Determining Patterns in Neural Activity for Reaching Movements Using Nonnegative Matrix Factorization

  • Sung-Phil Kim1Email author,

    Affiliated with

    • Yadunandana N. Rao2,

      Affiliated with

      • Deniz Erdogmus3,

        Affiliated with

        • Justin C. Sanchez4,

          Affiliated with

          • Miguel A. L. Nicolelis5 and

            Affiliated with

            • Jose C. Principe1

              Affiliated with

              EURASIP Journal on Advances in Signal Processing20052005:829802

              DOI: 10.1155/ASP.2005.3113

              Received: 31 January 2004

              Published: 17 November 2005


              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.

              Keywords and phrases

              brain-machine interfaces nonnegative matrix factorization spatiotemporal patterns neural firing activity

              Authors’ Affiliations

              Department of Electrical and Computer Engineering, University of Florida
              Motorola Inc.
              Department of Computer Science and Biomedical Engineering, Oregon Health & Science University
              Department of Pediatrics, Division of Neurology, University of Florida
              Department of Neurobiology, Center for Neuroengineering, Duke University


              © Kim et al. 2005