User Training for Pattern Recognition-Based Myoelectric Prostheses: Improving Phantom Limb Movement Consistency and Distinguishability

Abstract

We assessed the ability of four transradial amputees to control a virtual prosthesis capable of nine classes of movement both before and after a two-week training period. Subjects attended eight one-on-one training sessions that focused on improving the consistency and distinguishability of their hand and wrist movements using visual biofeedback from a virtual prosthesis. The virtual environment facilitated the precise quantification of three prosthesis control measures. During a final evaluation, the subject population saw an average increase in movement completion percentage from 70.8% to 99.0%, an average improvement in normalized movement completion time from 1.47 to 1.13, and an average increase in movement classifier accuracy from 77.5% to 94.4% (p<0.001). Additionally, all four subjects were reevaluated after eight elapsed hours without retraining the classifier, and all subjects demonstrated minimal decreases in performance. Our analysis of the underlying sources of improvement for each subject examined the sizes and separation of high-dimensional data clusters and revealed that each subject formed a unique and effective strategy for improving the consistency and/or distinguishability of his or her phantom limb movements. This is the first longitudinal study designed to examine the effects of user training in the implementation of pattern recognition-based myoelectric prostheses.

Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control

“…The conventional approach to myographic control leverages user-learning and machine-learning by interleaving phases of open-loop calibration and real-time user adaptation [24]. This can be relatively slow as the machine learns only once in each iteration, and the user does not receive feedback on improvements of the model until the next evaluation period.…”

“…Powell et al [24] demonstrated the great importance of usertraining for classification-based myoelectric control. They used a strategy based on alternating open-loop calibration of the classifier and real-time evaluation using a virtual prosthesis.…”

Continuous Estimation of Human Multi-Joint Angles From sEMG Using a State-Space Model

“…In this study, we attempt to estimate the four angles of {θ 1 , θ 2 , θ 3 , θ 4 } from sEMG signals, and the angles measured by the Vicon system will be used as a reference to verify the estimations.…”

“…SEMG OF S1, COMPUTED BY (4) In this study, the segmentation threshold η thre was manually set to 0.61. Then, the eight-channel muscle activities extracted from sEMG signals can be segmented into two parts, i.e., the irredundant subvector u (1) k and the redundant subvector u …”

A virtual myoelectric prosthesis training system capable of providing instructions on hand operations

“…8 To support this stage, a variety of computer-based systems and evaluation for control ability have been proposed. [9][10][11][12][13] However, even amputees who achieve voluntary control of EMG signals may struggle to perform tasks as desired because EMG signals are affected by the weight of the prosthesis and arm posture. Task training with the myoelectric prosthesis is therefore necessary before the unit can be prescribed.…”