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...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhou Biyan, Pao-Sheng Vincent Sun, Arindam Basu
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