Marios Krestenitis

Papers

Total Citations

H-Index

About

Marios Krestenitis is a researcher at the forefront of applying machine learning to intelligent manufacturing and assembly processes. His primary research focuses on developing real-time, data-driven frameworks for quality assurance in industrial automation, with a particular emphasis on snap-fit assembly verification. Krestenitis’s most significant contribution is his pioneering work on a machine learning framework for the real-time identification of successful snap-fit assemblies, which has garnered 40 citations. This work addresses a critical challenge in manufacturing: snap-fit joints, while efficient, often conceal their locking mechanisms within the product structure, making visual inspection impossible. By leveraging force profile data, Krestenitis’s classifier enables automated systems to detect successful assembly with high accuracy. To support this research, he also created and published the "Ds.04.Certh.Snapfitforceprofiles" dataset, which captures force profiles from both robotic and human assembly processes. This dataset serves as a foundational resource for training and benchmarking machine learning models in assembly verification. Krestenitis’s work bridges the gap between traditional mechanical engineering and modern AI, offering practical solutions for Industry 4.0 and smart factory environments.