• International Journal of Quality Innovation
• /
• v.3 no.2
• /
• pp.113-131
• /
• 2002

The relationships among multi-dimensional data (such as medical examination data) with ambiguity and variation are difficult to explore. The traditional approach to building a data classification system requires the formulation of rules by which the input data can be analyzed. The formulation of such rules is very difficult with large sets of input data. This paper first describes two classification approaches using back-propagation (BP) neural network and Mahalanobis distance (MD) classifier, and then proposes two classification approaches for multi-dimensional feature selection. The first one proposed is a feature selection procedure from the trained back-propagation (BP) neural network. The basic idea of this procedure is to compare the multiplication weights between input and hidden layer and hidden and output layer. In order to simplify the structure, only the multiplication weights of large absolute values are used. The second approach is Mahalanobis-Taguchi system (MTS) originally suggested by Dr. Taguchi. The MTS performs Taguchi's fractional factorial design based on the Mahalanobis distance as a performance metric. We combine the automatic thresholding with MD: it can deal with a reduced model, which is the focus of this paper In this work, two case studies will be used as examples to compare and discuss the complete and reduced models employing BP neural network and MD classifier. The implementation results show that proposed approaches are effective and powerful for the classification.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.215-221
• /
• 2003

Generally, we want to be searched the newest as well as some appropriate personalized information from the internet resources. However, it is a complex and repeated procedure to search some appropriate information. Moreover, because the user's interests are changed as time goes, the real time modeling of a user's interests should be necessary. In this paper, I propose PREA system that can search and filter documents that users are interested from the World Wide Web. And then it constructs the user's interest model by a modified spreading neural network. Based on this network, PREA can easily produce some queries to search web documents, and it ranks them. The conventional spreading neural network does not have a visualization function, so that the users could not know how to be configured his or her interest model by the network. To solve this problem, PREA gives a visualization function being shown how to be made his interest user model to many users.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.429-431
• /
• 2003

The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.211-218
• /
• 2010

Taguchi has used the signal-to-noise ratio (SN) to achieve the appropriate set of operating conditions where variability around target is low in the Taguchi parameter design. Many Statisticians criticize the Taguchi techniques of analysis, particularly those based on the SN. Moreover, there are difficulties in practical application, such as complexity and nonlinear relationships among quality characteristics and design (control) factors, and interactions occurred among control factors. Neural networks have a learning capability and model free characteristics. There characteristics support neural networks as a competitive tool in processing multivariable input-output implementation. In this paper we propose a substantially simpler optimization procedure for parameter design using neural network without resorting to SN. An example is illustrated to compare the difference between the Taguchi method and neural network method.

• Journal of Korean Institute of Industrial Engineers
• /
• v.24 no.1
• /
• pp.23-35
• /
• 1998

This article presents a network flow analysis to form flexible machine cells with minimum intercellular part moves and a neural network model to form part families. The operational sequences and production quantity of the part, and the number of cells and the cell size are taken into considerations for a 0-1 quadratic programming formulation and a network flow based solution procedure is developed. After designing the machine cells, a neural network approach for the integration of part families and the automatic assignment of new parts to the existing cells is proposed. A multi-layer backpropagation network with one hidden layer is used. Experimental results with varying number of neurons in hidden layer to evaluate the role of hidden neurons in the network learning performance are also presented. The comprehensive methodology developed in this article is appropriate for solving large-scale industrial applications without building the knowledge-based expert rule for the cellular manufacturing environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1165-1168
• /
• 1996

The neural network approach has been shown to be a general scheme for nonlinear dynamical system identification. Unfortunately the error surface of a Multilayer Neural Network(MNN) that widely used is often highly complex. This is a disadvantage and potential traps may exist in the identification procedure. The objective of this paper is to identify a nonlinear dynamical systems based on Radial Basis Function Networks(RBFN). The learning with RBFN is fast and precise. This paper discusses RBFN as identification procedure is based on a nonlinear dynamical systems. and A design method of model follow control system based on RBFN controller is developed. As a result of applying this method to inverted pendulum, the simulation has shown that RBFN can be used as identification and control of nonlinear dynamical systems effectively.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.253-260
• /
• 1999

The recycling cell formation problem means that disposal products me classified into recycling part families using group technology in their end of life phase. Disposal products have the uncertainties of product status by usage influences during product use phase and recycling cells are formed design, process and usage attributes. In order to treat the uncertainties, fuzzy set theory and fuzzy logic-based neural network model are applied to recycling cell formation problem far disposal products. In this paper, a heuristic approach fuzzy ART neural network is suggested. The modified fuzzy ART neural network is shown that it has a great efficiency and give an extension for systematically generating alternative solutions in the recycling cell formation problem. We present the results of this approach applied to disposal refrigerators and the comparison of performances between other algorithms. This paper introduced a procedure which integrates economic and environmental factors into the disassembly of disposal products for recycling in recycling cells. A qualitative method of disassembly analysis is developed and its ai is to improve the efficiency of the disassembly and to generated an optimal disassembly which maximize profits and minimize environmental impact. Three criteria established to reduce the search space and facilitate recycling opportunities.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.253-260
• /
• 1999

The recycling cell formation problem means that disposal products are classified into recycling part families using group technology in their end of life phase. Disposal products have the uncertainties of product status by usage influences during product use phase and recycling cells are formed design, process and usage attributes. In order to treat the uncertainties, fuzzy set theory and fuzzy logic-based neural network model are applied to recycling cell formation problem for disposal products. In this paper, a heuristic approach for fuzzy ART neural network is suggested. The modified Fuzzy ART neural network is shown that it has a great efficiency and give an extension for systematically generating alternative solutions in the recycling cell formation problem. We present the results of this approach applied to disposal refrigerators and the comparison of performances between other algorithms. This paper introduced a procedure which integrates economic and environmental factors into the disassembly of disposal products for recycling in recycling cells. A qualitative method of disassembly analysis is developed and its aim is to improve the efficiency of the disassembly and to generated an optimal disassembly which maximize profits and minimize environmental impact. Three criteria established to reduce the search space and facilitate recycling opportunities.

• Transactions of Materials Processing
• /
• v.27 no.4
• /
• pp.227-235
• /
• 2018

The flow stresses have been identified prior to a numerical simulation for predicting a deformation of materials using the experimental or analytical analysis. Recently, the flow stress models considering the temperature effect have been developed to reduce the number of experiments. Artificial neural network can provide a simple procedure for solving a problem from the analytical models. The objective of this paper is the prediction of flow stress on the fiber metal laminate using the artificial neural network. First, the training data were obtained by conducting the uniaxial tensile tests at the various temperature conditions. After, the artificial neural network has been trained by Levenberg-Marquardt method. The numerical results of the trained model were compared with the analytical models predicted at the previous study. It is noted that the artificial neural network can predict flow stress effectively as compared with the previously-proposed analytical models.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2006.05a
• /
• pp.370-375
• /
• 2006

This paper suggests the method for estimating a partial discharge (PD) location using divide of the inside transformer as a grid. The PD location is found swiftly and economically compared with the typical method detecting a PD. The reason is that the location of PD is detected in the section. The estimation of PD location is trained using the Neural Network. JavaNNS(Java Neural Network Simulator) and SNNS(Stuttgart Neural Network Simulator) are used for searching the location of PD. The simulation procedure is following, The transformer is assumed that the case is a regular hexahedron. The sensor is installed in a proper location. A section of PD location is set as a target, and training set is studied with several PD locations in the inside of the transformer. As a result of training process, the learning capability of neural network is excellent. The PD location is detected by division of internal structure of transformer and application of neural network.