Abstract
Three CMAC-based neural networks (CMAC, FCMAC, ANFIS) are respectively introduced to deal with four medical image classification problems. According to our experiments, the features and applicability of these three classifiers are discussed. At the same time, a series of optimization methods based on wavelet transform, genetic algorithm, and self-organization competition neural network are applied on FCMAC and ANFIS in order to increase convergence speed and reduce memory requirement.
Supported by NSFC (No. 60272029) and NSF of Zhejiang Province (No. M603227)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Albus, J.S.: Data Storage in the Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems, Measurement, and Control, Trans. of ASME 97, 228–233 (1975)
Brown, M., Harris, C.J.: Neurofuzzy Adaptive Modeling and Control. Prentice-Hall, Englewood Cliffs (1997)
Yu, H., Yu, J.S.: A Novel Fuzzy CMAC Network and Its Application. Control and Instruments in Chemical Industry 30, 28–32 (2003)
Jang, J.-S.R.: ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Trans. on System, Man, and Cybernetics 23, 665–685 (1993)
Cong, S., Li, G.D.: The Decrease of Fuzzy Label Number Using Self-Organization Competition Network. In: International ICSC/IFAC Symposium on Neural Computation (NC 1998), Vienna University of Technology, Austria, pp. 106–112 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, W., Xia, S., Xie, H. (2004). Application of CMAC-Based Networks on Medical Image Classification. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_157
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_157
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive