Task discrimination from myoelectric activity: A learning scheme for EMG-based interfaces

Minas V. Liarokapis, Panagiotis Artemiadis, Kostas J. Kyriakopoulos

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

10 Scopus citations

Abstract

A learning scheme based on Random Forests is used to discriminate the task to be executed using only myoelectric activity from the upper limb. Three different task features can be discriminated: subspace to move towards, object to be grasped and task to be executed (with the object). The discrimination between the different reach to grasp movements is accomplished with a random forests classifier, which is able to perform efficient features selection, helping us to reduce the number of EMG channels required for task discrimination. The proposed scheme can take advantage of both a classifier and a regressor that cooperate advantageously to split the task space, providing better estimation accuracy with task-specific EMG-based motion decoding models, as reported in [1] and [2]. The whole learning scheme can be used by a series of EMG-based interfaces, that can be found in rehabilitation cases and neural prostheses.

Original languageEnglish (US)
Title of host publication2013 IEEE 13th International Conference on Rehabilitation Robotics, ICORR 2013
DOIs
StatePublished - Dec 31 2013
Event2013 IEEE 13th International Conference on Rehabilitation Robotics, ICORR 2013 - Seattle, WA, United States
Duration: Jun 24 2013Jun 26 2013

Publication series

NameIEEE International Conference on Rehabilitation Robotics
ISSN (Print)1945-7898
ISSN (Electronic)1945-7901

Other

Other2013 IEEE 13th International Conference on Rehabilitation Robotics, ICORR 2013
CountryUnited States
CitySeattle, WA
Period6/24/136/26/13

Keywords

  • ElectroMyoGraphy (EMG)
  • Learning Scheme
  • Random Forests
  • Task Specificity

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Rehabilitation
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Task discrimination from myoelectric activity: A learning scheme for EMG-based interfaces'. Together they form a unique fingerprint.

Cite this