Paulius Palevičius

Associate Professor at KTU Faculty of Mathematics and Natural Sciences

Paulius Palevičius is an associate professor at KTU Faculty of Mathematics and Natural Sciences. He obtained a PhD degree in mechanical engineering in 2015. The scientist is involved in the activities of the Nonlinear Systems Mathematical Research Centre. The main directions of P. Palevičius’ research are image analysis and computer vision and multidisciplinary mathematical models.

  • Image analysis and computer vision
  • Multidisciplinary mathematical models

A Novel AI-Based Automated Identification of Cracks in Concrete Bridges and Offshore Oil Installations (ConcreteAI)

Environmental factors affecting concrete structures like bridges, beams, columns and highways in onshore and offshore environments lead to development of micro-cracks. Early detection of surface micro-cracks in concrete structures helps to put preventive measures in place to avoid failure potentially saving loss of assets and in some cases lives.

In this project scientists created an automated AI based system which will allow training and testing of real time images of concrete bridges and offshore structures, which are augmented by the presence of shadows and other noises. Researchers have worked hard on the development of an image database of images of concrete structures with cracks and shadows, which will then be used for training and testing of the AI network created specifically for this project.

Development of a predictive model for antimicrobial activity of titanium dioxide structures surfaces

Despite numerous existing potent antibiotics and other antimicrobial means, bacterial infections are still a major cause of morbidity, implant rejection, and mortality. Moreover, the need to develop additional bactericidal means has significantly increased due to the growing concern regarding multidrug-resistant bacterial strains and biofilm associated infections.

The projects aimed to develop and implement machine learning based model for prediction of the formed structures’ surface antimicrobial activity for targeted gram-negative bacteria. The development of this model would lead to the advanced use of antimicrobial coatings and bacterial control. The main project result – machine learning based model for prediction of the TiO2 structures’ surface antimicrobial activity for targeted gram-negative bacteria and related software.

No. Title Authors Year
1. An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows Mayur Pal, Paulius Palevičius, Mantas Landauskas, Ugnė Orinaitė, Inga Timofejeva, Minvydas Ragulskis 2021
2. Formation of Au nanostructures on the surfaces of annealed TiO 2 thin films Mantas Sriubas, Vytautas Kavaliūnas, Kristina Bočkutė, Paulius Palevičius, Marius Kaminskas, Žilvinas Rinkevičius, Minvydas Ragulskis, Giedrius Laukaitis 2021
3. Diagnostics measure for roller bearings based on variable moiré gratings Loreta Saunorienė, Paulius Palevičius, Giedrius Laukaitis, Maciek Trusiak, Krzysztof Patorski, Minvydas Ragulskis 2020