the Resilient Back-Propagation (Rprop) algorithm, which is derived from the original Back-Propagation, for adaptation of its weights. In addition to the error in projection directions of the image being reconstructed, the proposed network makes use of errors in pixels between an image which passed the median filter and the reconstructed one. Improved reconstruction was obtained, and the proposed method was found to be very effective in CT image reconstruction when the given number of projection directions is very limited.

• 전자공학회논문지C
• /
• 제35C권6호
• /
• pp.67-75
• /
• 1998

다층퍼셉트론의 학습에서 나타나는 출력노드의 부적절한 포화를 해결하기 위해서 n차 크로스-엔트로피 오차함수가 제안되었으나, 이 오차함수를 이용한 학습성능은 오차함수의 차수에 민감하여 적절한 차수를 결정해야 하는 문제점이 있다. 이 논문에서는, 학습의 진행에 따라 학습률을 가변시키는 새로운 방법을 제시하여 다층퍼셉트론의 학습성능이 n차 크로스-엔트로피 오차함수의 차수에 덜 민감하도록 한다. 또한, 가변학습률이 매우 커지는 경우에 학습이 불안정해지는 것을 방지하기 위해서 오차신호의 크기를 제한하는 방법을 제시한다. 마지막으로, 필기체 숫자 인식 문제와 갑상선 진단 문제의 시뮬레이션으로 제안한 방법의 효용성을 검증한다.