Decision-change Informed Rejection Improves Robustness in Pattern Recognition-based Myoelectric Control

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 conventional or deep classifiers. These results suggest that added robustness can be gained by appropriately leveraging temporal context in myoelectric control.

Analyzing the Impact of Class Transitions on the Design of Pattern Recognition-based Myoelectric Control Schemes

Despite continued efforts to improve classification accuracy, it has been reported that offline accuracy is a poor indicator of the usability of pattern recognition-based myoelectric control. One potential source of this disparity is the existence of transitions between contraction classes that happen during regular use and are reported to be problematic for pattern recognition systems. Nevertheless, these transitions are often ignored or undefined during both the training and testing processes. In this work, we propose a set of metrics for analyzing the transitions that occur during the voluntary changes between contraction classes during continuous control. These metrics quantify the common types of errors that occur during transitions and compare them to existing metrics that apply only to the steady-state portions of the data. We then use these metrics to analyze transition characteristics of 6 commonly used classifiers on a novel dataset that includes continuous transitions between all combinations of seven different contraction classes. Results show that a linear discriminant classifier consistently outperforms other conventional classifiers during both transitions and steady-state conditions, despite having an almost identical offline performance. Results also show that, although offline training metrics correlate with steady-state performance, they do not correlate with transition performance. These insights suggest that the proposed set of metrics could provide a shift in perspective on the way pattern recognition systems are evaluated and provide a more representative picture of a classifier's performance, potentially narrowing the gap between offline performance and online usability.

Self-Supervised Learning via VICReg Enables Training of EMG Pattern Recognition Using Continuous Data with Unclear Labels

In this study, we investigate the application of self-supervised learning via pre-trained Long Short-Term Memory (LSTM) networks for training surface electromyography pattern recognition models (sEMG-PR) using dynamic data with transitions. While labeling such data poses challenges due to the absence of ground-truth labels during transitions between classes, self-supervised pre-training offers a way to circumvent this issue. We compare the performance of LSTMs trained with either fully-supervised or self-supervised loss to a conventional non-temporal model (LDA) on two data types: segmented ramp data (lacking transition information) and continuous dynamic data inclusive of class transitions. Statistical analysis reveals that the temporal models outperform non-temporal models when trained with continuous dynamic data. Additionally, the proposed VICReg pre-trained temporal model with continuous dynamic data significantly outperformed all other models. Interestingly, when using only ramp data, the LSTM performed worse than the LDA, suggesting potential overfitting due to the absence of sufficient dynamics. This highlights the interplay between data type and model choice. Overall, this work highlights the importance of representative dynamics in training data and the potential for leveraging self-supervised approaches to enhance sEMG-PR models.

Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning

Current electromyography (EMG) pattern recognition (PR) models have been shown to generalize poorly in unconstrained environments, setting back their adoption in applications such as hand gesture control. This problem is often due to limited training data, exacerbated by the use of supervised classification frameworks that are known to be suboptimal in such settings. In this work, we propose a shift to deep metric-based meta-learning in EMG PR to supervise the creation of meaningful and interpretable representations. We use a Siamese Deep Convolutional Neural Network (SDCNN) and contrastive triplet loss to learn an EMG feature embedding space that captures the distribution of the different classes. A nearest-centroid approach is subsequently employed for inference, relying on how closely a test sample aligns with the established data distributions. We derive a robust class proximity-based confidence estimator that leads to a better rejection of incorrect decisions, i.e. false positives, especially when operating beyond the training data domain. We show our approach's efficacy by testing the trained SDCNN's predictions and confidence estimations on unseen data, both in and out of the training domain. The evaluation metrics include the accuracy-rejection curve and the Kullback-Leibler divergence between the confidence distributions of accurate and inaccurate predictions. Outperforming comparable models on both metrics, our results demonstrate that the proposed meta-learning approach improves the classifier's precision in active decisions (after rejection), thus leading to better generalization and applicability.