ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Human-computer interaction with an armband by electromyography

Cornet, Erwin
(2023)

Files

Cornet_65461600_2023.pdf
  • UCLouvain restricted access
  • Adobe PDF
  • 58.62 MB
Cornet_65461600_2023_appendix.zip
  • UCLouvain restricted access
  • Unknown
  • 282.44 MB

Details

Supervisors
Vanderdonckt, Jean
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] en sciences informatiques, à finalité spécialisée
Abstract
Thalmic Lab’s Myo Armband is a wearable device that arrived on the market several years ago. It embeds both hardware and software to transmit data that is continuously generated by sensors to a computer linked to it in order to recognize a predefined set of gestures performed by the user. The device has been studied several times in the past, in various contexts and with different techniques. However, the product was recently discontinued, and the support and documentation gone with it. The objective of this thesis is to recreate the pipeline, from the extraction of data to the insertion of processed samples into a custom framework designed for gesture recognition, emphasizing on modularity and reusability. This task requires to explore the possibility of re-engineering the entire pipeline from scratch, or with what is reminiscent of the past, for the benefit of anyone who would be in the same circumstances. It is also an opportunity to extend the set of gestures and evaluate the behaviour of the system with custom parameters. In this work, we will talk low-level programming of communication protocols, data gathering, GUI, processing of data, properties of sensors, and more.