Abstract
Options currently available to individuals with upper limb loss range from prosthetic hands that can perform many movements, but require more cognitive effort to control, to simpler terminal devices with limited functional abilities. We attempted to address this issue by designing a myoelectric control system to modulate prosthetic hand posture and digit force distribution. We recorded surface electromyographic (EMG) signals from five forearm muscles in eight able-bodied subjects while they modulated hand posture and the flexion force distribution of individual fingers. We used a support vector machine (SVM) and a random forest regression (RFR) to map EMG signal features to hand posture and individual digit forces, respectively. After training, subjects performed grasping tasks and hand gestures while a computer program computed and displayed online feedback of all digit forces, in which digits were flexed, and the magnitude of contact forces. We also used a commercially available prosthetic hand, the i-Limb (Touch Bionics), to provide a practical demonstration of the proposed approach's ability to control hand posture and finger forces. Subjects could control hand pose and force distribution across the fingers during online testing. Decoding success rates ranged from 60% (index finger pointing) to 83-99% for 2-digit grasp and resting state, respectively. Subjects could also modulate finger force distribution. This work provides a proof of concept for the application of SVM and RFR for online control of hand posture and finger force distribution, respectively. Our approach has potential applications for enabling in-hand manipulation with a prosthetic hand.
Highlights
A significant challenge faced in modern medicine is in replacing a lost hand for upper limb amputees
A second analysis of variance (ANOVA) was performed on overall hand pose prediction accuracy for the grasping tasks using one within-subject factor (Round; five levels)
The EMG control system design presented here is for demonstrating the use of machine learning techniques to decode five surface EMG signals from the forearm to predict desired hand motion
Summary
A significant challenge faced in modern medicine is in replacing a lost hand for upper limb amputees. Numerous systems have been developed for recording surface EMG signals from the upper limb and extracting features to predict in real-time grasp postures and/or forces, or for individuals with upper limb loss, predicting the user’s intended hand movement. Castellini and Kõiva [9] demonstrated the use of a myoelectric control system that allowed 12 able-bodied subjects to modulate individual finger forces when the hand lay flat on a surface with each finger placed on top of force sensors. Later work by Cipriani et al [10] examined real-time myoelectric control of grasp types by individuals with upper limb loss with nine EMG electrodes placed along either side of the residual forearm muscles. The system’s performance is demonstrated on able-bodied individuals before future testing on individuals with upper limb loss
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 call
