Sigurd Villumsen
Papers
4
Total Citations
17
H-Index
2
About
Sigurd Villumsen is a researcher at the intersection of industrial AI, robotics, and signal processing, whose work focuses on building intelligent monitoring and automation systems for manufacturing. His primary research areas include anomaly detection in industrial acoustic and time-series data, as well as motion planning for redundant robotic systems used in remote laser processing. Villumsen’s most notable contribution is the development of ScaloAdaptAlert (2025), a novel framework that integrates power scalograms, adaptive filter banks, and convolutional neural networks for supervised anomaly detection in industrial acoustic data—a paper that has already garnered 9 citations, signaling its timely impact. He also introduced STAD-FEBTE (2023), a shallow, supervised framework for time-series anomaly detection that emphasizes automatic feature engineering and tree-based ensembles, addressing the critical need for robust monitoring to prevent faulty production and equipment damage. In robotics, his work on task sequencing and motion planning for redundant laser processing equipment (2017) leverages redundancy space sampling and PRM-based algorithms to optimize multi-DOF systems. With a growing citation footprint and a focus on practical, data-driven solutions for Industry 4.0, Villumsen is establishing himself as a key contributor to safer, smarter industrial automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4