LiteMamba-EMG: A Lightweight Mamba-based Framework for Robust sEMG-based Swallowing Activity Classification in Dysphagia Patients
-
Abstract
Accurate swallowing assessment via surface electromyography (sEMG) is hindered by limited channel interaction modeling, uniform temporal processing of event-driven signals, and scarce labeled clinical data. We propose SwallowMamba, a hybrid framework that integrates multi-scale convolutional feature extraction with a multi-channel cooperative scanning state space model (MCCS-SSM). MCCS-SSM assigns channel-specific state space parameters and employs a time-varying dynamic cooperation matrix via scaled dot-product attention to model inter-muscle coordination at each time step. An event-aware adaptive step-size (EAAS) mechanism modulates temporal resolution by integrating short-time energy, spectral flux, and instantaneous amplitude variation, allocating finer discretization to swallowing events and coarser steps to rest. To address labeled data scarcity, a hierarchical VICReg (H-VICReg) self-supervised pretraining strategy leverages the large-scale NinaPro hand sEMG dataset for cross-anatomical transfer with multi-layer regularization. Evaluated on a five-class swallowing sEMG dataset (11 subjects, including 3 laryngeal cancer patients) using leave-one-subject-out cross-validation, SwallowMamba achieves 93.5% ± 0.3% accuracy with 2.56 M parameters and 5.2 ms inference latency, outperforming Transformer, MoEMba, and EEGMamba baselines. Ablation experiments confirm the individual and synergistic contributions of each module.
Full Text Translation (powered by iFLYTEK)
Full Text Translation (powered by iFLYTEK)
-
-