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

Sung Phil Kim, Yadunandana N. Rao, Deniz Erdogmus, Justin C. Sanchez, Miguel A.L. Nicolelis, Jose C. Principe

Research output: Contribution to journalArticle

10 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)3113-3121
Number of pages9
JournalEurasip Journal on Applied Signal Processing
Volume2005
Issue number19
DOIs
StatePublished - Dec 1 2005

    Fingerprint

Keywords

  • Brain-machine interfaces
  • Neural firing activity
  • Nonnegative matrix factorization
  • Spatiotemporal patterns

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Signal Processing

Cite this

Kim, S. P., Rao, Y. N., Erdogmus, D., Sanchez, J. C., Nicolelis, M. A. L., & Principe, J. C. (2005). Determining patterns in neural activity for reaching movements using nonnegative matrix factorization. Eurasip Journal on Applied Signal Processing, 2005(19), 3113-3121. https://doi.org/10.1155/ASP.2005.3113