Muscle Activity Analysis using Higher-Order Tensor Models: Application to Muscle Synergy Identification

TL;DR

This paper explores the use of higher-order tensor decompositions, specifically a new constrained Tucker method, for analyzing muscle activity and identifying muscle synergies from multi-way EMG data, outperforming traditional NMF approaches.

Contribution

The paper introduces a novel constrained Tucker decomposition method for muscle synergy extraction, demonstrating its effectiveness over existing tensor models and NMF in multi-task muscle activity analysis.

Findings

ConsTD effectively extracts shared and task-specific muscle synergies.

Tensor models outperform NMF in robustness to task-repetition disarrangements.

Proposed methods successfully analyze multi-way EMG data for muscle synergy identification.

Abstract

Higher-order tensor decompositions have hardly been used in muscle activity analysis despite multichannel electromyography (EMG) datasets naturally occurring as multi-way structures. Here, we seek to demonstrate and discuss the potential of tensor decompositions as a framework to estimate muscle synergies from $3^{rd}$-order EMG tensors built by stacking repetitions of multi-channel EMG for several tasks. We compare the two most widespread tensor decomposition models -- Parallel Factor Analysis (PARAFAC) and Tucker -- in muscle synergy analysis of the wrist's three main Degree of Freedoms (DoFs) using the public first Ninapro database. Furthermore, we proposed a constrained Tucker decomposition (consTD) method for efficient synergy extraction building on the power of tensor decompositions. This method is proposed as a direct novel approach for shared and task-specific synergy estimation from two biomechanically related tasks. Our approach is compared with the current standard approach of repetitively applying non-negative matrix factorisation (NMF) to a series of movements. The results show that the consTD method is suitable for synergy extraction compared to PARAFAC and Tucker. Moreover, exploiting the multi-way structure of muscle activity, the proposed methods successfully identified shared and task-specific synergies for all three DoFs tensors. These were found to be robust to disarrangement with regard to task-repetition information, unlike the commonly used NMF. In summary, we demonstrate how to use tensors to characterise muscle activity and develop a new consTD method for muscle synergy extraction that could be used for shared and task-specific synergies identification. We expect that this study will pave the way for the development of novel muscle activity analysis methods based on higher-order techniques.