S-WD-EEMD: A hybrid framework for imbalanced sEMG signal analysis in diagnosis of human knee abnormality

• DOI: 10.1371/journal.pone.0301263
• Publication Date: 2024-05-31T19:25:36Z
• Authors: Ankit Vijayvargiya; Aparna Sinha; Naveen Gehlot; Ashutosh Jena; Rajesh Kumar; Kieran Moran
• Keywords: Oversampling; SIGNAL (programming language)

The diagnosis of human knee abnormalities using the surface electromyography (sEMG) signal obtained from lower limb muscles with machine learning is a major problem due to noisy nature sEMG and imbalance in data corresponding healthy abnormal subjects. To address this challenge, combination wavelet decomposition (WD) ensemble empirical mode (EEMD) Synthetic Minority Oversampling Technique (S-WD-EEMD) proposed. In study, hybrid WD-EEMD considered for minimization noises produced during collection, while (SMOTE) balance by increasing minority class samples training techniques. findings indicate that SMOTE oversampling technique enhances efficacy examined classifiers when employed on imbalanced data. F-Score Extra Tree Classifier, utilizing processing oversampling, 98.4%, whereas, without technique, it 95.1%.