Multilayered GMDH-Type Neural Network with Radial Basis Functions and its Application to 3-Dimensional Medical Image Recognition of the Liver
Tadashi Kondo*, Junji Ueno*, and Abhijit S. Pandya**
*School of Health Sciences, The University of Tokushima, 3-18-15 Kuramoto-cho, Tokushima 770-8509, Japan
**Computer Sciences & Engineering, Florida Atlantic University, Boca Raton, FL 33431, U.S.A.
In this paper, a Group Method of Data Handling (GMDH)-type neural network algorithm with radial basis functions (RBF) is proposed. The proposed algorithm generates optimum RBF network architectures fitting the complexity of nonlinear systems using heuristic self-organization. The number of hidden layers, the number of neurons in hidden layers and relevant input variables are selected by minimizing prediction error defined as Akaike’s Information Criterion (AIC). Various nonlinear combinations of variables are initially generated in each layer and only relevant combinations are selected based on AIC. Hence, the optimum RBF network architecture fitting the complexity of the nonlinear system is obtained. We apply the GMDH-type neural network algorithm with RBF to 3-dimensional medical image recognition of the liver, showing that this algorithm is very easy and useful in 3-dimensional medical image recognition of the liver because the neural network architecture is automatically organized to minimize prediction error based on AIC.
-  T. Kondo, “GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem,” Proc. of the 37th SICE Annual Conference, pp. 1143-1148, 1998.
-  T. Kondo, A. S. Pandya, and J. M. Zurada, “GMDH-type neural networks and their application to the medical image recognition of the lungs,” Proc. of the 38th SICE Annual Conference, pp. 1181-1186, 1999.
-  T. Kondo, J. Ueno, and K. Kondo, “Revised GMDH-type Neural Networks Using AIC and PSS Criterion and Their Application to Medical Image Recognition,” Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.9, No.3, pp. 257-267, 2005.
-  A. G. Ivakhnenko, “Heuristic self-organization in problems of engineering cybernetics,” Automatica, Vol.6, No.2, pp. 207-219, 1970.
-  S. J. Farlow (ed.), “Self-organizing Methods in Modeling, GMDHtype Algorithms,” Marcel Dekker, Inc., New York, 1984.
-  H. Akaike, “A new look at the statistical model identification,” IEEE Trans. Automatic Control, Vol.AC-19, No.6, pp. 716-723, 1974.
-  H. Tamura and T. Kondo, “Heuristics free group method of data handling algorithm of generating optimum partial polynomials with application to air pollution prediction,” Int. J. System Sci., Vol.11, No.9, pp. 1095-1111, 1980.
-  D. M. Allen, “The relationship between variable selection and data augmentation and a method for prediction,” Technometrics, Vol.16, No.1, pp. 125-127, 1974.
-  J. Moody and C. J. Darken, “Fast learning in networks of locallytuned processing units,” Neural Computation, Vol.1, pp. 281-294, 1989.
-  N. R. Draper and H. Smith, “Applied Regression Analysis,” John Wiley and Sons, New York, 1981.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.