PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation

2025-06-12

AI Summary

Physiological signals (e.g., EMG, ECG, EEG) suffer from motion artifacts, baseline drift, low signal-to-noise ratio, and strong non-stationarity, limiting the representational capacity of conventional time-domain or filtering-based methods. To address this, we propose a novel wavelet-Transformer hybrid paradigm for multi-scale time-frequency modeling. Specifically, we design a wavelet-guided continuous wavelet transform (CWT) preprocessing module, coupled with modality-specific encoding branches and a learnable dynamic weighting fusion architecture. Furthermore, we release the first large-scale self-supervised pre-trained model tailored for EMG and ECG. Our approach achieves new state-of-the-art performance across multiple downstream tasks: noise robustness improves by 23.6%, and cross-subject generalization error decreases by 18.4%. This work establishes a new benchmark and a general-purpose representation framework for wearable health monitoring and clinical physiological signal analysis.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Physiological signals are often corrupted by motion artifacts, baseline drift, and other low-SNR disturbances, which pose significant challenges for analysis. Additionally, these signals exhibit strong non-stationarity, with sharp peaks and abrupt changes that evolve continuously, making them difficult to represent using traditional time-domain or filtering methods. To address these issues, a novel wavelet-based approach for physiological signal analysis is presented, aiming to capture multi-scale time-frequency features in various physiological signals. Leveraging this technique, two large-scale pretrained models specific to EMG and ECG are introduced for the first time, achieving superior performance and setting new baselines in downstream tasks. Additionally, a unified multi-modal framework is constructed by integrating pretrained EEG model, where each modality is guided through its dedicated branch and fused via learnable weighted fusion. This design effectively addresses challenges such as low signal-to-noise ratio, high inter-subject variability, and device mismatch, outperforming existing methods on multi-modal tasks. The proposed wavelet-based architecture lays a solid foundation for analysis of diverse physiological signals, while the multi-modal design points to next-generation physiological signal processing with potential impact on wearable health monitoring, clinical diagnostics, and broader biomedical applications.

Problem

• Addressing motion artifacts and low-SNR noise in physiological signals
• Capturing non-stationary multi-scale features in physiological data
• Overcoming inter-subject variability and device mismatch in multi-modal analysis

Innovation

• Wavelet-based multi-scale time-frequency feature extraction
• Large-scale pretrained models for EMG and ECG
• Unified multi-modal framework with learnable fusion