Determining patterns in neural activity for reaching movements using nonnegative matrix factorization

Published

Journal Article

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. © 2005 Hindawi Publishing Corporation.

Full Text

Duke Authors

Cited Authors

  • Kim, SP; Rao, YN; Erdogmus, D; Sanchez, JC; Nicolelis, MAL; Principe, JC

Published Date

  • December 1, 2005

Published In

Volume / Issue

  • 2005 / 19

Start / End Page

  • 3113 - 3121

Electronic International Standard Serial Number (EISSN)

  • 1687-0433

International Standard Serial Number (ISSN)

  • 1110-8657

Digital Object Identifier (DOI)

  • 10.1155/ASP.2005.3113

Citation Source

  • Scopus