Inter-Subject Variance Transfer Learning for EMG Pattern Classification Based on Bayesian Inference

TL;DR

This paper introduces a Bayesian transfer learning method for EMG pattern classification that leverages inter-subject variance similarities to improve accuracy with limited target data.

Contribution

It proposes a novel variance transfer approach based on Bayesian inference, enabling effective inter-subject transfer learning in EMG classification.

Findings

Outperforms existing transfer learning methods in EMG classification.

Effectively reduces calibration data needed for new subjects.

Demonstrates robustness across two EMG datasets.

Abstract

In electromyogram (EMG)-based motion recognition, a subject-specific classifier is typically trained with sufficient labeled data. However, this process demands extensive data collection over extended periods, burdening the subject. To address this, utilizing information from pre-training on multiple subjects for the training of the target subject could be beneficial. This paper proposes an inter-subject variance transfer learning method based on a Bayesian approach. This method is founded on the simple hypothesis that while the means of EMG features vary greatly across subjects, their variances may exhibit similar patterns. Our approach transfers variance information, acquired through pre-training on multiple source subjects, to a target subject within a Bayesian updating framework, thereby allowing accurate classification using limited target calibration data. A coefficient was also introduced to adjust the amount of information transferred for efficient transfer learning. Experimental evaluations using two EMG datasets demonstrated the effectiveness of our variance transfer strategy and its superiority compared to existing methods.