• 한국통신학회논문지
• /
• 제16권2호
• /
• pp.128-136
• /
• 1991

A neural network of multi layer perception type, learned by error back propagation learning rule, is generally used for the verification or clustering of similar type of patterns. When learning is completed, the network has a constant value of output depending on a pattern. This paper shows that the intensity of neuron's out put can be controlled by a function which intensifies the excitatory interconnection coefficients or the inhibitory one between neurons in output layer and those in hidden layer. In this paper the value of factor in the function to control the output is derived from the know values of the neural network after learning is completed And also this paper show that the amount of an increased neuron's output in output layer by arbitary value of the factor is derived. For the applications increased recognition performance of a pattern than has distortion is introduced and the output of partially damaged neurons are first managed and this paper shows that the reduced recognition performance can be recovered.

• 산업공학
• /
• 제24권3호
• /
• pp.267-273
• /
• 2011

In the shipbuilding industry, since production processes are so complicated that the data collection for decision making cannot be fully automated, most of production planning and controls are based on the information provided only by field workers. Therefore, without sufficient information it is very difficult to manage the whole production process efficiently. Job status is one of the most important information used for evaluating the remaining processing time in production control, specifically, in block assembly shop. Currently, it is checked by a production manager manually and production planning is modified based on that information, which might cause a delay in production control, resulting in performance degradation. Motivated by these remarks, in this paper we propose an efficient algorithm for identifying job status in block assembly shop for shipbuilding. The algorithm is based on the multi-layer perceptron neural network model using two key factors for input parameters. We showed the superiority of the algorithm by using a numerical experiment, based on real data collected from block assembly shop.

• 한국공작기계학회논문집
• /
• 제15권5호
• /
• pp.114-122
• /
• 2006

This paper presents a new control scheme that combines a sliding mode control and a neural network. In the proposed sliding mode control, a continuous control is employed removing the switching phenomena and the equivalent control within the boundary layer is estimated through on-line teaming of the neural network. The performances of the proposed control are compared with off-line neural network and on-line neural sliding mode control by computer simulation. The simulation results show that the proposed control reduces high frequency chattering and tracking error in example of the two link manipulator.

• 전자공학회논문지B
• /
• 제28B권12호
• /
• pp.27-37
• /
• 1991

In this paper, the novel PLD (Preceding Layer Driven) MLP (Multi Layer Perceptron) neural network model and its learning algorithm is described. This learning algorithm is different from the conventional. This integer weights and hard limit function are used for synaptic weight values and activation function, respectively. The entire learning process is performed by layer-by-layer method. the number of layers can be varied with difficulty of training data. Since the synaptic weight values are integers, the synapse circuit can be easily implemented with CMOS. PLD MLP neural network was applied to English Characters, arbitrary waveform generation and spiral problem.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 추계학술대회 논문집
• /
• pp.327-328
• /
• 2006

• 한국정밀공학회지
• /
• 제15권2호
• /
• pp.35-44
• /
• 1998

This paper describes multiple fault diagnosis method in complex system with hierarchical structure. Complex system is divided into subsystem, item and component. For diagnosing this hierarchical complex system, it is necessary to implement special neural network. We introduced Modular Artificial Neural Network(MANN) for this purpose. MANN consists of four level neural network, first level for symptom classification, second level for item fault diagnosis, third level for component symptom classification, forth level for component fault diagnosis. Each network is multi layer perceptron with 7 inputs, 30 hidden node and 7 outputs trained by backpropagation. UNIX IPC(Inter Process Communication) is used for implementing MANN with multitasking and message transfer between processes in SUN workstation. We tested MANN in reactor system.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권5_6호
• /
• pp.540-549
• /
• 2003

협력적 추천에서는 일반적으로 사용자 모델과 항목 모델이 사용되어진다. 사용자 모델은 사용자들간의 선호도 상관관계를 학습하고, 추천하고자 하는 항목에 대한 다른 사용자들의 선호도를 기반으로 그 항목을 추천한다. 이와 유사한 방식으로 항목 모델은 항목들간의 선호도 상관관계를 학습하고, 다른 항목들간의 선호도를 기반으로 추천 받는 사용자에게 항목을 추천한다. 본 논문에서는 추천 성능의 향상을 위해서 사용자 모델과 항목 모델간의 다양한 통합 방법을 제안한다. 제안하는 통합 방법으로는 순차적, 병렬적 통합 방법, 퍼셉트론 또는 다층 퍼셉트론을 이용한 통합 방법, 퍼지 규칙을 이용한 통합 방법 그리고 BKS를 적용한 방법이다. 본 실험에서는 통합 모델을 위해서 다층 퍼셉트론을 이용하여 사용자와 항목 모델을 각각 학습한다. 다층 퍼셉트론은 최근접 이웃방법이나 연관 규칙을 이용한 방법과 같은 기존의 추천 방법보다 연관된 항목들간의 가중치를 학습할 수 있고, 기호 데이타와 수치 데이타를 쉽게 처리할 수 있는 장점이 있다. 본 논문에서는 통합된 모델이 어떠한 단일 모델보다도 우수하고, 실험을 통하여 다층 퍼셉트론을 이용한 통합 방법이 다른 통합 방법보다 효율적인 통합 방법임을 보여주고 있다.

• 전자공학회논문지B
• /
• 제32B권9호
• /
• pp.1137-1153
• /
• 1995

It is not yet possible to solve the optimal number of neurons in hidden layer at neural networks. However, it has been proposed and proved by experiments that there is a limit in increasing the number of neuron in hidden layer, because too much incrememt will cause instability,local minima and large error. This paper proposes a module neural controller with pattern recognition ability to solve the above trade-off problems and to obtain fast learning convergence speed. The proposed neural controller is composed of several module having Multi-layer Perrceptron(MLP). Each module have the less neurons in hidden layer, because it learns only input patterns having a similar learning directions. Experiments with six joint robot manipulator have shown the effectiveness and the feasibility of the proposed the parallel module neural controller with pattern recognition perceptron.

• 전자공학회논문지B
• /
• 제31B권1호
• /
• pp.81-87
• /
• 1994

This paper describes the recognition of the printed Hanguel(Korean Character) using Neural Network. In this study, Neural network is used in only specific classification. Hanguel is classified globally by using template matching. Neural network is learned using the segmented grapheme. The grapheme of Hanguel is segmented using the structural method. Neural network is constructed, which is corresponded to the kind and the shape of graphemes. Each neural network is multi layer perceptron. The learning algorithm is the modified error back propagation using descending epsilon method. With five test character sets, the recognition rate of 94.95% is obtained.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.345-350
• /
• 2002

In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.