Dynamic SVM detection of tremor and dyskinesia during unscripted and unconstrained activities

Author

Cole, Bryan T. ; Ozdemir, P. ; Nawab, S. Hamid

Author_Institution

Drager Med. Syst., Inc., Andover, MA, USA

fYear

2012

fDate

Aug. 28 2012-Sept. 1 2012

Firstpage

4927

Lastpage

4930

Abstract

In this paper, we report an experimental comparison of dynamic support vector machines (SVMs) to dynamic neural networks (DNNs) in the context of a system for detecting dyskinesia and tremor in Parkinson´s disease (PD) patients wearing accelerometer (ACC) and surface electromyographic (sEMG) sensors while performing unscripted and unconstrained activities of daily living. These results indicate that SVMs and DNNs of comparable computational complexities yield approximately identical performance levels when using an identical set of input features.

Keywords

accelerometers; biomedical measurement; diseases; electromyography; medical signal processing; neural nets; support vector machines; DNN; Parkinson disease patients; accelerometer; dynamic SVM dyskinesia detection; dynamic SVM tremor detection; dynamic neural networks; support vector machines; surface electromyographic sensors; unconstrained activities; unscripted activities; Error analysis; Kernel; Neural networks; Sensors; Support vector machines; Training; Actigraphy; Algorithms; Diagnosis, Computer-Assisted; Dyskinesias; Humans; Monitoring, Ambulatory; Parkinson Disease; Reproducibility of Results; Sensitivity and Specificity; Support Vector Machines; Tremor;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE

Conference_Location

San Diego, CA

ISSN

1557-170X

Print_ISBN

978-1-4244-4119-8

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/EMBC.2012.6347040

Filename

6347040