Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control

Abstract

Post-processing techniques have been shown to improve the quality of the decision stream generated by classifiers used in pattern-recognition-based myoelectric control. However, these techniques have largely been tested individually and on well-behaved, stationary data, failing to fully evaluate their trade-offs between smoothing and latency during dynamic use. Correspondingly, in this work, we survey and compare 8 different post-processing and decision stream improvement schemes in the context of continuous and dynamic class transitions: majority vote, Bayesian fusion, onset locking, outlier detection, confidence-based rejection, confidence scaling, prior adjustment, and adaptive windowing. We then propose two new temporally aware post-processing schemes that use changes in the decision and confidence streams to better reject uncertain decisions. Our decision-change informed rejection (DCIR) approach outperforms existing schemes during both steady-state and transitions based on error rates and decision stream volatility whether using a LDA or SVM classifier, or a deep LSTM model. These results suggest that added robustness can be gained by appropriately leveraging temporal context in myoelectric control.

Context-informed incremental learning improves both the performance and resilience of myoelectric control

“…Despite its history of success within HCI, the concept of context has only recently begun to surface in prosthetics. For example, some have used decision stream context like majority voting [35] and rejection [36] to improve control. Similarly, Sensinger et al proposed a form of decision stream context during unsupervised adaptation by not adapting to changes in contractions that were not physically possible (i.e., they happened too quickly) [11].…”