Abstract
In Traditional Chinese Medicine (TCM), it is difficult to interpret how to judge syndrome according to clinic information in scientific means because TCM depends mostly on experience and subjective judgment. Now there are more and more people begin to study TCM with modern techniques in many countries. Neural network techniques have developed quickly during these years and many complex problems are solved with them. It is feasible to discover the hidden mechanism of TCM with neuron network. In this paper a multilevel neural network model is developed to dispose TCM problem. In this model, Principle Component Analysis network is used to preprocess symptoms and back-propagation network is used to give out syndromes and Boltzmann machine is used to give out prescription. After training, the network can realize the whole diagnosis procedure. The feasibility is illustrated through simulation example with stroke patients’ clinical data.
The research was supported by National Basic Research Program of China (973 program) under grant No. (2003CB517106).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Qin, B., He, Y.M., et al.: Neural Network Model of TCM Syndromes Based on MFBP Learning Algorithm. Chinese J. Basic Med TCM 7, 66–69 (2001)
Hu, J.N., Yan, S.C., et al.: An Intelligent Traditional Chinese Medicine Pulse Analysis System Model Based on Artificial Neural Network. Journal of China Medical University 26, 134–137 (1997)
Fan, X.P., Peng, Z., et al.: Study on Depression Classified System Based on Multilayer Perceptrons Artificial Neural Network. Computer Engineering and Application 40, 205–208 (2004)
Pang, B., Zhang, D.: Computerized Tongue Diagnosis Based on Bayesian Networks. IEEE Transactions on Biomedical Engineering 51, 1803–1810 (2004)
Clifford, C., Harry, W.: Color Image Compression Using PCA and Backpropagation Learning. Pattern Recognition 33, 1555–1560 (2000)
Simon, H.: Neural Networks: a Comprehensive Foundation (M). Prentice hall, New York (2001)
Xi, G.C.: Neural Network Based on Mean-Field Theory Approximation. ACTA Electronic SINICA 23, 62–64 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, Z., Yi, J., Xi, G. (2005). Multilevel Neural Network to Diagnosis Procedure of Traditional Chinese Medicine. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3498. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427469_127
Download citation
DOI: https://doi.org/10.1007/11427469_127
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25914-5
Online ISBN: 978-3-540-32069-2
eBook Packages: Computer ScienceComputer Science (R0)