Skip to content
~/patrick/projects/ppg-biomarkers
← projects

model lane · 2024

Biomarker Detection in PPG Signals

Research on extracting biomarkers from photoplethysmogram (PPG) signals, including peak detection, signal-quality metrics, and a Bayesian mixture-of-experts ensemble.

pipeline
  1. data (covered)
  2. model (covered)
  3. eval (covered)
  4. serve (not covered)
  5. monitor (not covered)
result

My signal-resampling module and its test suite were merged into the research group's shared codebase and adopted lab-wide.

stack

PythonBayesian modelingSignal processingJupyterMixture of experts

I worked on this as a research assistant in the Jarvis Lab in BYU’s Department of Mathematics, from December 2023 to October 2024. The group works on extracting biomarkers from PPG signals, which are the optical pulse waveforms that wearables and pulse oximeters measure.

I built a dynamic signal-resampling module and its pytest test suite, and I developed signal-quality metrics to automatically detect and filter low-quality waveform data.

I also designed, implemented, and evaluated several peak-detection algorithms (wavelet transforms, Gaussian smoothing, and zero-crossing detection), along with a Bayesian mixture-of-experts ensemble that combines them. I authored a comparative literature review of 15+ published peak-detection methods, and I presented our findings each week to my faculty advisor and an external data-collection partner.

nextFootball Performance and Admissions →

keyboard

⌘K /
Search and commands
t T
Next / previous theme
j k
Move through items on the page (k on the first one goes back to the top)
o
Open the selected item
g then h w p b a l
Home, Work, Projects, Blog, About, Lab
c
Copy email
?
This list

Choose a theme

Dark

Light

You can also press t to step through them.