• Korean Journal of Computational Design and Engineering
• /
• v.18 no.4
• /
• pp.275-282
• /
• 2013

This paper proposes a method for human identification using teeth contours extracted from dental images that are captured from the frontal views of subjects each of who opens his or her mouth slightly. Each dental image has a black-colored region containing the subject's teeth contours which are usually different from subject to subject. This means that this black-colored region has bio-mimetic information useful for human identification. The basic idea of the method is to extract the upper and lower teeth contours from the dental image of each subject and to encode their geometric patterns using a back-propagation neural network model. After acquiring 400 teeth images form 10 university students, we used 300 images for the training data of the neural network model and 100 images for its verification. Experimental results have shown that the proposed neural network-based method can be used as an alternative solution for identification among a small group of humans with a low cost and simple setup.

• Korean Management Science Review
• /
• v.29 no.3
• /
• pp.81-89
• /
• 2012

Since introduced by Vining and Myers in 1990, the concept of dual response approach based on response surface methodology has widely been investigated and adopted for the purpose of robust design. Separately estimating mean and variance responses, dual response approach may take advantages of optimization modeling for finding optimum settings of input factors. Explicitly assuming functional relationship between responses and input factors, however, it may not work well enough especially when the behavior of responses are poorly represented. A sufficient number of experimentations are required to improve the precision of estimations. This study proposes an alternative to dual response approach in which additional experiments are not required. An artificial neural network has been applied to model relationships between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Training, validating, and testing a neural network with empirical process data, an artificial data based on the neural network may be generated and used to estimate response functions without performing real experimentations. A drug formulation example from pharmaceutical industry has been investigated to demonstrate the procedures and applicability of the proposed approach.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.05a
• /
• pp.607-608
• /
• 2012

• Journal of KSNVE
• /
• v.4 no.1
• /
• pp.59-69
• /
• 1994

A new LMS algorithm titled constrained LMS' is proposed for problems with constrained structure. The conventional LMS algorithm can not be used because it destroys the constrained structures of the weights or parameters. Proposed method uses error-back propagation, which is popular in training neural networks, for error minimization. The illustrative examplesare shown to demonstrate the applicability of the proposed algorithm.

• Proceedings of the KIEE Conference
• /
• 2006.10d
• /
• pp.50-52
• /
• 2006

This paper Proposes a new method of on-line estimation for rotor resistance of the induction motor in the indirect vector controlled drive, using artificial neural network (ANN). The back propagation algorithm is used for training of the neural networks. The error between the desired state variable of an induction motor and actual state variable of a neural network model is back propagated to adjust the weight of a neural network model, so that the actual state variable tracks the desired value. The performance of rotor resistance estimator and torque and flux responses of drive, together with these estimators, are investigated variations rotor resistance from their nominal values. The rotor resistance are estimated analytically, using the proposed ANN in a vector controlled induction motor drive.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.747-753
• /
• 1997

Function approximation from a set of input-output parirs has numerous applications in scientiffc and engineer-ing areas.Multiayer feedforward neural networks have been proposed as a good approximator of noninear function.The back propagation (BP) algorithm allows muktiayer feedforward neural networks oro learn input-output mappongs from training samples.However, the mapping acquired through the BP algorithm nay be cor-rupt when errorneous trauning data are employed.In this paper we propose a robust BP learning algorithm that is resistant to the errormeous data and is capable of rejecting gross errors during the approximation process.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.34-37
• /
• 2005

An efficient and robust neural network-based scheme is introduced in this paper to perform automatic cloud detection. Unlike many existing cloud detection schemes which use thresholding and statistical methods, we used the artificial neural network methods, the multi-layer perceptrons (MLP) with back-propagation algorithm and radial basis function (RBF) networks for cloud detection from Geostationary satellite images. We have used a simple scene (a mixed scene containing only cloud and clear sky). The main results show that the neural networks are able to handle complex atmospheric and meteorological phenomena. The experimental results show that two methods performed well, obtaining a classification accuracy reaching over 90 percent. Moreover, the RBF model is the most effective method for the cloud classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.310-314
• /
• 2000

This paper proposes a new parallel architecture for extracting the object from binarized images using recurrent linear threshold neural networks. Binary functions are initially obtained from the existing iterative thinning algorithms, and the linear threshold neural threshold neural networks are then synthesized using the MSP term grouping algorithm. Experimental results show that the proposed architectures can be implemented easier than with other existing methods.