A novel unsupervised dynamic feature domain adaptation strategy for cross-individual myoelectric gesture recognition

Abstract

Objective.
Surface electromyography pattern recognition (sEMG-PR) is considered as a promising control method for human-machine interaction systems. However, the performance of a trained classifier would greatly degrade for novel users since sEMG signals are user-dependent and largely affected by a number of individual factors such as the quantity of subcutaneous fat and the skin impedance. Approach. To solve this issue, we proposed a novel unsupervised cross-individual motion recognition method that aligned sEMG features from different individuals by self-adaptive dimensional dynamic distribution adaptation (SD-DDA) in this study. In the method, both the distances of marginal and conditional distributions between source and target features were minimized through automatically selecting the optimal feature domain dimension by using a small amount of unlabelled target data.
Main results.
The effectiveness of the proposed method was tested on four different feature sets, and results showed that the average classification accuracy was improved by above 10% on our collected dataset with the best accuracy reached 90.4%. Compared to six kinds of classic transfer learning methods, the proposed method showed an outstanding performance with improvements of 3.2%-13.8%. Additionally, the proposed method achieved an approximate 9% improvement on a publicly available dataset. Significance. These results suggested that the proposed SD-DDA method is feasible for cross-individual motion intention recognition, which would provide help for the application of sEMG-PR based system.

Robust myoelectric pattern recognition methods for reducing users’ calibration burden: challenges and future

“…Xue et al ( Xue et al, 2021 ) extracted inherent user-independent properties using canonical correlation analysis (CCA) and subsequently minimized inter-user distributional differences through the optimal transport (OT) framework. Moreover, many other robust MPR works are based on similar feature alignment strategies ( Zhang et al, 2022 ; Wang et al, 2023a ; Liu et al, 2023 ). Feature alignment involves computing the distance between the distributions of the source and target domains and subsequently minimizing this loss to achieve alignment between data domains.…”

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition

“…Enabling subtle and intuitive gesture-based inputs using the electromyogram (EMG) signals generated when muscles are contracted (i.e. myoelectric control) is emerging as an increasingly important input modality because it enables always-available input that can be readily incorporated into wearable and ubiquitous computing technologies [1][2][3][4]. However, if myoelectric control interfaces (MCIs) are to eventually be widely adopted, these control gestures must be recognized reliably across a range of real-world environments and conditions.…”

“…With the increasing interest in MCIs, which will require a paradigm shift from continuous to discrete myoelectric control, identifying, evaluating, and alleviating confounding factors will become an increasing research focus. Toward the goal of creating robust and reliable discrete control-based MCIs, this work explores the effect of three important confounding factors-(1) limb position variations, (2) cross-day use, and (3) gesture elicitation speed-on classification accuracy across four discrete myoelectric control architectures. In doing so, this work creates a foundation and highlights future research directions for ensuring the success of MCIs as a widely applicable ubiquitous input.…”