Mantas Landauskas

Associate Professor at KTU Faculty of Mathematics and Natural Sciences

Mantas Landauskas is an associate professor at KTU Faculty of Mathematics and Natural Sciences, associate professor, Vice-Dean for Research. The main research – image analysis and computer vision, nonlinear dynamic systems, time series forecasts and optimization tasks. In scientific research, M. Landauskas often uses machine learning algorithms to solve classification or forecasting tasks; some of the models being developed are designed for automatic decision-making (detection of a defect in the system from the data stream, detection of an anomaly in the electrocardiogram, etc.).

  • Image analysis and computer vision
  • Nonlinear dynamic systems
  • Time series forecasting problems
  • Optimization tasks

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.

is vaizdų duomenų bazę, kuri yra naudojama mokant ir išbandant specialiai šiam projektui sukurtą DI tinklą.

Smart Hybrid Approach for Defect Detection Based on Analysis of System Entropy (DDetect)

Detection of non-typical or defect related measurements is one of the most important problems in engineering, medicine and other areas. In the first scenario the existence of a fault is identified and further degradation of the system is prevented while in the second – the illness is diagnosed. Constant increase in amounts of diagnostic and measurement data implies the need of automated and smart solutions for the detection of defects. Novel aspect of this project is the joining of artificial intelligence and methods of analysis of nonlinear dynamical systems.

The data will be analyzed not directly but by performing computations, during which representative two-dimensional digital images based on permutation entropy, Wada characteristics, time averaged geometric moiré will be constructed, first. Thus the problem of detection of defects in signals is transformed to the problem of image classification and/or identification. This problem will be dealt with methods of artificial intelligence during this project. Additionally, smart approach for detection of defects without prior knowledge of their existence will be developed.

Investigation of Cardiovascular Relationships Between Humans and Animals and the Earth’s Magnetic Field (GEOMAG)

The project aimed to assess the impact of the earth’s local and global magnetic fields on human and animal health. Scientists have studied the variations and resonances of magnetic fields that affect the cardiovascular system of humans and animals. The software developed during the project for geomagnetic field calculations is continuously used to this day in the activities of the scientific group in cooperation with LSMU researchers.

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. Global study of human heart rhythm synchronization with the Earth’s time varying magnetic field Inga Timofejeva, Rollin McCraty, Mike Atkinson, Abdullah A. Alabdulgader, Alfonsas Vainoras, Mantas Landauskas, Vaiva Šiaučiūnaitė, Minvydas Ragulskis 2021
3. Permutation entropy-based 2D feature extraction for bearing fault diagnosis Mantas Landauskas, Maosen Cao, Minvydas Ragulskis 2020