Author:
Karrenbach Maxim,Preechayasomboon Pornthep,Sauer Peter,Boe David,Rombokas Eric
Abstract
We anticipate wide adoption of wrist and forearm electomyographic (EMG) interface devices worn daily by the same user. This presents unique challenges that are not yet well addressed in the EMG literature, such as adapting for session-specific differences while learning a longer-term model of the specific user. In this manuscript we present two contributions toward this goal. First, we present the MiSDIREKt (Multi-Session Dynamic Interaction Recordings of EMG and Kinematics) dataset acquired using a novel hardware design. A single participant performed four kinds of hand interaction tasks in virtual reality for 43 distinct sessions over 12 days, totaling 814 min. Second, we analyze this data using a non-linear encoder-decoder for dimensionality reduction in gesture classification. We find that an architecture which recalibrates with a small amount of single session data performs at an accuracy of 79.5% on that session, as opposed to architectures which learn solely from the single session (49.6%) or learn only from the training data (55.2%).
Funder
National Science Foundation
Subject
Biomedical Engineering,Histology,Bioengineering,Biotechnology
Reference50 articles.
1. Advancing muscle-computer interfaces with high-density electromyography;Amma,2015
2. Deep learning with convolutional neural networks applied to electromyography data: A resource for the classification of movements for prosthetic hands;Atzori;Front. Neurorobot.,2016
3. Electromyography data for non-invasive naturally-controlled robotic hand prostheses;Atzori;Sci. Data,2014
4. Electromyography (emg) data-driven load classification using empirical mode decomposition and feature analysis;Aziz,2019
5. Dimensionality reduction of human gait for prosthetic control;Boe;Front. Bioeng. Biotechnol.,2021
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献