Machine Learning Methods for Personalized Detection of Stress Level

At imec, Body Area Networks

Background and problem statement

Mental stress monitoring can help to prevent stress-related problems and the advent of chronic diseases. Aim of the thesis is to investigate data analysis frameworks for personalized stress detection models.

Skills

·

Fluent in MATLAB and/or Python

·

Knowledge of Java and Android Programming

·

Knowledge of Applied Machine Learning and/or Data Mining

·

Motivated student eager to work independently and expand knowledge in the field  

·

Good written and verbal English skills 

Assignment

Mental stress monitoring can help to prevent stress-related problems and the advent of chronic diseases. Offices and working environments are good examples of places where stress often arises. Wearable devices able to gather physiological signals represent nowadays the most suitable technology for continuous and unobtrusive stress monitoring. At Holst Centre, a data analysis architecture and related stress detection algorithms have been developed with promising results for the detection of stress levels. 

The aim of this thesis is further investigate data analysis frameworks for personalized stress detection models. The candidate will apply adaptive Machine Learning techniques and Context-Awareness methodologies for modelling stress level of the users, on the basis of stress models previously created.  

The successful candidate has knowledge of Machine Learning and/or Data Mining and is fluent in at least one between MATLAB/Python and Java. Knowledge of Android  programming in highly valuable. 

Components

·

Literature Review on Stress Monitoring and Adaptive Machine Learning Techniques

·

Development of Data Analysis Architectures for personalizing existing stress level models

·

Development of data-driven Models for personalized stress monitoring

Educational program

MSc

Biomedical Engineering / Computer Science

Research theme

From Human Sensory-Motor Function to Patient-Practitioner Interaction

Principal Investigator track

H.Hermens?

B.J. van Beijnum?

Supervision and info

imec supervision:

Pierluigi Casale

(Pierluigi.Casale@imec-nl.nl)

UT supervision:

?

For all inquiries, please contact:

Ms Sandra Maas, Management Assistant Human Resources.

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