A parallel point-process filter for estimation of goal-directed movements from neural signals
Brain machine interfaces work by mapping the relevant neural activity to the intended movement known as 'decoding'. Here, we develop a recursive Bayesian decoder for goal-directed movements from neural observations, which exploits the optimal feedback control model of the sensorimotor syst...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2012
|
| Online Access: | http://hdl.handle.net/1721.1/70535 https://orcid.org/0000-0003-2668-7819 https://orcid.org/0000-0001-9166-4758 |
| _version_ | 1826195548155150336 |
|---|---|
| author | Modir Shanechi, Maryam Wornell, Gregory W. Williams, Ziv Brown, Emery N. |
| author2 | Harvard University--MIT Division of Health Sciences and Technology |
| author_facet | Harvard University--MIT Division of Health Sciences and Technology Modir Shanechi, Maryam Wornell, Gregory W. Williams, Ziv Brown, Emery N. |
| author_sort | Modir Shanechi, Maryam |
| collection | MIT |
| description | Brain machine interfaces work by mapping the relevant neural activity to the intended movement known as 'decoding'. Here, we develop a recursive Bayesian decoder for goal-directed movements from neural observations, which exploits the optimal feedback control model of the sensorimotor system to build better prior state-space models. These controlled state models depend on the movement duration that is not known a priori. We thus consider a discretization of the task duration and develop a decoder consisting of a bank of parallel point-process filters, each combining the neural observation with the controlled state model of a discretization point. The final reconstruction is made by optimally combining these filter estimates. Using very coarse discretization and hence only a few parallel branches, our decoder reduces the root mean square (RMS) error in trajectory reconstruction in reaches made by a rhesus monkey by approximately 40%. |
| first_indexed | 2024-09-23T10:14:27Z |
| format | Article |
| id | mit-1721.1/70535 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:14:27Z |
| publishDate | 2012 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/705352022-09-26T16:38:42Z A parallel point-process filter for estimation of goal-directed movements from neural signals Modir Shanechi, Maryam Wornell, Gregory W. Williams, Ziv Brown, Emery N. Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Brown, Emery N. Brown, Emery N. Modir Shanechi, Maryam Wornell, Gregory W. Williams, Ziv Brain machine interfaces work by mapping the relevant neural activity to the intended movement known as 'decoding'. Here, we develop a recursive Bayesian decoder for goal-directed movements from neural observations, which exploits the optimal feedback control model of the sensorimotor system to build better prior state-space models. These controlled state models depend on the movement duration that is not known a priori. We thus consider a discretization of the task duration and develop a decoder consisting of a bank of parallel point-process filters, each combining the neural observation with the controlled state model of a discretization point. The final reconstruction is made by optimally combining these filter estimates. Using very coarse discretization and hence only a few parallel branches, our decoder reduces the root mean square (RMS) error in trajectory reconstruction in reaches made by a rhesus monkey by approximately 40%. National Institutes of Health (U.S.) (Grant No. DP1- 0D003646-01) National Institutes of Health (U.S.) (Grant R01-EB006385) Microsoft Research 2012-05-07T20:36:09Z 2012-05-07T20:36:09Z 2010-06 2010-03 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-4295-9 1520-6149 INSPEC Accession Number: 11553666 http://hdl.handle.net/1721.1/70535 Shanechi, Maryam Modir et al. “A Parallel Point-process Filter for Estimation of Goal-directed Movements from Neural Signals.” IEEE, 2010. 521–524. Web. © 2010 IEEE. https://orcid.org/0000-0003-2668-7819 https://orcid.org/0000-0001-9166-4758 en_US http://dx.doi.org/10.1109/ICASSP.2010.5495644 Proceedings of the 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Modir Shanechi, Maryam Wornell, Gregory W. Williams, Ziv Brown, Emery N. A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title | A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title_full | A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title_fullStr | A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title_full_unstemmed | A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title_short | A parallel point-process filter for estimation of goal-directed movements from neural signals |
| title_sort | parallel point process filter for estimation of goal directed movements from neural signals |
| url | http://hdl.handle.net/1721.1/70535 https://orcid.org/0000-0003-2668-7819 https://orcid.org/0000-0001-9166-4758 |
| work_keys_str_mv | AT modirshanechimaryam aparallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT wornellgregoryw aparallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT williamsziv aparallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT brownemeryn aparallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT modirshanechimaryam parallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT wornellgregoryw parallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT williamsziv parallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals AT brownemeryn parallelpointprocessfilterforestimationofgoaldirectedmovementsfromneuralsignals |