• 한국수자원학회논문집
• /
• 제31권1호
• /
• pp.45-57
• /
• 1998

본 논문의 목적은 다목적 저수지의 홍수유입량 예측을 위한 방법으로 병렬다중결선의 계층구조를 가진 신경망이론에 의하여 홍수시 불확실한 비선형시스템의 특성을 같는 저수지 유입량 예측모형을 개발하는 것이다. 신경망이론을 이용한 예측모형의 개발을 위하여 역전파 학습알고리즘을 사용하였으며 역전파 학습알고리즘 사용시 흔히 대두되는 지역최소값 문제와 수렴속도의 향상을 위해서 최적화기법인 경사하강법을 이용한 모멘트법과 경사하강법과 Gauss-Newton 방법을 이용한 Leverberg-Marquardt 법을 사용하였다. 모형개발에 사용된 자료는 연속적인 값으로 입력자료와 출력자료를 강우와 댐유입량을 학습시킨 후, 저수지의 홍수유입량 예측을 위한 다층신경망 모형을 구성하였다. 학습시 사용한 자료를 토대로 개발된 모형을 검정한 결과 매우 만족스런 결과를 얻을 수 있었고 실제 충주댐 유역을 대상으로 저수지 홍수유입량 예측결과 모형의 타당성을 입증할 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1239-1242
• /
• 2003

The neural networks are a famous model to learn the nonlinear function or nonlinear system. The main point of neural network is that the difference actual output from desired output is used to update weights. Usually, the gradient descent method is used for the learning process. On training process, if learning rate is too large, neural networks hardly guarantee convergence of neural networks. On the other hand, if learning rate is too small, the training spends much time. Therefore, one major problem in use of neural networks are to decrease the teaming time while neural networks are guaranteed convergence. In this paper, we suggest the model of fuzzy logic to neural networks to calibrate learning rate. This method is to tune learning rate dynamically according to error and demonstrates the optimization of training.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1302-1308
• /
• 2019

본 논문은 CNN (Convolutional Neural Network)와 2D Lidar 센서에서 획득한 위치 데이터를 이용하여 이미지를 분류하는 방법을 제시한다. Lidar 센서는 데이터 정확도, 형상 왜곡 및 광 변화에 대한 강인성 측면에서의 이점으로 인해 무인 장치에 널리 사용되어 왔다. CNN 알고리즘은 하나 이상의 컨볼루션 및 풀링 레이어로 구성되며 이미지 분류에 만족스러운 성능을 보여 왔다. 본 논문에서는 학습 방법에 따라 다른 유형의 CNN 아키텍처들인 Gradient Descent (GD) 및 Levenberg-arquardt (LM)를 구현하였다. LM 방법에는 학습 파라메터를 업데이트하는 요소 중 하나인 Hessian 행렬 근사 빈도에 따라 두 가지 유형이 있다. LM 알고리즘의 시뮬레이션 결과는 GD 알고리즘보다 이미지 데이터의 분류 성능이 우수하였다. 또한 Hessian 행렬 근사가 더 빈번한 LM 알고리즘은 다른 유형의 LM 알고리즘보다 작은 오류를 보여주었다.

• 한국지능시스템학회논문지
• /
• 제12권4호
• /
• pp.334-340
• /
• 2002

본 논문에서는 상대적으로 큰 퍼지 엔트로피를 갖는 입력-출력 데이터 집단에 다중 회귀 분석을 적용하여 다차원 평면 클러스터를 생성하고, 이 클러스터를 새로운 퍼지 모델의 규칙으로 추가한 후 모델 파라미터의 개략 동조와 정밀 동조를 반복 수행하는 자기구성 퍼지 모델링을 제안한다 Weighted recursive least squared 알고리즘과 fuzzy C-regression model 클러스터링에 의해 퍼지 모델의 파라미터를 개략적으로 동조한 후 gradient descent 알고리즘에 의해 파라미터를 정밀 동조하면서 감수분열 유전 알고리즘을 이용하여 최적의 학습률을 탐색한다. 그리고, 자기구성 퍼지 모델링 기법을 이용하여 Box-Jenkins의 가스로 데이터, 비선형 다변수 정적 함수의 데이터, 하수처리 활성오니 공정과 Mackey-Glass 시계열 데이터의 모델링을 수행하고, 기존의 방법에 의한 모델링 결과와 비교하여 그 성능을 입증한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• Journal of Mechanical Science and Technology
• /
• 제15권5호
• /
• pp.580-591
• /
• 2001

