Embedded Classification of Local Field Potentials Recorded from Rat Barrel Cortex with Implanted Multi-Electrode Array
OPEN ACCESS
Loading...
Author / Producer
Date
2018
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
This paper focuses on ultra-low power embedded classification of neural activities. The machine learning (ML) algorithm has been trained using evoked local field potentials (LFPs) recorded with an implanted 16x16 multi-electrode array (MEA) from the rat barrel cortex while stimulating the whisker. Experimental results demonstrate that ML can be successfully applied to noisy single-trial LFPs. We achieved up to 95.8% test accuracy in predicting the whisker deflection. The trained ML model is successfully implemented on a low-power embedded system with an average consumption of 2.6mW.
Permanent link
Publication status
published
External links
Editor
Book title
2018 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Journal / series
Volume
Pages / Article No.
511 - 514
Publisher
IEEE
Event
2018 IEEE Biomedical Circuits and Systems Conference (BioCAS 2018)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Neuroscience; Machine learning; brain-chip interface; Image processing; bio-sensors; implantable devices
Organisational unit
03996 - Benini, Luca / Benini, Luca
Notes
Funding
162524 - MicroLearn: Micropower Deep Learning (SNF)