Efficient Decoding With Steady-State Kalman Filter in Neural Interface Systems
The Kalman filter is commonly used in neural interface systems to decode neural activity and estimate the desired movement kinematics.We analyze a low-complexity Kalman filter implementation in which the filter gain is approximated by its steady-state form, computed offline before real-time decoding...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2012
|
| Online Access: | http://hdl.handle.net/1721.1/70553 https://orcid.org/0000-0003-2668-7819 https://orcid.org/0000-0002-7260-7560 |
| Summary: | The Kalman filter is commonly used in neural interface systems to decode neural activity and estimate the desired movement kinematics.We analyze a low-complexity Kalman filter implementation in which the filter gain is approximated by its steady-state form, computed offline before real-time decoding commences. We evaluate its performance using human motor
cortical spike train data obtained from an intracortical recording array as part of an ongoing pilot clinical trial. We demonstrate that the standard Kalman filter gain converges to within 95% of the steady-state filter gain in 1.5[plus-over-minus sign]0.5 s (mean[plus-over-minus sign]s.d.) . The difference in the intended movement velocity decoded by the two filters vanishes within 5 s, with a correlation coefficient of 0.99 between the two decoded velocities over the session length. We also find that the steady-state Kalman filter reduces the computational load (algorithm execution time) for decoding the firing
rates of 25[plus-over-minus sign]3 single units by a factor of 7.0[plus-over-minus sign]0.9. We expect that the gain in computational efficiency will be much higher in
systems with larger neural ensembles. The steady-state filter can thus provide substantial runtime efficiency at little cost in terms of estimation accuracy. This far more efficient neural decoding approach will facilitate the practical implementation of future
large-dimensional, multisignal neural interface systems. |
|---|