By Topic

NNERVE: Neural Network Extraction of Repetitive Vectors for Electromyography. II. Performance analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Hassoun, M.H. ; Dept. of Electr. & Comput. Eng., Wayne State Univ., Detroit, MI, USA ; Wang, C. ; Spitzer, A.R.

For pt. I see ibid., vol. 41, no. 11, p. 1039-53 (1994). In pt. I the authors presented a new method for the decomposition of clinical electromyographic signals, NNERVE, which utilizes a novel "pseudo-unsupervised" neural network approach to signal decomposition. Here the authors present a detailed performance analysis. They present definitions for quantitative performance criteria. NNERVE is shown to be highly reliable over a wide range of neural network architectures. It is also minimally sensitive to learning parameters. The degradations of performance over a wide range of signals and parameters are shown to be gradual, slight and graceful. These characteristics are shown to translate directly into a high degree of robustness over widely varying signals. Real signals obtained from the entire range of patients encountered in clinical situations are shown to be correctly handled without any modifications or adjustments of any parameters. This neural network method is then directly compared to a prior traditional signal processing method and is shown quantitatively to have consistently superior performance on both simulated and real signals. Clinically acceptable performance over a wide range of signals, recorded using standard clinical methodology, and the lack of a need for user interaction, will facilitate the use of motor unit quantitation in routine clinical electromyography.

Published in:

Biomedical Engineering, IEEE Transactions on  (Volume:41 ,  Issue: 11 )