Loading [MathJax]/extensions/TeX/color_ieee.js
Locomotion Modes Recognition Driven by Time-Variant Muscle Synergy Feature | IEEE Journals & Magazine | IEEE Xplore

Locomotion Modes Recognition Driven by Time-Variant Muscle Synergy Feature

; ; ; ; ;

Abstract:

Muscle synergy (MS) has been proven to be a simple and intuitive EMG feature for myoelectric interface to simplify human-machine interaction in the upper limb. However, s...Show More

Abstract:

Muscle synergy (MS) has been proven to be a simple and intuitive EMG feature for myoelectric interface to simplify human-machine interaction in the upper limb. However, suffering from poor discriminability results from similar features between locomotion modes, spatial MS has not been widely applied in a myoelectric interface for lower limb assistance. Recent studies suggested providing a synergy-based neural controller with extra time-variant information to improve their dynamic performance, but it remains to be clarified that synergetic patterns in either invariant spatial or variant time domains are superior for locomotion mode recognition. Instead of traditional locomotion mode recognition with spatial MS, we extracted the synergetic pattern in both spatial and temporal domains via a nonnegative matrix factorization (NMF) algorithm, and their performance together with similarities between locomotion modes, that is, evaluated by recognizing five locomotion modes using four common machine learning algorithms. The results showed that the performance of time-variant MS patterns on machine learning classifiers was significantly better than that of spatial time-invariant features. All the used classification models based on time-variant features achieved better results, with a classification accuracy of 93% for the machine learning method and 97% for the deep learning method, which supported the view of taking time-variant MS pattern into consideration for lower limb myoelectric interface. The proposed method improves the classifier performance of commonly used synergy-based locomotion modes recognition and provides a new research idea that encourages future human-machine interface (HMI) systems or instruments to develop more dynamic-sensitive measurement setups for the synergy-based myoelectric interface.
Article Sequence Number: 2503609
Date of Publication: 09 January 2025

ISSN Information:

Funding Agency:


References

References is not available for this document.