Intelligent strategies to learn and recognize lifestyle patterns

At imec, Body Area Networks

Background and problem statement

The Holst Centre has proven track record of wearable technologies for continuous activity and vital signs monitoring. Thanks to the quality and design of our sensor systems and to collaboration with clinical centers and universities we have developed and validated several algorithms for extracting meaningful information on the health status of a subject. We are currently developing “at hand” solutions  (such as applications for smartphones and tablets) that can allow users to visualize their health status and receive feedback for improving their condition on routine basis. This master thesis has the objective to contribute to our goal to derive algorithms more and more tailored to the specific user needs.


You have a proven experience with Matlab or Python, and JAVA

You have a proven experience with machine learning techniques 

You have experience with data collected from wearable devices (preferable)

You are able to quickly understand problems and discuss analytically solutions within the team 

You like to work independently and are capable to clearly refer to team members and supervisor for technical needs and consultancy 

You have good written and verbal English skills 

You are highly motivated and passionate for wearables, health and data mining

You are eager to grow in your knowledge and competences 


The aim of the student project is (1) to integrate quantitative vital signs collected by our sensors with qualitative information collected with technologies already available in the consumer market; (2) to develop intelligent algorithms able to learn from the user and capable of recognizing lifestyle patterns; (3) to test the robustness and flexibility of the algorithms with respect to noise and missing data; (4) to contribute to the design of feedback systems able to motivate behavioral changes.  


Develop and test innovative multi-parameter algorithms 

Provide technical support for experimental protocols design

Actively interact with interdisciplinary team

Write technical reports

Educational program


Biomedical Engineering / Computer Science

Research theme

From Human Sensory-Motor Function to Patient-Practitioner Interaction

Principal Investigator track


B.J. van Beijnum?

Supervision and info

imec supervision:

Giuseppina Schiavone


UT supervision:


For all inquiries, please contact:

Ms Sandra Maas, Management Assistant Human Resources.

Telephone number: +31 (0)40 40 20 500