Abstract/Details

Adaptive online brain -computer interface for interpretation and visualization of desired reach


2009 2009

Other formats: Order a copy

Abstract (summary)

We present an adaptive online brain-computer interface (BCI) based on natural reaching motor imagery with feedback of realistic animations of the intended reaching task.

We describe a unified approach to BCI design which addresses the complete system simultaneously to improve the overall user experience. In Chapter 2 we show how the proper selection of processing steps and combination of classifiers improves system accuracy. Chapter 3 discusses how realistic animations boost motor-imagery-related brain signals, and Chapter 4 describes classification rates in natural reaching tasks.

These findings come together in Chapter 5 where we describe our online system, which improves the user experience by eliminating training sessions, providing a very natural and straightforward mapping between user task and system feedback, and by using an adaptive classifier which can adjust to changes in brain signal over the time.

Research in this field has the potential to aid patients with motor disabilities, and it represents a novel way to study the brain. For users with severe motor disabilities such as ALS (Lou Gehrig's disease), a BCI may provide their only means of communicating with the world. Thus, reducing training time and improving the user's experience are important contributions to the BCI field.

Indexing (details)


Subject
Electrical engineering
Classification
0544: Electrical engineering
Identifier / keyword
Applied sciences; Brain-computer interface; Motor imagery; Reaching tasks
Title
Adaptive online brain -computer interface for interpretation and visualization of desired reach
Author
Hammon, Paul S.
Number of pages
106
Publication year
2009
Degree date
2009
School code
0033
Source
DAI-B 70/05, Dissertation Abstracts International
Place of publication
Ann Arbor
Country of publication
United States
ISBN
9781109149807
Advisor
Sa, Virginia R. de; Kreutz-Delgado, Kenneth
Committee member
Lanckriet, Gert; Pineda, Jaime A.; Vasconcelos, Nuno
University/institution
University of California, San Diego
Department
Electrical Engineering (Intelsys, Robotics and Cont)
University location
United States -- California
Degree
Ph.D.
Source type
Dissertations & Theses
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
3355687
ProQuest document ID
304851230
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Document URL
http://search.proquest.com/docview/304851230
Access the complete full text

You can get the full text of this document if it is part of your institution's ProQuest subscription.

Try one of the following:

  • Connect to ProQuest through your library network and search for the document from there.
  • Request the document from your library.
  • Go to the ProQuest login page and enter a ProQuest or My Research username / password.