BSc/MSc – Source Estimation in Atmospheric Radiological Releases
Abstract When radioactivity is detected in the atmosphere, a crucial task is to determine both the location of a release and its temporal profile. While the location is often known, the temporal profile and the total quantity of the released substance are usually only roughly estimated or entirely unknown.The main objective is to reconstruct the […]
MSc/BSc – Tuning of decision-rules parameters
Abstract Abstract The quality of optimised decision-making algorithms (estimation, forecasting, classification, hypothesis testing, economic, medical or political decision-making, management, etc.) depends, often critically, on the choice of their parameters (order of models, weight of individual attributes in multi-criteria decision-making, probability of mutations in genetic algorithms, etc.). Therefore, it is desirable to set them, preferably automatically. […]
Identity Attributes Matrix Initiative (IAMI) Project
Identity Attributes Matrix Initiative The Identity and Access Management Integration (IAMI) system is an initiative aimed at enhancing the capabilities of European Union Law Enforcement Agencies (LEAs) and security/intelligence agencies in combating terrorism and ensuring national security. IAMI project leverages AI-powered technologies to improve biometric and non-biometric identity identification and resolution while adhering to […]
MSc – Productivity of Geniuses
Abstract Even highly creative humans (scientists, artists, influencers…) can produce a limited number of significant outputs in life. Predicting the extent to which their creative capacity is exhausted is significant for making decisions that influence their careers. The work focuses on a data-driven personalisation of personal-creative productivity. From a formal point of view, it is […]
Dynamic distributed decision making: role of uncertainty
The aim of the project is to promote understanding of complex interactions and the dynamics of decision making (DM) under complexity and uncertainty. The theory under consideration should be applicable to dynamic DM and interaction within a flat structure without any coordination. It will support modelling a living agent acting within a complex network of […]
Strategy AV21
The program “AI: Artificial Intelligence for Science and Society” supports research and development in the area of general AI and ML methods as well as their application in a wide range of fields. UTIA is responsible for research topics related to the deployment of artificial intelligence tools in technical, economic and humanities fields. Find out […]
Controllable gripping mechanics: Modelling, control and experiments
The project strives to expand knowledge of gripping mechanics, based on 3D-printed electroactive materials and pneumatically stretchable structures, origami/kirigami type, for applications in robotics, biomedicine and space. Both concepts are compared with each other. The project focuses on solving open scientific issues in the field of soft robotics such as: whether electroactive materials from 3D […]
Distributed rational decision making: cooperation aspects
The proposed project aims to contribute to theoretical and algorithmic development of cooperation and negotiation aspects while respecting agent imperfection and deliberation. The targeted solution should be applicable to decentralised dynamic DM under complexity and uncertainty. It will support a single agent acting within a network of strategically interacting agents. A flat cooperation structure without […]
Optimal Distributional Design for External Stochastic Knowledge Processing
Optimal processing of distributed knowledge is key agenda in machine learning, signal processing and control, driven by sensor networks for smart environments, autonomous agents and distributed infrastruktures (clouds, Internet) serving the tnternet of things. Nodes may communicate via partially specied probability distributions (moments, etc.). If a remote node or central coordinator is to process this […]
Hierarchical models for detection and description of anomalies
Anomaly detection, which aims to identity samples very different from majority, is an important tool of unsupervised data analysis. Currently, most methods for anomaly detection use relatively simple shallow models without any complex layers and hierarchies. This in sharp contrast to the area of supervised classification, where hierarchical models with large number of layers stacked […]