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)

Signal Processing Approaches for EMG-based Hands-off Cursor Control

Pixel1.gif (51 bytes)

Abstract:
 
"Signal Processing Approaches for EMG-based Hands-off Cursor Control", (2005)
Craig Chin and Armando Barreto

ABSTRACT: There are numerous scenarios in which it would be preferred or necessary to manipulate the screen cursor of a computer’s graphic user interface (GUI). Some specialized operators, such as pilots or surgeons may need to interact with computer-based equipment while their hands are committed to tasks with higher priorities. For individuals with severe motor disabilities, who may not be able to perform movements from the neck down, manipulation of a “hand-held mouse for directing the pointing and clicking functions associated with the screen cursor is not possible. These diverse needs have inspired the design and development of interfaces that do not require the usual coordinated movements of the user’s hands to drive the screen cursor in the GUI. Part of these efforts have been devoted to the potential use of electrical activity that is generated by the activation of excitable cells in our brain and muscles, to control the movements and functions of the screen cursor. Several groups around the world are actively pursuing the development of interfaces driven by the electroencephalogram (EEG) signals recorded from the head of the user. These interfaces are often referred to as “Brain-Computer Interfaces”, or BCIs. For the last 5 years, our group has targeted the development of cursor control approaches that utilize a different biopotential signal: the electromyogram (EMG) from facial muscles, i.e., the electrical signal changes that take place when the user contracts some specific muscles in his/her face. A large proportion of individuals with severe motor disabilities still retain control over these muscles. Initially, an EMG-based cursor control system was created to provide real-time, hands-free cursor control from signals collected through three surface electrodes. This initial system uses the real-time spectral analysis of three EMG signals to produce the following five cursor actions: i) LEFT, ii) RIGHT, iii) UP, iv) DOWN, v) LEFT-CLICK. The three EMG signals are obtained from two surface electrodes placed on the left and right temples of the head and one electrode placed in the forehead region. It was found, however, that the differentiation between lowering and raising the eyebrows to move the cursor DOWN and UP, respectively, from just one EMG signal was particularly (and maybe unnecessarily) challenging. Accordingly, it was proposed that the three-electrode system be converted into a four-electrode system, using two electrodes in the forehead of the user, instead of one. This paper compares the effectiveness of the four-electrode system to that of the three-electrode system in classifying EMG activity into cursor actions through the use of Matlab simulations. It will be shown that the new four-electrode system produces significant improvements in classification performance.