Master Thesis - In-ear health monitoring with smart sensors

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

Bosch R&D Center Lund stands for modern development in cutting edge technology in the areas of connectivity, security, mobility solutions and AI. We are growing rapidly and looking for people to join us on our mission to become the Bosch Group’s 1st address for secure connected mobility solutions.  We are working on a range of interesting projects, with a particular focus on software development for the automotive industry, electrical bicycles and Internet of Things. 

Problem statement

Wearable smart devices are everywhere and the demand for personal health monitoring solutions in these devices is increasing, it is no longer all about smart watches. This master’s thesis project will offer you an exciting opportunity to develop a health monitoring application using our in-ear headphones.

 

The headphones are equipped with Bosch Sensortec sensors that can monitor movements and tiny vibrations reaching the ear canal. The challenge is to transform raw sensor data into meaningful and actionable health insights. Through this project you will gain hands-on experience with cutting-edge smart sensor technology and signal processing development, contributing to innovation in wearable health analytics.

 

Proposed solution

This thesis project will focus on developing algorithms for extracting a health insight from the in-ear headphone raw sensor data. This will include exploration of the data, application of traditional signal processing methods, and preferably machine learning methods. Depending on the choice of health insight, there is some data collected for this project, but you are encouraged to also collect your own data using our headphones.

We propose the following topics to be covered in the thesis:

• Initial exploration of the sensor and its raw data
• Describe and identify the features in the sensor data relevant to the physiological state or health metric
• Research and find suitable algorithms (classical signal processing or machine learning/AI methods) for reliably detecting and identifying the features
• Implement, test and refine the chosen algorithms
• Produce a simple demo using your findings

 

You will of course be able to shape the thesis based on your knowledge, interest, and discoveries during the project.

Scope of master thesis project

Two students completing 30 credits each (20 weeks) onsite at the Lund office

Your profile

To be successful in the project with think you are:

• A student in Engineering Mathematics/Physics, Control Science, Electronics or equivalent
• At least one upper basic or advanced course in mathematical statistics
• Relevant courses in statistical signal processing or machine learning
• An interest in algorithm development
• Experienced with or have at least some knowledge of programming in Matlab, Python, C++ or similar.
• Self-driven, able to challenge yourself, and gain the experience needed to move the project forward.
• A person with team spirit, social skills and a curiosity for exploring new technology areas.