DSP Workshop — From Math to Metal
Digital signal processing from theory to hardware: a 12-chapter learning path, 34 standalone topics, 115 exercises, and 30 embedded C implementations spanning an 8-bit AVR up to a Cortex-M33 with an NPU. Python and scipy throughout, no MATLAB.
Live
Augur — Energy Price Forecasting
Week-ahead electricity price predictions for the Netherlands. 18+ energy market APIs, XGBoost ML pipeline with online learning, interactive Plotly dashboard.
Live
ese-bot — Chat with Your Docs
EU-compliant RAG system deployed for engineering students, two academic years running. Natural language document queries with local embeddings, GDPR-safe logging, and full EU AI Act compliance. Built with Weaviate vector search and Mistral AI.
Live-
Agreement is not verification.
A budget arrived from another session with an €8,000 GPU on it, marked "locked." Two models agreed on the number. Reading the actual spec, and making a different model family check the first, collapsed it to a €750 card. A confident plan and a correct plan look identical.
-
AI review is plausibility review.
In a 68-equation theory document, two AI reviews in assessment mode caught zero errors. A third pass with the same model family but a reproduction instruction caught three. AI review is plausibility review unless you make it not be.
I build things at the intersection of sensors, signal processing, and AI: prototypes, feasibility studies, data pipelines, embedded ML. Most useful when a problem spans physics and software. Recent work has included Parkinson's voice biomarkers on an ESP32, week-ahead electricity-price forecasting from 18+ energy APIs, a small EU-only RAG chatbot for my students, and multi-agent review of engineering requirements.
PhD in Electrical Engineering from TU/e, MSc cum laude. Six years at Philips Research on biomedical sensors and patient monitoring, with multiple patents. Ten years teaching and researching at HAN on embedded ML, signal processing, and computer vision. 27 publications, h-index 12, 500+ citations.
Freelance R&D: feasibility studies, prototyping, technical training, EU AI Act guidance. Most at home where physics, signals, and software meet.