In this section
@article{Ahmadi:2021:1741-2552/abde8a,
author = {Ahmadi, N and Constandinou, TG and Bouganis, C-S},
doi = {1741-2552/abde8a},
journal = {Journal of Neural Engineering},
pages = {1--23},
title = {Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning},
url = {http://dx.doi.org/10.1088/1741-2552/abde8a},
volume = {18},
year = {2021}
}
TY - JOUR
AB - Objective. Brain–machine interfaces (BMIs) seek to restore lost motor functions in individuals with neurological disorders by enabling them to control external devices directly with their thoughts. This work aims to improve robustness and decoding accuracy that currently become major challenges in the clinical translation of intracortical BMIs. Approach. We propose entire spiking activity (ESA)—an envelope of spiking activity that can be extracted by a simple, threshold-less, and automated technique—as the input signal. We couple ESA with deep learning-based decoding algorithm that uses quasi-recurrent neural network (QRNN) architecture. We evaluate comprehensively the performance of ESA-driven QRNN decoder for decoding hand kinematics from neural signals chronically recorded from the primary motor cortex area of three non-human primates performing different tasks. Main results. Our proposed method yields consistently higher decoding performance than any other combinations of the input signal and decoding algorithm previously reported across long-term recording sessions. It can sustain high decoding performance even when removing spikes from the raw signals, when using the different number of channels, and when using a smaller amount of training data. Significance. Overall results demonstrate exceptionally high decoding accuracy and chronic robustness, which is highly desirable given it is an unresolved challenge in BMIs.
AU - Ahmadi,N
AU - Constandinou,TG
AU - Bouganis,C-S
DO - 1741-2552/abde8a
EP - 23
PY - 2021///
SN - 1741-2552
SP - 1
TI - Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning
T2 - Journal of Neural Engineering
UR - http://dx.doi.org/10.1088/1741-2552/abde8a
UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000624502400001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR - https://iopscience.iop.org/article/10.1088/1741-2552/abde8a
UR - http://hdl.handle.net/10044/1/87386
VL - 18
ER -
Centre for Bio-Inspired Technology
Imperial College London
Bessemer Building
South Kensington
SW7 2AZ, UK
Tel: +44 (0)207 594 0701
Fax: +44 (0)207 594 0704
E-mail: bioinspired@imperial.ac.uk