A detection method of body movement signals measured with magnetic tracking device for human balance investigations
by Jyrki Rasku, Martti Juhola
International Journal of Medical Engineering and Informatics (IJMEI), Vol. 2, No. 1, 2010

Abstract: The article addresses a signal analysis technique to be used for humans' balance signals. Our preliminary measurements consist of signals of healthy volunteers. Such signals are useful in order to investigate balance problems of vertiginous patients. We studied body movements during standing by means of magnetic sensors for the purpose of humans' balance investigations. Two test conditions were applied when a subject steadily stood and kept eyes either open or closed. Hidden Markov models were constructed and tested for these balance signals, and they were used to detect between the two test conditions. Before modelling it was necessary to smooth three-dimensional signals, which was performed by Kalman filtering. Recognition accuracies of the models were fairly good between the two test conditions, eyes open or closed, which is the basic test executed in posturography but often difficult, because differences between signals of two test conditions are typically small. The current method seemed to be efficient in order to distinguish the two test conditions among young, healthy subjects.

Online publication date: Wed, 02-Dec-2009

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 Medical Engineering and Informatics (IJMEI):
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