| Literature DB >> 34372482 |
Ernest N Kamavuako1,2, Mitchell Brown1, Xinqi Bao1, Ines Chihi3,4, Samuel Pitou1, Matthew Howard1.
Abstract
Commercial myoelectric prostheses are costly to purchase and maintain, making their provision challenging for developing countries. Recent research indicates that embroidered EMG electrodes may provide a more affordable alternative to the sensors used in current prostheses. This pilot study investigates the usability of such electrodes for myoelectric control by comparing online and offline performance against conventional gel electrodes. Offline performance is evaluated through the classification of nine different hand and wrist gestures. Online performance is assessed with a crossover two-degree-of-freedom real-time experiment using Fitts' Law. Two performance metrics (Throughput and Completion Rate) are used to quantify usability. The mean classification accuracy of the nine gestures is approximately 98% for subject-specific models trained on both gel and embroidered electrode offline data from individual subjects, and 97% and 96% for general models trained on gel and embroidered offline data, respectively, from all subjects. Throughput (0.3 bits/s) and completion rate (95-97%) are similar in the online test. Results indicate that embroidered electrodes can achieve similar performance to gel electrodes paving the way for low-cost myoelectric prostheses.Entities:
Keywords: conventional gel electrodes; embroidered EMG electrodes; myoelectric prostheses; online and offline performance; pilot study
Year: 2021 PMID: 34372482 DOI: 10.3390/s21155245
Source DB: PubMed Journal: Sensors (Basel) ISSN: 1424-8220 Impact factor: 3.576