From classical signal theory to physiological intelligence.
Signals define the perception layer of Neuroide. This topic covers how information is gathered from raw measurements and sensory streams across digital signal theory, biosignals, physiological sensing, EEG, EDA, ECG, PPG, and multimodal data.
Sampling, transforms, filtering, stochastic signals, spectral estimation, wavelets, and state-space views of time series.
ECG, EEG, EMG, EDA, respiration, PPG, sleep data, wearable sensing, and multimodal physiological measurement.
Sequence learning, feature engineering, self-supervision, transfer across devices, and subject-specific adaptation.
Monitoring, anomaly detection, digital health, and machine intelligence grounded in noisy human-centered data.
Physiological Signals as Dynamic Systems
A structured introduction to physiological signals as noisy, multiscale measurements of biological regulation.
Classical Signal Concepts for Physiological Data
Sampling, filtering, spectra, stationarity, and artifacts for serious biosignal analysis.
Self-Supervised ECG Representation Learning
Contrastive and masked objectives for waveform data under label scarcity and domain shift.
Multimodal Biosignal Foundation Models
Cross-modal fusion and representation learning for physiological data collected across sensors and settings.