Skip to main navigation Skip to search Skip to main content

Cortical motor intention decoding on an analog co-processor with fast training for non-stationary data

  • Shoeb Shaikh
  • , Chen Yi
  • , Arindam Basu*
  • , Rosa So
  • *Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

This paper presents a low power hardware implementation of a motor intention decoder used in intra-cortical Brain Machine Interfaces. It offers two specific advantages over current state of the art decoders. Firstly, the decoding is done on an analog co-processor instead of a personal computer thereby reducing both the power consumption and size of the overall system. Secondly, the co-processor employs a randomized neural network - extreme learning machine (ELM), which is as quick to train as the linear decoders while being adept at capturing the complex non-linear mappings between the neural activity and the intended movements. Results show an average 10% improvement in decoding accuracy over linear discriminant analysis in non-stationary datasets.
Original languageEnglish
Title of host publication2017 IEEE Biomedical Circuits and Systems Conference, BioCAS 2017 - Proceedings
PublisherIEEE
Pages1-4
Volume2018-January
ISBN (Print)9781509058037
DOIs
Publication statusPublished - 23 Mar 2018
Externally publishedYes
Event2017 IEEE Biomedical Circuits and Systems Conference, BioCAS 2017 - Torino, Italy
Duration: 19 Oct 201721 Oct 2017

Publication series

Name2017 IEEE Biomedical Circuits and Systems Conference, BioCAS 2017 - Proceedings
Volume2018-January

Conference

Conference2017 IEEE Biomedical Circuits and Systems Conference, BioCAS 2017
PlaceItaly
CityTorino
Period19/10/1721/10/17

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

  • Brain-machine interfaces
  • low power hardware
  • machine learning
  • motor intention decoding
  • neural network

Fingerprint

Dive into the research topics of 'Cortical motor intention decoding on an analog co-processor with fast training for non-stationary data'. Together they form a unique fingerprint.

Cite this