Citation

BibTex format

@inproceedings{Ahmadi:2019:10.1109/NER.2019.8717045,
author = {Ahmadi, N and Constandinou, TG and Bouganis, C-S},
doi = {10.1109/NER.2019.8717045},
pages = {415--419},
publisher = {IEEE},
title = {Decoding Hand Kinematics from Local Field Potentials Using Long Short-Term Memory (LSTM) Network},
url = {http://dx.doi.org/10.1109/NER.2019.8717045},
year = {2019}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Local field potential (LFP) has gained increasing interest as an alternativeinput signal for brain-machine interfaces (BMIs) due to its informativefeatures, long-term stability, and low frequency content. However, despitethese interesting properties, LFP-based BMIs have been reported to yield lowdecoding performances compared to spike-based BMIs. In this paper, we propose anew decoder based on long short-term memory (LSTM) network which aims toimprove the decoding performance of LFP-based BMIs. We compare offline decodingperformance of the proposed LSTM decoder to a commonly used Kalman filter (KF)decoder on hand kinematics prediction tasks from multichannel LFPs. We alsobenchmark the performance of LFP-driven LSTM decoder against KF decoder drivenby two types of spike signals: single-unit activity (SUA) and multi-unitactivity (MUA). Our results show that LFP-driven LSTM decoder achievessignificantly better decoding performance than LFP-, SUA-, and MUA-driven KFdecoders. This suggests that LFPs coupled with LSTM decoder could provide highdecoding performance, robust, and low power BMIs.
AU - Ahmadi,N
AU - Constandinou,TG
AU - Bouganis,C-S
DO - 10.1109/NER.2019.8717045
EP - 419
PB - IEEE
PY - 2019///
SP - 415
TI - Decoding Hand Kinematics from Local Field Potentials Using Long Short-Term Memory (LSTM) Network
UR - http://dx.doi.org/10.1109/NER.2019.8717045
UR - http://arxiv.org/abs/1901.00708v1
UR - http://hdl.handle.net/10044/1/67356
ER -

Contact us

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