Research on Predicting Joint Rotation Angles Through Mechanomyography Signals and the Broad Learning System
Year: 2025
Type: article
Abstract: This study presents a methodology for the extraction of Mechanomyography (MMG) signals and their subsequent application in estimating the rotational angles of the shoulder and elbow joints. To mitigate modal aliasing artifacts during the extraction of MMG signals, an enhanced version of the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (denoted as ICEEMDAN) has been introduced. Comparative analysis of ICEEMDAN and six decomposition algorithms revealed that ICEEMDAN yielded the lowest envelope entropy at 8.033. Consequently, the ICEEMDAN algorithm effectively isolated MMG signals from the raw acceleration signals, achieving an optimal balance between maximizing artifact rejection and minimizing signal distortion. To mitigate the economic burden associated with the training of estimation models, the Broad Learning System (BLS) has been introduced. This system facilitates iterative training through the incremental addition of nodes to both the feature layer and the enhancement layer, thereby enhancing the efficiency of the training process. The estimation precision of the BLS model was enhanced through the optimization of its parameters via the application of the Slime Mould Algorithm (SMA). This investigation revealed that the typical center frequency for MMG ranged between 10 and 100 Hz. Moreover, the estimation model founded on the SMA-BLS technique exhibited a minimum coefficient of determination (R2) value of 0.971. This model effectively estimated the rotational angles of the shoulder joints.
Source: Applied Sciences
DOI: 10.3390/app15126454
Institution: Nanjing University of Science and Technology
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,896
Funder: Government of Jiangsu Province
OpenAlex ID: W4411153333