The body speaks in waves.
Engineering the next generation of contactless health monitoring.
Deep dives into the engineering behind wearable health tech — BCG signal processing, sleep-stage AI, sensor design, and the systems that make non-invasive monitoring possible.
What your body is telling you
Latest writing
ECG and BCG: Reading Your Heart's Electrical and Mechanical Signatures
Every heartbeat leaves two distinct traces — an electrical fingerprint in the ECG and a mechanical recoil signature in the BCG. Understanding both is the foundation of contactless cardiac monitoring.
AI / MLKnowledge distillation: teaching a BCG model with ECG labels
When your teacher model is 85% accurate and your student input is noisier, you use that gap intentionally.
Sensor HardwarePVDF vs capacitive: which sensor survives a restless sleeper?
Two sensor modalities, one hostile environment. After six months of field testing, here is what actually breaks.
HealthTechThe engineering stack behind contactless vitals: from PVDF film to sleep stage
Sensor physics, ADC design, embedded firmware, cloud DSP, and the ML inference layer that ties it together.
HealthTechBLE for overnight ECG: what the spec sheets don't tell you
Bluetooth Low Energy looks ideal for overnight biosignal recording. The spec sheet omits the parts that will break your study.
Deep LearningTransformers for biosignals: what the hype gets right (and wrong)
Attention mechanisms are genuinely useful for long-context physiological signals. The implementation details are where most papers quietly fail.
BCG / HRVBuilding a Signal Quality Index from scratch
An SQI is the immune system of your BCG pipeline. Here is how to build one that actually rejects bad data without being paranoid.
BCG / HRVSnoring detection from BCG: separating breath from ballistic noise
Snoring produces a characteristic vibration signature in BCG. Isolating it from cardiac and respiratory signals requires understanding all three simultaneously.
The person behind the signal
-
ECG–BCG Synchronization Pipeline
Full-stack system aligning Polar H10 ECG with BCG (PVDF Sensor). R peaks detected via SciPy's signal module; BCG J peaks extracted and filtered using z-score based thresholding to retain only high-confidence peaks. Cross-correlation between R and J peaks computes per-beat alignment. R-to-J peak matching with ±50ms delay handling and drift logging.
- Python
- NumPy/SciPy
- asyncio/BLE
- Polar H10
- PVDF
-
Contactless Vitals Stack
End-to-end pipeline extracting heart rate and respiratory rate from raw PVDF BCG signals — no contact, no wearable. Bandpass filtering, peak detection, and RR interval analysis to deliver continuous vitals from an under-mattress sensor.
- Python
- SciPy
- PVDF
- BCG
-
Snoring Detection via BCG
Vibration-based snoring classifier using under-mattress PVDF sensor — no microphone required. Frequency-domain analysis of BCG signal to distinguish snoring events from movement artifacts and normal breathing patterns.
- Python
- SciPy
- scikit-learn
- PVDF
-
Multi-Sensor Signal Processing
Evaluated and extracted meaningful insights from diverse sensor modalities — contactless vitals (HR, respiration) from PVDF, bed occupancy and posture detection from custom capacitive sensors. Demonstrates the ability to adapt signal processing and data science techniques to any sensor to unlock actionable health insights.
- PVDF
- Capacitive Sensors
- Signal Processing
- Python
- scikit-learn