Predictive systems that anticipate failures and optimize operations.
Time-series forecasting and anomaly detection on high-frequency sensor data. Built early-warning systems that reduced operational downtime and improved reliability.
Monte Carlo simulation, Bayesian inference, and stochastic processes applied from railway maintenance planning to investment risk assessment.
Led cross-functional projects as Head of Innovation, managing stakeholders, contracts, and delivering systems under tight deadlines.
Deployed scalable pipelines on GCP (Python, TensorFlow, BigQuery). Built dashboards translating technical metrics into business decisions.
Fusing expert knowledge with sensor data for condition assessment. Published in Sensors, 2023.
Read paperComparing value-based and policy-based Reinforcement Learning for infrastructure planning. Published in Structural Health Monitoring, 2023.
Read paperBuilt distributed monitoring system processing sensor data across multiple sites. Machine Learning models detected to detect asset health, enabling proactive maintenance and reducing downtime.
Technical detailsDeveloped analytics platform combining operational metrics with data-driven indicators. Monte Carlo simulations provided confidence intervals for resource allocation decisions.
Case studyPhD research using Bayesian networks to fuse expert knowledge with inspection data. Algorithms estimate remaining service life of railway welds. Collaboration with Swiss Federal Railways.
Read paperETH Entrepreneurship Award 2020. Concept combining camera, accelerometer, and gyroscope data to estimate body measurements and reduced the fashion e-commerce return rates.
Applied unsupervised learning to identify operational modes from turbine sensor data. Estimated remaining lifetime via fatigue damage accumulation models.
Adøn Power Down project. Developed user detection system to automatically cut standby power consumption, combining motion sensors with usage pattern learning.