Design of continuous EMG classification approaches towards the control of a robotic exoskeleton in reaching movements

Nerea Irastorza-Landa*, Andrea Sarasola-Sanz, Eduardo López-Larraz, Carlos Bibián, Parid Shiman, Niels Birbaumer, Ander Ramos-Murguialday

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

Myoelectric control of rehabilitation devices engages active recruitment of muscles for motor task accomplishment, which has been proven to be essential in motor rehabilitation. Unfortunately, most electromyographic (EMG) activity-based controls are limited to one single degree-of-freedom (DoF), not permitting multi-joint functional tasks. On the other hand, discrete EMG-triggered approaches fail to provide continuous feedback about muscle recruitment during movement. For such purposes, myoelectric interfaces for continuous recognition of functional movements are necessary. Here we recorded EMG activity using 5 bipolar electrodes placed on the upper-arm in 8 healthy participants while they performed reaching movements in 8 different directions. A pseudo on-line system was developed to continuously predict movement intention and attempted arm direction. We evaluated two hierarchical classification approaches. Movement intention detection triggered different movement direction classifiers (4 or 8 classes) that were trained and tested over a 5-fold cross validation. We also investigated the effect of 3 different window lengths to extract EMG features on classification. We obtained classification accuracies above 70% for both hierarchical approaches. These results highlight the viability of classifying online 8 upper-arm different directions using surface EMG activity of 5 muscles and represent a first step towards an online EMG-based control for rehabilitation devices.

Original languageEnglish
Title of host publication2017 International Conference on Rehabilitation Robotics, ICORR 2017
EditorsArash Ajoudani, Panagiotis Artemiadis, Philipp Beckerle, Giorgio Grioli, Olivier Lambercy, Katja Mombaur, Domen Novak, Georg Rauter, Carlos Rodriguez Guerrero, Gionata Salvietti, Farshid Amirabdollahian, Sivakumar Balasubramanian, Claudio Castellini, Giovanni Di Pino, Zhao Guo, Charmayne Hughes, Fumiya Iida, Tommaso Lenzi, Emanuele Ruffaldi, Fabrizio Sergi, Gim Song Soh, Marco Caimmi, Leonardo Cappello, Raffaella Carloni, Tom Carlson, Maura Casadio, Martina Coscia, Dalia De Santis, Arturo Forner-Cordero, Matthew Howard, Davide Piovesan, Adriano Siqueira, Frank Sup, Masia Lorenzo, Manuel Giuseppe Catalano, Hyunglae Lee, Carlo Menon, Stanisa Raspopovic, Mo Rastgaar, Renaud Ronsse, Edwin van Asseldonk, Bram Vanderborght, Madhusudhan Venkadesan, Matteo Bianchi, David Braun, Sasha Blue Godfrey, Fulvio Mastrogiovanni, Andrew McDaid, Stefano Rossi, Jacopo Zenzeri, Domenico Formica, Nikolaos Karavas, Laura Marchal-Crespo, Kyle B. Reed, Nevio Luigi Tagliamonte, Etienne Burdet, Angelo Basteris, Domenico Campolo, Ashish Deshpande, Venketesh Dubey, Asif Hussain, Vittorio Sanguineti, Ramazan Unal, Glauco Augusto de Paula Caurin, Yasuharu Koike, Stefano Mazzoleni, Hyung-Soon Park, C. David Remy, Ludovic Saint-Bauzel, Nikos Tsagarakis, Jan Veneman, Wenlong Zhang
PublisherIEEE Computer Society
Pages128-133
Number of pages6
ISBN (Electronic)9781538622964
DOIs
Publication statusPublished - 11 Aug 2017
Event2017 International Conference on Rehabilitation Robotics, ICORR 2017 - London, United Kingdom
Duration: 17 Jul 201720 Jul 2017

Publication series

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

Conference

Conference2017 International Conference on Rehabilitation Robotics, ICORR 2017
Country/TerritoryUnited Kingdom
CityLondon
Period17/07/1720/07/17

Fingerprint

Dive into the research topics of 'Design of continuous EMG classification approaches towards the control of a robotic exoskeleton in reaching movements'. Together they form a unique fingerprint.

Cite this