implement biosignal processing

Portable ECG systems face challenges in performing real-time, privacy-compliant, and energy-efficient signal preprocessing at the edge. Method: This work proposes a co-optimized preprocessing framework tailored for AI-driven analysis, integrating lightweight filtering, adaptive baseline correction, and compressed sensing–based denoising to achieve low-latency signal enhancement on resource-constrained edge devices; critically, it jointly optimizes preprocessing and subsequent model inference to balance energy consumption, accuracy, and real-time performance. Contribution/Results: Extensive experiments on representative edge platforms (e.g., Raspberry Pi, Jetson Nano) demonstrate feasibility and efficacy: compared to conventional cloud-based preprocessing, the framework reduces data upload volume by 62%, decreases end-to-end latency by 78%, and fully satisfies GDPR-level local data processing requirements—thereby significantly improving the energy efficiency, security, and practicality of long-term ECG monitoring systems.

This study addresses the analytical unreliability of electroencephalography (EEG) signals arising from artifact susceptibility, low signal-to-noise ratios, and substantial inter-subject variability. To overcome these challenges, we present a comprehensive modern EEG analysis pipeline encompassing preprocessing, statistical modeling, and machine learning. Methodologically, this work systematically integrates independent component analysis for artifact removal, time-frequency analysis, source localization, multivariate decoding, and deep learning techniques, bridging traditional signal processing with emerging EEG foundation models while strictly adhering to BIDS and FAIR data standards. The primary contribution lies in establishing best-practice guidelines for cross-subject generalization and equitable benchmarking. Ultimately, this framework provides the field with a reliable, interpretable, and highly reproducible reference architecture for end-to-end EEG analysis.

This study addresses the lack of consensus on preprocessing strategies for multi-label ECG-based cardiac disease classification. We systematically evaluate the impact of downsampling, normalization, and bandpass filtering on three state-of-the-art time-series classifiers—InceptionTime, TS-Transformer, and ROCKET—across three benchmark ECG datasets. Results show that 50 Hz sampling achieves performance comparable to 500 Hz, reducing model parameter count and training time by ~90%; min-max normalization slightly degrades accuracy, while IIR/FIR bandpass filtering yields no significant improvement; Z-score normalization demonstrates robustness. Crucially, we empirically refute both the “preprocessing-irrelevance” and “blind-preprocessing-effectiveness” hypotheses, providing the first evidence that preprocessing must be task-adaptive: sensitivity varies significantly across cardiac disease subtypes and model architectures. Our findings establish a reproducible, lightweight, and task-driven preprocessing paradigm for ECG-based intelligent diagnosis.

This study investigates the cross-modal transferability of EEG pre-trained foundation models to blood pressure estimation from ECG/PPG time-series signals, proposing a fine-tuning paradigm that obviates additional large-scale pre-training. Methodologically: (1) EEG foundation models are directly adapted to ECG/PPG inputs to construct end-to-end systolic/diastolic blood pressure regression models; (2) a lightweight dynamic INT8 quantization strategy is introduced to preserve accuracy under edge-device constraints. The core contribution lies in the first empirical validation of EEG models’ representational transfer capability to cardiovascular signals, achieving joint optimization of accuracy and efficiency. On MIMIC-III and VitalDB, the method achieves diastolic and systolic BP MAEs of 1.57 mmHg and 2.72 mmHg—improving upon state-of-the-art by ~1.5×—while compressing model size by 3.5× to 3.83 MB, enabling real-time inference on wearable devices.

Real-world ECG analysis faces significant challenges, including strong data heterogeneity, high noise levels, substantial inter-population variability, and complex rhythm-event associations. To address these, we propose AnyECG—the first foundation model tailored for multi-source heterogeneous ECG data. Our method introduces three key innovations: (1) an ECG Tokenizer that encodes continuous, noisy signals into discrete, compact, and clinically interpretable local rhythm tokens; (2) a proxy-task-driven discretized representation learning framework coupled with rhythm-pattern-aware autoregressive pretraining; and (3) joint self-supervised learning across diverse devices and clinical scenarios. Evaluated on four tasks—abnormality detection, arrhythmia classification, lead imputation, and ultra-long ECG analysis—AnyECG consistently surpasses state-of-the-art methods, demonstrating marked improvements in generalization and robustness under realistic, noisy, and heterogeneous conditions.

