Abstract
The conventional neural networks methods of motor unit action potential analysis in clinical Electromyography are mainly based on single feature set model, the diagnosis accuracy of which is not always satisfactory. In order to utilize multiple feature sets to improve diagnosis accuracy, a hybrid decision support system based on fusion of multiple feature sets classification outputs is presented. Back-propagation (BP) neural network is used as single diagnosis model in every feature set, i.e. i) time domain morphological measures, ii) frequency parameters, and iii) time-frequency domain wavelet transform feature set. Then these outputs are combined by a modified fuzzy integral method to obtain the consensus diagnosis result. More excellent diagnosis yield indicates the potential of the proposed multiple feature domain strategies for aiding the neurophysiologist in the early and accurate diagnosis of neuromuscular disorders. The method is also compared with the majority vote combination scheme.
This is a preview of subscription content, log in via an institution to check access.
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
Stalberg, E., Nandedkar, S.D., Sanders, D.B.: Quantitative Motor unit potential analysis. Clinical Neurophysiology 13, 401–422 (1996)
Andreassen, S., Andreassen, S.K., Jensen, F.V.: MUNIN—An expert system for EMG. Electroence Clinical Neurophysiol. 66, S4 (1987)
Coatrieux, J.L., Toulouse, P., Rouvrais, B.: Automatic classification of electromyographic signals. Electroence Clin Neurophysiol. 55, 333–341 (1983)
Pattichis, C.S., Elia, A.C.: Autoregressive and cepstral analyses of motor unit action potentials. Med. Eng. Physi. 21, 405–419 (1999)
Shipp, C.A., Kuncheva, L.I.: Relationships between combination methods and measures of diversity in combining classifiers. Information Fusion 3, 135–148 (2002)
Sugeno, M.: Fuzzy measures and fuzzy integrals: a survey. In: Fuzzy Automata and Decision Processes, Amsterdam. North Holland (1977)
He, Y.Y., Chu, F.L., Zhong, B.L.: A study on group decision-make based fault multi-symptom- domain consensus diagnosis. Reliability Engineering & System Safety 74, 43–52 (2001)
Stalberg, E., Andreassen, S., Falck, B.: Quantitative analysis of individual motor unit potentials: A proposition for standardized terminology and criteria for measurement. Clinl. Neurophysiol. 3, 313–348 (1986)
Cioffi, J.M., Kailath, T.: Fast recursive least-squares traversal filters for adaptive filtering. IEEE Trans Acoust Speech Sig. Process 32, 304–337 (1984)
Lindsotrm, L., Petersen, I.: Power spectrum analysis of EMG signals and its application. In: Desmedt, J.E. (ed.) Computer-Aided Electromyography Prog. Clin. Neurophysiol. Basel, Karger, vol. 10, pp. 1–51 (1983)
Breiman, L.: Bagging predictors. Machine Learning 24, 123–140 (1996)
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
Xie, H., Huang, H., Wang, Z. (2005). Multiple Feature Domains Information Fusion for Computer-Aided Clinical Electromyography. In: Gagalowicz, A., Philips, W. (eds) Computer Analysis of Images and Patterns. CAIP 2005. Lecture Notes in Computer Science, vol 3691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11556121_38
Download citation
DOI: https://doi.org/10.1007/11556121_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28969-2
Online ISBN: 978-3-540-32011-1
eBook Packages: Computer ScienceComputer Science (R0)