Spectral Transfer Learning Using Information Geometry for a User-Independent Brain-Computer Interface

Guardat en:
Dades bibliogràfiques
Publicat a:Frontiers in Neuroscience (Sep 22, 2016), p. n/a
Autor principal: Waytowich, Nicholas R
Altres autors: Lawhern, Vernon J, Bohannon, Addison W, Ball, Kenneth R, Lance, Brent J
Publicat:
Frontiers Research Foundation
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 2305509796
003 UK-CbPIL
022 |a 1662-4548 
022 |a 1662-453X 
024 7 |a 10.3389/fnins.2016.00430  |2 doi 
035 |a 2305509796 
045 0 |b d20160922 
100 1 |a Waytowich, Nicholas R 
245 1 |a Spectral Transfer Learning Using Information Geometry for a User-Independent Brain-Computer Interface 
260 |b Frontiers Research Foundation  |c Sep 22, 2016 
513 |a Journal Article 
520 3 |a Recent advances in signal processing and machine learning techniques have enabled the application of Brain-Computer Interface (BCI) technologies to fields such as medicine, industry and recreation. However, BCIs still suffer from the requirement of frequent calibration sessions due to the intra- and inter- individual variability of brain-signals, which makes calibration suppression through transfer learning an area of increasing interest for the development of practical BCI systems. In this paper, we present an unsupervised transfer method (spectral transfer using information geometry, STIG), which ranks and combines unlabeled predictions from an ensemble of information geometry classifiers built on data from individual training subjects. The STIG method is validated in both offline and real-time feedback analysis during a rapid serial visual presentation task (RSVP). For detection of single-trial, event-related potentials (ERPs), the proposed method can significantly outperform existing calibration-free techniques as well as outperform traditional within-subject calibration techniques when limited data is available. This method demonstrates that unsupervised transfer learning for single-trial detection in ERP-based BCIs can be achieved without the requirement of costly training data, representing a step-forward in the overall goal of achieving a practical user-independent BCI system. 
610 4 |a Government Publishing Office--GPO 
651 4 |a United States--US 
653 |a Laboratories 
653 |a Brain 
653 |a Computer science 
653 |a Brain research 
653 |a Calibration 
653 |a Signal processing 
653 |a Classification 
653 |a Implants 
653 |a Event-related potentials 
653 |a Computer applications 
653 |a Paradigms 
653 |a Geometry 
653 |a Visualization 
653 |a Learning algorithms 
653 |a Transfer learning 
653 |a Pattern recognition 
653 |a Machine learning 
653 |a Artificial intelligence 
700 1 |a Lawhern, Vernon J 
700 1 |a Bohannon, Addison W 
700 1 |a Ball, Kenneth R 
700 1 |a Lance, Brent J 
773 0 |t Frontiers in Neuroscience  |g (Sep 22, 2016), p. n/a 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2305509796/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/2305509796/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/2305509796/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch