Classification of Surface Electromyography Recordings from Young and Older Adults Using CWT Scalograms: A Window-Level Proof-of-Concept Study

Background/Objectives: Age-related changes in skeletal muscle involve alterations in both muscle structure and neuromuscular function. Surface electromyography (sEMG) provides a non-invasive method for assessing muscle electrical activity. This study aimed to investigate whether time–frequency representations of sEMG signals combined with deep learning could classify recordings obtained from healthy young and older adults, without assuming that the discriminative features necessarily reflect age-related neuromuscular changes. Methods: sEMG signals were experimentally collected from 60 healthy adults, including 30 young and 30 older adults. The resulting continuous wavelet transform (CWT) scalogram images were randomly divided into training and test sets at the image-window level using an 80:20 ratio. Consequently, windows from the same participant could appear in both sets. Signals were filtered, segmented into overlapping windows, and converted into CWT scalogram images for classification using ResNet-18. Results: At the window level, the CWT-ResNet model achieved an accuracy of 78.98%, an area under the receiver operating characteristic curve (AUC) of 0.8589, a sensitivity of 71.34%, a specificity of 85.06%, and a balanced accuracy of 78.20%. Muscle-specific analyses showed window-level classification accuracies ranging from 78.57% to 79.89% across all three muscle sites. However, the observed classification performance may have been influenced by differences in movement timing, active and resting periods, anthropometric characteristics, and participant overlap between the training and test sets. These potential influences were not isolated through additional control analyses. Conclusions: CWT-based time–frequency representations of sEMG combined with ResNet-18 demonstrated preliminary feasibility for classifying sEMG recordings obtained from young and older adults under the revised preprocessing and image-window-level evaluation conditions. The findings do not establish that the model specifically detects age-related neuromuscular changes. Participant-independent validation and analyses controlling for task execution and anthropometric characteristics are required.