Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals
For brain–computer interfaces (BCIs) to be viable for long-term daily usage, they must be able to quickly identify and adapt to signal disruptions. Furthermore, the detection and mitigation steps need to occur automatically and without the need for user intervention while also being computationally...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.858377/full |
| _version_ | 1828841706095640576 |
|---|---|
| author | Jordan L. Vasko Laura Aume Sanjay Tamrakar Samuel C. IV Colachis Collin F. Dunlap Collin F. Dunlap Adam Rich Eric C. Meyers David Gabrieli David A. Friedenberg |
| author_facet | Jordan L. Vasko Laura Aume Sanjay Tamrakar Samuel C. IV Colachis Collin F. Dunlap Collin F. Dunlap Adam Rich Eric C. Meyers David Gabrieli David A. Friedenberg |
| author_sort | Jordan L. Vasko |
| collection | DOAJ |
| description | For brain–computer interfaces (BCIs) to be viable for long-term daily usage, they must be able to quickly identify and adapt to signal disruptions. Furthermore, the detection and mitigation steps need to occur automatically and without the need for user intervention while also being computationally tractable for the low-power hardware that will be used in a deployed BCI system. Here, we focus on disruptions that are likely to occur during chronic use that cause some recording channels to fail but leave the remaining channels unaffected. In these cases, the algorithm that translates recorded neural activity into actions, the neural decoder, should seamlessly identify and adjust to the altered neural signals with minimal inconvenience to the user. First, we introduce an adapted statistical process control (SPC) method that automatically identifies disrupted channels so that both decoding algorithms can be adjusted, and technicians can be alerted. Next, after identifying corrupted channels, we demonstrate the automated and rapid removal of channels from a neural network decoder using a masking approach that does not change the decoding architecture, making it amenable for transfer learning. Finally, using transfer and unsupervised learning techniques, we update the model weights to adjust for the corrupted channels without requiring the user to collect additional calibration data. We demonstrate with both real and simulated neural data that our approach can maintain high-performance while simultaneously minimizing computation time and data storage requirements. This framework is invisible to the user but can dramatically increase BCI robustness and usability. |
| first_indexed | 2024-12-12T20:08:48Z |
| format | Article |
| id | doaj.art-a64a7450ff584f889abde5de2d31d6b0 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-12T20:08:48Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-a64a7450ff584f889abde5de2d31d6b02022-12-22T00:13:34ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-04-011610.3389/fnins.2022.858377858377Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input SignalsJordan L. Vasko0Laura Aume1Sanjay Tamrakar2Samuel C. IV Colachis3Collin F. Dunlap4Collin F. Dunlap5Adam Rich6Eric C. Meyers7David Gabrieli8David A. Friedenberg9Battelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesDepartment of Biomedical Engineering, The Ohio State University, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesBattelle Memorial Institute, Columbus, OH, United StatesFor brain–computer interfaces (BCIs) to be viable for long-term daily usage, they must be able to quickly identify and adapt to signal disruptions. Furthermore, the detection and mitigation steps need to occur automatically and without the need for user intervention while also being computationally tractable for the low-power hardware that will be used in a deployed BCI system. Here, we focus on disruptions that are likely to occur during chronic use that cause some recording channels to fail but leave the remaining channels unaffected. In these cases, the algorithm that translates recorded neural activity into actions, the neural decoder, should seamlessly identify and adjust to the altered neural signals with minimal inconvenience to the user. First, we introduce an adapted statistical process control (SPC) method that automatically identifies disrupted channels so that both decoding algorithms can be adjusted, and technicians can be alerted. Next, after identifying corrupted channels, we demonstrate the automated and rapid removal of channels from a neural network decoder using a masking approach that does not change the decoding architecture, making it amenable for transfer learning. Finally, using transfer and unsupervised learning techniques, we update the model weights to adjust for the corrupted channels without requiring the user to collect additional calibration data. We demonstrate with both real and simulated neural data that our approach can maintain high-performance while simultaneously minimizing computation time and data storage requirements. This framework is invisible to the user but can dramatically increase BCI robustness and usability.https://www.frontiersin.org/articles/10.3389/fnins.2022.858377/fullbrain–machine (computer interface)neuroprostheticdeep learning – artificial neural networkintracortical arraystatistical process control |
| spellingShingle | Jordan L. Vasko Laura Aume Sanjay Tamrakar Samuel C. IV Colachis Collin F. Dunlap Collin F. Dunlap Adam Rich Eric C. Meyers David Gabrieli David A. Friedenberg Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals Frontiers in Neuroscience brain–machine (computer interface) neuroprosthetic deep learning – artificial neural network intracortical array statistical process control |
| title | Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals |
| title_full | Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals |
| title_fullStr | Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals |
| title_full_unstemmed | Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals |
| title_short | Increasing Robustness of Brain–Computer Interfaces Through Automatic Detection and Removal of Corrupted Input Signals |
| title_sort | increasing robustness of brain computer interfaces through automatic detection and removal of corrupted input signals |
| topic | brain–machine (computer interface) neuroprosthetic deep learning – artificial neural network intracortical array statistical process control |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.858377/full |
| work_keys_str_mv | AT jordanlvasko increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT lauraaume increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT sanjaytamrakar increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT samuelcivcolachis increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT collinfdunlap increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT collinfdunlap increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT adamrich increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT ericcmeyers increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT davidgabrieli increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals AT davidafriedenberg increasingrobustnessofbraincomputerinterfacesthroughautomaticdetectionandremovalofcorruptedinputsignals |