Human-Machine Interaction Using Discrete Myoelectric Control: Contrastive Learning Reduces False Activations During Activities of Daily Living

扫码查看

原文链接

NETL
IEEE

外文摘要：Although myoelectric control has predominantly been used as a continuous input for prosthesis control， there are many applications in robotics， mixed reality， and wearable devices where discrete， event-driven inputs may be preferred。 Furthermore， the traditional closed-set assumption in pros-thetics， where users are assumed to be constantly (and only) controlling the target device， may be undesirable for these emerging applications。 To enable the real-world viability of such EMG-based inputs， myoelectric control research must move toward open-set systems that can reliably recognize and classify target gesture commands and discriminate them from out-of-set inputs。 This work proposes and evaluates an end-to-end LSTM-based architecture that leverages contrastive learning to recognize a set of dynamic gestures while simultaneously rejecting activities of daily living。 Compared to the current standard training approach (which generally uses the cross entropy loss function)， the proposed contrastive approach significantly reduces the number of false positives (p<0。0005) during a set of activities of daily living (including walking， writing， typing， driving， and phone use) while maintaining high accuracy (95%) on the closed-set target gestures。 These results highlight a promising path for developing discrete myoelectric control as an always-available human-machine interface。

外文关键词：

TrainingLegged locomotionTarget recognitionMixed realityContrastive learningWritingReliabilityWearable devicesRobotsStandards

作者：

Ethan Eddy、Evan Campbell、Scott Bateman、Erik Scheme

展开 >

作者单位：

Department of Electrical Engineering, Institute of Biomedical Engineering, University of New Brunswick, Fredericton, Canada

HCI and SPECTRAL Lab, University of New Brunswick, Fredericton, Canada

会议名称：

IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics

会议地点：

Heidelberg(DE)

会议母体文献：

2024 10th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics

页码：

128-133

出版时间：

2024

DOI：

10.1109/BioRob60516.2024.10719934