Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces
While it is important to make implantable brain-machine interfaces wireless to increase patient comfort and safety, the trend of increased channel count in recent neural probes poses a challenge due to the concomitant increase in the data rate. Extracting information from raw data at the source by u...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Neuromorphic Computing and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2634-4386/adba82 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850067852949716992 |
|---|---|
| author | Zhou Biyan Pao-Sheng Vincent Sun Arindam Basu |
| author_facet | Zhou Biyan Pao-Sheng Vincent Sun Arindam Basu |
| author_sort | Zhou Biyan |
| collection | DOAJ |
| description | While it is important to make implantable brain-machine interfaces wireless to increase patient comfort and safety, the trend of increased channel count in recent neural probes poses a challenge due to the concomitant increase in the data rate. Extracting information from raw data at the source by using edge computing is a promising solution to this problem, with integrated intention decoders providing the best compression ratio. Recent benchmarking efforts have shown recurrent neural networks to be the best solution. Spiking Neural Networks (SNN) emerge as a promising solution for resource efficient neural decoding while Long Short Term Memory (LSTM) networks achieve the best accuracy. In this work, we show that combining traditional signal processing techniques, namely signal filtering, with SNNs improve their decoding performance significantly for regression tasks, closing the gap with LSTMs, at little added cost. Results with different filters are shown with Bessel filters providing best performance. Two block-bidirectional Bessel filters have been used–one for low latency and another for high accuracy. Adding the high accuracy variant of the Bessel filters to the output of ANN, SNN and variants provided statistically significant benefits with maximum gains of $\approx 5\%$ and 8% in R ^2 for two SNN topologies (SNN_Streaming and SNN_3D). Our work presents state of the art results for this dataset and paves the way for decoder-integrated-implants of the future. |
| format | Article |
| id | doaj-art-2f5684b53a514d9ab96bac2f30ffbe30 |
| institution | DOAJ |
| issn | 2634-4386 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Neuromorphic Computing and Engineering |
| spelling | doaj-art-2f5684b53a514d9ab96bac2f30ffbe302025-08-20T02:48:12ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015101401310.1088/2634-4386/adba82Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfacesZhou Biyan0https://orcid.org/0009-0003-7725-8974Pao-Sheng Vincent Sun1https://orcid.org/0009-0008-7743-0961Arindam Basu2https://orcid.org/0000-0003-1035-8770City University of Hong Kong , Hong Kong Special Administrative Region of China, People’s Republic of ChinaCity University of Hong Kong , Hong Kong Special Administrative Region of China, People’s Republic of ChinaCity University of Hong Kong , Hong Kong Special Administrative Region of China, People’s Republic of ChinaWhile it is important to make implantable brain-machine interfaces wireless to increase patient comfort and safety, the trend of increased channel count in recent neural probes poses a challenge due to the concomitant increase in the data rate. Extracting information from raw data at the source by using edge computing is a promising solution to this problem, with integrated intention decoders providing the best compression ratio. Recent benchmarking efforts have shown recurrent neural networks to be the best solution. Spiking Neural Networks (SNN) emerge as a promising solution for resource efficient neural decoding while Long Short Term Memory (LSTM) networks achieve the best accuracy. In this work, we show that combining traditional signal processing techniques, namely signal filtering, with SNNs improve their decoding performance significantly for regression tasks, closing the gap with LSTMs, at little added cost. Results with different filters are shown with Bessel filters providing best performance. Two block-bidirectional Bessel filters have been used–one for low latency and another for high accuracy. Adding the high accuracy variant of the Bessel filters to the output of ANN, SNN and variants provided statistically significant benefits with maximum gains of $\approx 5\%$ and 8% in R ^2 for two SNN topologies (SNN_Streaming and SNN_3D). Our work presents state of the art results for this dataset and paves the way for decoder-integrated-implants of the future.https://doi.org/10.1088/2634-4386/adba82implantable-brain machine interfaceintention decoderspiking neural networkslow-power |
| spellingShingle | Zhou Biyan Pao-Sheng Vincent Sun Arindam Basu Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces Neuromorphic Computing and Engineering implantable-brain machine interface intention decoder spiking neural networks low-power |
| title | Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces |
| title_full | Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces |
| title_fullStr | Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces |
| title_full_unstemmed | Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces |
| title_short | Combining SNNs with filtering for efficient neural decoding in implantable brain-machine interfaces |
| title_sort | combining snns with filtering for efficient neural decoding in implantable brain machine interfaces |
| topic | implantable-brain machine interface intention decoder spiking neural networks low-power |
| url | https://doi.org/10.1088/2634-4386/adba82 |
| work_keys_str_mv | AT zhoubiyan combiningsnnswithfilteringforefficientneuraldecodinginimplantablebrainmachineinterfaces AT paoshengvincentsun combiningsnnswithfilteringforefficientneuraldecodinginimplantablebrainmachineinterfaces AT arindambasu combiningsnnswithfilteringforefficientneuraldecodinginimplantablebrainmachineinterfaces |