Work

Projects

Explore projects built by Harry Wik, from TinyML posture classification on Arduino to graph neural network research with Neo4j. Detailed technical write-ups included.

Neo4j MPGNN Thesis

Jun 15, 2026

Master's thesis on integrating Graph Neural Networks with Neo4j, benchmarking cost-efficient training and inference pipelines for graph-structured data.

#thesis#graph-neural-networks#neo4j#machine-learning#graph-databases#pytorch

5 parts

TinyML Arduino Posture Classifier

Dec 1, 2025

An Echo State Network running on Arduino Nano 33 BLE that classifies posture using IMU sensor data, with federated learning over Bluetooth Low Energy.

#tinyml#embedded#machine-learning#arduino#edge-computing#federated-learning

4 parts