Pixel1.gif (51 bytes)
Pixel1.gif (51 bytes)
Pixel1.gif (51 bytes) Main Page Pixel1.gif (51 bytes)
About DSP Laboratory
People
Research
Publications
Courses
Pixel.gif (52 bytes)
Contact Us
Sponsors
Credits
Pixel.gif (52 bytes)
Search
Go to FIU's Homepage

 

 Pixel1.gif (51 bytes)

 

Curve.gif (104 bytes) Pixel1.gif (51 bytes)

Electromyograms as Physiological Inputs that Provide Efficient Computer Cursor Control

Pixel1.gif (51 bytes)

Abstract:
 
"Electromyograms as Physiological Inputs that Provide Efficient Computer Cursor Control", (2006)
Chin, C., and Barreto, A.

ABSTRACT: This paper presents a new algorithm to translate electromyogram (EMG) signals, produced during facial muscle contractions, into computer cursor actions. These cursor actions are: left, right, up, down and left-click. The translation is performed in real-time and the classification of the EMG signals is based on features derived from the spectral analysis of the electromyograms. We have sought to improve upon the original EMG-based cursor control system described in [1] [2], and have devised a new system set-up and algorithm for the translation of the EMG signals into cursor actions. The two systems were compared using Matlab simulations and point-and-click trials. The simulation results show a marked improvement of the new system over the previous system in terms of classification accuracy, and the preliminary point-and-click tests indicate the possibility of a faster operation for the new system when compared to the old system.