Performance index assessment of intelligent computing methods in EMG-based neuromuscular diseases
by Babita Pandey; R.B. Mishra
International Journal of Knowledge Engineering and Soft Data Paradigms (IJKESDP), Vol. 4, No. 1, 2013

Abstract: In the medical systems, there is a lack of determining and assessing the performance measure of the intelligent computing methods (ICM) deployed in the diagnosis of bioelectric signals (EEG/EMG/ECG)-based diseases. There have been few attempts for performance measure of mathematical models in medical computing. In this paper, we have developed a heuristic method for the assessment of performance measure in the diagnosis of EMG-based neuromuscular diseases. Firstly, we review the various ICM then we perform qualitative assessment of mathematical, algorithmic and heuristic content, data acquisition cost as well as medical consultancy cost of various parameter of EMG and non-EMG (psychological, cognitive and muscular). The computational overhead (CO) of EMG parameters, overall computational overhead (OCO) and clinical consultancy cost (CC) are determined. Finally, performance index (PI) is computed based on the two overheads and clinical cost. A graph showing the comparative view of CO of EMG parameters, OCO and CC is plotted and PI is shown for all the methods.

Online publication date: Sat, 19-Jul-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Knowledge Engineering and Soft Data Paradigms (IJKESDP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com