We propose the use of nonnegative matrix factorization (NMF) as a model-independent methodology to analyze neural activity. We demonstrate that, using this technique, it is possible to identify local spatiotemporal patterns of neural activity in the form of sparse basis vectors. In addition, the sparseness of these bases can help infer correlations between cortical firing patterns and behavior. We demonstrate the utility of this approach using neural recordings collected in a brain-machine interface (BMI) setting. The results indicate that, using the NMF analysis, it is possible to improve the performance of BMI models through appropriate pruning of inputs.
This article is part of the series Trends in Brain Computer Interfaces.
Determining Patterns in Neural Activity for Reaching Movements Using Nonnegative Matrix Factorization
1 Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA
2 Motorola Inc., FL, USA
3 Department of Computer Science and Biomedical Engineering, Oregon Health & Science University, Beaverton, OR 97006, USA
4 Department of Pediatrics, Division of Neurology, University of Florida, Gainesville, FL 32611, USA
5 Department of Neurobiology, Center for Neuroengineering, Duke University, Durham, NC 27710, USA
EURASIP Journal on Advances in Signal Processing 2005, 2005:829802 doi:10.1155/ASP.2005.3113
The electronic version of this article is the complete one and can be found online at: http://asp.eurasipjournals.com/content/2005/19/829802
|Received:||31 January 2004|
|Revisions received:||23 March 2005|
|Published:||17 November 2005|
© 2005 Kim et al.