Rakeness-based Compressed Sensing of Surface ElectroMyoGraphy for Improved Hand Movement Recognition in the Compressed Domain

Alex Marchioni, Mauro Mangia, Fabio Pareschil, Riccardo Rovatti, Gianluca Setti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Surface electromyography (sEMG) waveforms are widely used to generate control signals in several application areas, ranging from prosthetic to consumer electronics. Classically, such waveforms are acquired at Nyquist rate and digitally transmitted trough a wireless channel to a decision/actuation node. This causes large energy consumption and is incompatible with the implementation of ultra-low power acquisition nodes. We already proposed Compressed Sensing (CS) as a low-complexity method to achieve substantial energy saving by reducing the size of data to be transmitted while preserving the information content. We here make a significant leap forward by showing that hand movements recognition task can be performed directly in the compressed domain with a success rate greater than 98 % and with a reduction of the number of transmitted bits by two order of magnitude with respect to row data.
Original languageEnglish (US)
Title of host publication2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781538636039
DOIs
StatePublished - Dec 20 2018
Externally publishedYes

Fingerprint

Dive into the research topics of 'Rakeness-based Compressed Sensing of Surface ElectroMyoGraphy for Improved Hand Movement Recognition in the Compressed Domain'. Together they form a unique fingerprint.

Cite this