This work addresses the computational and memory bottlenecks of deploying high-performance Transformer models for electrocardiogram (ECG) and electromyogram (EMG) analysis on resource- and power-constrained micro neural processing units (μNPUs). To this end, the authors propose PhysioLite—a lightweight, hardware-aware model architecture and training framework that integrates learnable wavelet filter banks, CPU-offloaded positional encoding, μNPU-optimized network layers, and 8-bit quantization. This approach achieves state-of-the-art accuracy on ECG and EMG tasks while reducing model size to approximately 370 KB—less than 10% of the baseline—and demonstrates efficient real-time inference with low latency and power consumption. Notably, PhysioLite is the first to enable effective physiological signal modeling on real-world μNPU platforms such as the MAX78000 and HX6538 WE2.

Medical time series such as electrocardiograms (ECGs) and photoplethysmograms (PPGs) are frequently affected by measurement artifacts due to challenging acquisition environments, such as in ambulances and during routine daily activities. Since automated algorithms for analyzing such signals increasingly inform clinically relevant decisions, identifying signal segments on which these algorithms may produce unreliable outputs is of critical importance. Signal quality indices (SQIs) are commonly used for this purpose. However, most existing SQIs are task agnostic and do not account for the specific algorithm and performance metric used downstream. In this work, we formalize signal quality as a task- and metric-dependent concept and propose a perturbation-based SQI (pSQI) that aims to detect an algorithm's performance degradation on an input signal with respect to a metric. The pSQI is defined as the worst-case value of the performance metric under an additive, colored Gaussian noise perturbation with a lower-bounded signal-to-noise ratio. We introduce formal requirements for task- and metric-specific SQIs, including monotonicity of the metric in expectation and maximal separation under thresholding. Experiments on R-peak detection and atrial fibrillation classification benchmarks demonstrate that the proposed pSQI consistently outperforms existing feature- and deep learning-based SQIs in identifying unreliable inputs without requiring training.

This study addresses the challenge posed by strong artifacts in transcranial magnetic stimulation (TMS)-evoked electroencephalography (EEG) signals, which hinder their application in closed-loop neuromodulation and brain–computer interfaces. The work presents the first standardized benchmark dataset for TMS-EEG denoising and systematically evaluates two mainstream source-domain denoising pipelines under conditions lacking ground-truth physiological signals, assessing both artifact suppression efficacy and preservation of genuine TMS-evoked responses. The proposed preprocessing framework demonstrates robust performance, significantly enhancing signal quality and establishing a unified benchmark for algorithm development. This advancement facilitates more reliable use of TMS-EEG in neuroscience research, clinical settings, and embedded brain–computer interface systems.

Standard Transformers struggle to effectively model long-range dependencies, complex temporal dynamics, and multi-scale frequency characteristics inherent in biomedical signals. To address this limitation, this work proposes WaveFormer, a novel Transformer architecture that integrates wavelet decomposition to jointly model time-frequency features during token embedding and positional encoding. The key innovations include generating frequency-aware tokens via multi-channel discrete wavelet transform (DWT) and introducing dynamic wavelet positional encoding (DyWPE) to adaptively capture the temporal structure of signals. Evaluated on eight datasets spanning human activity recognition and electroencephalogram (EEG) analysis, WaveFormer demonstrates competitive performance, validating its effectiveness in modeling multi-scale frequency information in biomedical time-series data.

This study addresses the challenge of extracting secondary modulation information—such as respiratory signals—from nonsinusoidal multicomponent biomedical signals like photoplethysmography, where coupling between oscillatory amplitude envelopes and instantaneous frequencies complicates analysis. To tackle this, the authors propose the TETRIS framework, which is grounded in a generalized adaptive non-harmonic model. TETRIS introduces, for the first time, a data-driven time–frequency plane tiling strategy guided by the instantaneous frequency of the cardiac component, combined with second-order oscillatory dynamic modeling to adaptively process distinct regions of the signal. This joint approach enables simultaneous decoding of nested rhythms embedded in both amplitude modulation and instantaneous frequency. Experimental results demonstrate that TETRIS significantly enhances time–frequency representation quality on semi-synthetic signals and accurately reconstructs multiple surrogate respiratory signals with high precision.