MASTER INTERNSHIP - MACHINE LEARNING FOR REMOTE VITAL SIGN MONITORING

  • CSEM SA
  • Canton of Neuchâtel, Switzerland
  • 20/05/2021
Full time Data Science Machine Learning Data Analytics Big Data Data Management Statistics

Job Description

This master’s is to help further our work on remote vital sign monitoring (VSM) and the detection of heart rate through non-contact video measurements. Specifically, in this work the aim is to use machine learning to improvement the accuracy of the prediction of heart rate and heart rate variability in realistic conditions e.g. with motion and at night using video data.

The work will consist of two threads. Firstly, an investigation of motion compensation and artefact removal in images to improve the robustness. Secondly a collection of a database to move the measurements to the infrared, proving that the technique can work over a 24 hour period, i.e. at night.

Your mission

Your mission will be to use state-of-the-art computer vision techniques on database collected to improve the accuracy and robustness of the heart rate predictions and secondly to collect a database at infrared wavelength which would allow this technique to be used 24 hours. The candidate is expected to present their results at the end of the project, which will last a minimum of 6 months.

Your profile

  • experience with deep learning platforms (e.g. Tensorflow and PyTorch)
  • familiar with signal processing: missing data, filtering, etc.
  • familiar with computer vision: face and facial landmark detection, tracking, etc.
  • a good team player ready to tackle technical challenges
  • experience with vital-signs monitoring algorithms is a plus.

We offer

CSEM offers a stimulating and multidisciplinary work environment with the opportunity to work with leading Swiss and international companies. You will have the opportunity to benefit from a multicultural company which clearly promotes an employee-driven culture. CSEM is an equal opportunities employer.

We look forward to receiving your complete application file. Preference will be given to professionals applying directly