Designing Game-Based Myoelectric Prosthesis Training

Abstract

A myoelectric prosthesis (myo) is a dexterous artificial limb controlled by muscle contractions. Learning to use a myo can be challenging, so extensive training is often required to use a myo prosthesis effectively. Signal visualizations and simple muscle-controlled games are currently used to help patients train their muscles, but are boring and frustrating. Furthermore, current training systems require expensive medical equipment and clinician oversight, restricting training to infrequent clinical visits. To address these limitations, we developed a new game that promotes fun and success, and shows the viability of a low-cost myoelectric input device. We adapted a user-centered design (UCD) process to receive feedback from patients, clinicians, and family members as we iteratively addressed challenges to improve our game. Through this work, we introduce a free and open myo training game, provide new information about the design of myo training games, and reflect on an adapted UCD process for the practical iterative development of therapeutic games.

Feature Extraction and Selection for Myoelectric Control Based on Wearable EMG Sensors

“…These EMG armbands have unlocked new possibilities for myoelectric control applications, which are not limited to the more traditional prosthetics market. Applications have included accessible game-based training for myoelectric prostheses [ 5 , 6 ], sport training systems [ 7 ], portable music player interfaces [ 3 ], sign language interpretation [ 8 ], and user authentication [ 9 ].…”

Mobile, Game-Based Training for Myoelectric Prosthesis Control

“…Previous research has indicated that amputees treated within a month of amputation by prosthetists and occupational therapists have a much higher rehabilitation success and return to work rate than those seen later (Bowker, 2004 ). Currently, prosthetists and occupational therapists lack tools that can be sent home with patients to allow for training between visits (Tabor et al, 2017 ). Given fiscal and geographic constraints, an additional 20 min of training per day, as observed in the current study, has the potential to improve rehabilitation success rates by providing myosite training outside of the clinical environment.…”

“…Given fiscal and geographic constraints, an additional 20 min of training per day, as observed in the current study, has the potential to improve rehabilitation success rates by providing myosite training outside of the clinical environment. In both amputee and able-bodied samples described previously, the major issues with current approaches to myosite training were identified as: boring and unengaging training (Tabor et al, 2017 ); training not accessible outside the clinic (Tabor et al, 2017 ); and training does not provide patient performance metrics to a provider when used remotely by a patient (Dawson et al, 2012 ). The current system addresses each of these concerns by presenting engaging, mobile training to amputees and is associated with a cloud and web-based approach to data communication for providers.…”

Hilbert sEMG data scanning for hand gesture recognition based on deep learning

“…A common limitation presented is the lack of classification robustness. To address this, recent studies provide evidence for significant performance improvement (with respect to classification accuracy and latency) achieved with DL approaches [6,41,47].…”