Abstract
Understanding how upper-limb prostheses are used in daily life helps to improve the design and robustness of prosthesis control algorithms and prosthetic components. However, only a very small fraction of published research includes prosthesis use in community settings. The cost, limited battery life, and poor generalisation may be the main reasons limiting the implementation of home-based applications. In this work, we introduce the design of a cost-effective Arduino-based myoelectric control system with wearable electromyogram (EMG) sensors. The design considerations focused on home studies, so the robustness, user-friendly control adjustments, and user supports were the main concerns. Three control algorithms, namely, direct control, abstract control, and linear discriminant analysis (LDA) classification, were implemented in the system. In this paper, we will share our design principles and report the robustness of the system in continuous operation in the laboratory. In addition, we will show a first real-time implementation of the abstract decoder for prosthesis control with an able-bodied participant.
Highlights
Myoelectric prostheses have the potential to restore the functionality of missing limbs.First developed in 1948 [1], myoelectric prostheses are widely used by amputees in their daily lives
Expansion of the training dataset helps to increase the robustness of the control, but training data in community settings are limited, and the data collected in laboratory settings can be different from user behaviour in daily life
We describe the development of a cost-effective myoelectric control system for achieving multiple hand tasks with selectable control algorithms
Summary
Myoelectric prostheses have the potential to restore the functionality of missing limbs.First developed in 1948 [1], myoelectric prostheses are widely used by amputees in their daily lives. One main reason for the status quo is that, in community settings, advanced prosthetic control algorithms do not perform as well as they do in the laboratory [5]. Factors such as electrode displacement [6,7], changes in limb positions [8,9], extra load on the limb [10], time between adaptation and application [11], and user learning [12,13] can degrade the performance of the prosthesis. The recalibration procedures for advanced algorithms are more complicated than the conventional control methods, and it will be challenging, if not impossible, to retune these algorithms in home trials without the support of specialists [14,15]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