This paper proposes a fuzzy-sliding mode control which is designed by a self tuning fuzzy inference method based on a genetic algorithm. Using the method, the number of inference rules and the shape of the membership functions of the proposed fuzzy-sliding mode control are optimized without the aid of an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. It is further guaranteed that the selected solution becomes the global optimal solution by optimizing Akaikes information criterion expressing the quality of the inference rules. In order to evaluate the learning performance of the proposed fuzzy-sliding mode control based on a genetic algorithm, a trajectory tracking simulation of the polishing robot is carried out. Simulation results show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the trajectory control result is similar to the result of the fuzzy-sliding mode control which is selected through trial error by an expert. Therefore, a designer who does not have expert knowledge of robot systems can design the fuzzy-sliding mode controller using the proposed self tuning fuzzy inference method based on the genetic algorithm.

• 한국소음진동공학회논문집
• /
• 제14권4호
• /
• pp.267-275
• /
• 2004

This research is concerned with the development of a real-time adaptive PPF controller for the active vibration suppression of smart structure. In general, the tuning of the PPF controller is carried out off-line. In this research, the real-time learning algorithm is developed to find the optimal filter frequency of the PPF controller in real time and the efficacy of the algorithm is proved by implementing it in real time. To this end, the adaptive algorithm is developed by applying the gradient descent method to the predefined performance index, which is similar to the method used popularly in the optimization and neural network controller design. The experiment was carried out to verify the validity of the adaptive PPF controller developed in this research. The experimental results showed that adaptive PPF controller is effective for active vibration control of the structure which is excited by either impact or harmonic disturbance. The filter frequency of the PPF controller is tuned in a very short period of time thus proving the efficiency of the adaptive PPF controller.

• ETRI Journal
• /
• 제35권2호
• /
• pp.193-199
• /
• 2013

This paper addresses nonnegative independent component analysis (NICA), with the aim to realize the blind separation of nonnegative well-grounded independent source signals, which arises in many practical applications but is hardly ever explored. Recently, Bertrand and Moonen presented a multiplicative NICA (M-NICA) algorithm using multiplicative update and subspace projection. Based on the principle of the mutual correlation minimization, we propose another novel cost function to evaluate the diagonalization level of the correlation matrix, and apply the multiplicative exponentiated gradient (EG) descent update to it to maintain nonnegativity. An efficient approach referred to as the EG-NICA algorithm is derived and its validity is confirmed by numerous simulations conducted on different types of source signals. Results show that the separation performance of the proposed EG-NICA algorithm is superior to that of the previous M-NICA algorithm, with a better unmixing accuracy. In addition, its convergence speed is adjustable by an appropriate user-defined learning rate.

• 한국멀티미디어학회논문지
• /
• 제7권6호
• /
• pp.841-850
• /
• 2004

This paper proposes a GA and GDM-based method for removing unnecessary rules and generating relevant rules from the fuzzy rules corresponding to several fuzzy partitions. The aim of proposed method is to find a minimum set of fuzzy rules that can correctly classify all the training patterns. When the fine fuzzy partition is used with conventional methods, the number of fuzzy rules has been enormous and the performance of fuzzy inference system became low. This paper presents the application of GA as a means of finding optimal solutions over fuzzy partitions. In each rule, the antecedent part is made up the membership functions of a fuzzy set, and the consequent part is made up of a real number. The membership functions and the number of fuzzy inference rules are tuned by means of the GA, while the real numbers in the consequent parts of the rules are tuned by means of the gradient descent method. It is shown that the proposed method has improved than the performance of conventional method in formulating and solving a combinatorial optimization problem that has two objectives: to maximize the number of correctly classified patterns and to minimize the number of fuzzy rules.

• 제어로봇시스템학회논문지
• /
• 제2권1호
• /
• pp.21-25
• /
• 1996

In this paper we suggest a general purpose RNN training algorithm which is derived on the optimal control concepts and variational methods. First, learning is regared as an optimal control problem, then using the variational methods we obtain optimal weights which are given by a two-point boundary-value problem. Finally, the modified gradient descent algorithm is applied to RNN for on-line training. This algorithm is intended to be used on learning complex dynamic mappings between time varing I/O data. It is useful for nonlinear control, identification, and signal processing application of RNN because its storage requirement is not high and on-line learning is possible. Simulation results for a nonlinear plant identification are illustrated.