SleepSensor

Context

Disrupted sleep is very common and poses a huge burden to society. To improve diagnosis and monitor treatment efficacy, new ways of recording sleep are needed

Partners

Dr. Shanaz Diessler and Prof. Paul Franken, Center for integrative genomics, University of Lausanne (project coordinator)

Proposed solution

  • A non-intrusive sensor-based system for acquiring physiological data during sleep
  • Machine learning algorithms for signal processing, feature extraction and automatic wake-sleep stage classification
  • Machine learning algorithms for patient data analysis