• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1652-1662
• /
• 1995

In this paper, a hybrid neural network is proposed to improve the learning ability of a neural network. The union of the characteristics of a Self-Organizing Neural Network model and of multi-layer perceptron model using the backpropagation learning method gives us the advantage of reduction of the learning error and the learning time. In learning process, the proposed hybrid neural network reduces the number of nodes in hidden layers to reduce the calculation time. And this proposed neural network uses the fuzzy feedback values, when it updates the responding region of each node in the hidden layer. To show the effectiveness of this proposed hybrid neural network, the boolean function(XOR, 3Bit Parity) and the solution of inverse kinematics are used. Finally, this proposed hybrid neural network is applied to the visual tracking control of a PUMA560 robot, and the result data is presented.

• 한국산업융합학회 논문집
• /
• 제2권2호
• /
• pp.51-59
• /
• 1999

This study aims at the development of the techniques for the rainfall forecasting in river basins by applying neural network theory and compared with results of Multivariate Model (MVM). This study forecasts rainfall and compares with a observed values in the San Chung gauging stations of Nakdong river basin for the rainfall forecasting of river basin by proposed Neural Network Model(NNM). For it, a multi-layer Neural Network is constructed to forecast rainfall. The neural network learns continuous-valued input and output data. The result of rainfall forecasting by the Neural Network Model is superior to the results of Multivariate Model for rainfall forecasting in the river basin. So I think that the Neural Network Model is able to be much more reliable in the rainfall forecasting.

• 한국통신학회논문지
• /
• 제27권3B호
• /
• pp.188-195
• /
• 2002

본 논문에서는 멀티 레이트 부호분할 다중접속(Code Division Multiple Access: CDMA) 방식에서의 효과적인 다중 사용자 검출 기술을 제안한다. 최적 다중 사용자 검출 기술이 최적의 비트 오류 확률(Bit Error Rate: BER) 성능을 보이긴 하지만, 실제 구현을 위해서는 계산상의 복잡도 측면에서의 문제가 있다. 따라서, 본 논문에서는 멀티 레이트 CDMA 환경에서 비교적 낮은 계산상의 복잡도를 갖는 준칙적의 다중 사용자 검출기 구조를 제안하며, 기존의 정합필터(matched filter)와 멀티 레이트 환경에서 제안된 다른 다중 사용자 검출기와의 성능 비교를 수행한다. 레일리 페이딩 환경에서의 컴퓨터 시뮬레이션을 통해 제안된 홉필em(Hopfield) 신경망(neural network) 알고리즘을 이용한 다중 사용자 검출기법의 성능이 우수함을 검증한다.

• 조명전기설비학회논문지
• /
• 제26권10호
• /
• pp.89-94
• /
• 2012

This research is to apply the control of neuron networks for the real-time walking control of Multi-articulated robot. Multi-articulated robot is expressed with a complicated mathematical model on account of the mechanic, electric non-linearity which each articulation of mechanism has, and includes an unstable factor in time of walking control. If such a complex expression is included in control operation, it leads to the disadvantage that operation time is lengthened. Thus, if the rapid change of the load or the disturbance is given, it is difficult to fulfill the control of desired performance. This paper proposes a new mode to implement a neural network controller by installing a real object for controlling and an algorithm for this, which can replace the existing method of implementing a neural network controller by utilizing activation function at the output node. The proposed control algorithm generated control signs corresponding to the non-linearity of Multi-articulated robot, which could generate desired motion in real time.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 추계학술대회
• /
• pp.197-200
• /
• 1995

In this paper, we proposed the multi-step multi-layer artificial neural network(MMANN) to classify the chromosome, Which is used as a chromosome pattern classifier after learning. We extracted three chromosome morphological feature parameters such as centromeric index, relative length ratio, and relative area ratio by means of preprocessing method from ten chromosome images. The feature parameters of five chromosome images were used to learn neural network and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more, comparing with less feature parameters than that of the other researchers.

• 한국군사과학기술학회지
• /
• 제11권5호
• /
• pp.49-57
• /
• 2008

In this paper, we suggested a methodology that can be used by an agent to learn models of other agents in a multi-agent system. To construct these model, we used influence diagram as a modeling tool. We present a method for learning models of the other agents at the decision nodes, value nodes, and chance nodes in influence diagram. We concentrated on learning of the other agents at the value node by using neural network learning technique. Furthermore, we treated anti-air units in anti-air defense domain as agents in multi. agent system.

• 지능정보연구
• /
• 제2권2호
• /
• pp.69-83
• /
• 1996

The objective of this research is to develop a knowledge acquisition and refinement method for a multi-objective and multi-decision FMS scheduling problem. A competitive neural network and an inductive learning algorithm are integrated to extract and refine necessary scheduling knowledge from simulation outputs. The obtained scheduling knowledge can assist the FMS operator in real-time to decide multiple decisions simultaneously, while maximally meeting multiple objective desired by the FMS operator. The acquired scheduling knowledge for an FMS scheduling problem is tested by comparing the desired and the simulated values of the multiple objectives. The result show that the knowledge acquisition and refinement method is effective for the multi-objective and multi-decision FMS scheduling problems.

• 반도체디스플레이기술학회지
• /
• 제22권3호
• /
• pp.149-154
• /
• 2023

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

• 대한전자공학회논문지TE
• /
• 제39권4호
• /
• pp.363-369
• /
• 2002

본 논문은 적응성 뉴로-퍼지 인터페이스 시스템(Adaptive Neuro-Fuzzy Inference System : ANFIS)과 웨이브렛 변환 다중해상도 분해(multi-resolution Analysis : MRA)을 기반으로 한 웨이브렛 신경망을 가지고 임의의 비선형 함수 학습 근사화를 개선하는 것이다. ANFIS 구조는 벨형 퍼지 소속 함수로 구성이 되었으며, 웨이브렛 신경망은 전파 알고리즘과 역전파 신경망 알고리즘으로 구성되었다. 이 웨이브렛 구성은 단일 크기이고, ANFIS 기반 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 1차원과 2차원 함수에서 웨이브렛 전달 파라미터 학습과 ANFIS의 벨형 소속 함수를 이용한 ANFIS 모델 기반 웨이브렛 신경망의 웨이브렛 기저 수 감소와 수렴 속도 성능이 기존의 알고리즘 보다 개선되었음을 확인하였다.

• 전기학회논문지
• /
• 제62권5호
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.