Internship: Sensor Data Fusion and Machine Learning for Human Activity Detection

Develop a multimodal sensor-fusion system for smarter human activity and occupancy detection in buildings.

Are you a tech-savvy student interested in machine learning, IoT and sensor systems?

In this internship, you will combine data from Crownstone BLE devices with other sensors such as smartphone orientation data, acoustic cameras, and PIR/RF sensors to improve human activity detection.

About this internship

Smart-building sensors each provide only part of the picture. BLE signals can indicate proximity, PIR can detect motion, acoustic systems can capture activity-related information, power usage can tell what for device is being used, and smartphones provide orientation or movement data. Your goal is to investigate and develop methods to fuse and leverage these heterogeneous data streams for a more accurate and robust human activity and occupancy detection system.

A key focus is edge processing: extracting and combining useful information close to the sensors so the solution remains responsive, scalable and privacy-conscious.

What will you do and learn?

This internship provides an exciting opportunity to engage directly with innovative technology and receive mentorship from experienced data scientists and engineers. You’ll:

• Research and select additional sensors that could add value to the HAC system
• Design how measurements from these sensors can be acquired, timestamped and transferred into the HAC system for sensor fusion.
• Prepare, synchronise and analyse multimodal data from Crownstone and complementary sensor systems.
• Design, train and evaluate sensor-fusion and machine-learning approaches for human activity and occupancy detection.
• Compare fused models with single-sensor baselines using metrics such as precision, recall and F1 score.
• Explore how the fusion pipeline can run efficiently at the edge under compute, memory and communication constraints.
• Test your approach in realistic building scenarios and document the main trade-offs and limitations.
• Collaborate closely with our multidisciplinary team and experience the dynamics of startup innovation.

About you

You don't need to have all the answers right away! If you're studying in a science or engineering discipline and enjoy programming and data analysis, you’ll feel right at home.

Ideally, you have the following qualifications:

• Are currently studying computer science, AI, electrical engineering, or a related field.
• In your final bachelor year or master's
• Strong analytical and problem-solving skills
• Interest in machine learning, signal processing, IoT or sensor fusion.
• Experience with programming like C(++) and Python.

It’s a bonus if:

• Have previously worked with sensor data fusion or IoT datasets.
• Have experience with ML frameworks (e.g., PyTorch, TensorFlow, scikit-learnx).
• Enjoy research-oriented projects and experimentation.

About Crownstone

This internship is at one of our daughter companies, namely Crownstone. Crownstone develops BLE-based smart-building and indoor sensing technology. For this project, Crownstone data will be combined with complementary sensors to create a genuinely multimodal edge-AI system.

We are a small, flat organisation with short communication lines. You will have room to work independently, test ideas and turn research into working prototypes. If you enjoy taking initiative, have many ideas, and wish to execute them, you’ll feel right at home.

We offer

• Real hands-on experience: Apply what you’ve learned in your studies to real-life situations
• Guidance and mentorship from experienced engineers and researchers.
• A peek into the international tech scene
• Build a network with industry pros
• A real R&D challenge with direct practical relevance.
• A hybrid working environment in Rotterdam.

Interested? Apply now!

Job Type: Internship

Pay: €400,00 per month

Ability to commute/relocate:

• 3013 Rotterdam: Reliably commute or planning to relocate before starting work (Required)

Work authorization:

• Netherlands (Required)

Work Location: Hybrid remote in 3013 Rotterdam