Scientific research conducted at the Department of Intelligent Systems and Networks is focused on the wide use of modern computer science and its related sciences in industry, management, applied research, and administration. A significant part of the obtained effects has already been verified in production conditions (industrial plants, local government units), where the high effectiveness of the proposed solutions has been confirmed. Besides that, the employees of the Department seek new methods in the field of artificial neural networks and machine learning that may be used in those areas. Research is conducted in several areas:
- Cybersecurity
- Analysis and synthesis of environmental and transport systems
- Machine learning in intelligent systems
- New architectures for neural networks
Contact: jkorniak@wsiz.edu.pl
Scientific research projects financed from external sources:
Multi-sensory platform for imaging and detection of threats occurring in areas with highly dynamic environmental conditions
Agreement: DOB-SZAFIR/01/B/038/04/2021 from 20.12.2022. Implementation period: 03.01.2023 – 02.01.2026
Project acronym: MUSE
Beneficiaries:
Military University of Technology
DRI Solutions Sp. z o.o.
University of Information Technology and Management in Rzeszów
Thematic scope:
Technologies used in unmanned systems and autonomous platforms supporting operations in maritime environments.
Project summary:
The aim of the project is to develop a demonstrator of a multi-sensory platform equipped with a visible light camera (VIS), a cooled thermal night camera with a bolometric array (MWIR), a laser designator (LD) for laser-guided weapons, a laser rangefinder (LRF), and a target tracking module (VT), integrated with an aerial research platform in the form of an unmanned aircraft and helicopter. The platform will be equipped with a secure, encrypted telecommunications link and a machine learning system for generating a prioritized threat map. The demonstrator is intended to operate in high-humidity environments with salt fog and strong wind gusts, i.e., environments with highly dynamic conditions characteristic of maritime settings.
Main objective of the project:
The goal of the project is:
- a) to develop a threat detection and imaging system (SDZZ) equipped with a machine learning system for prioritizing threats occurring in the monitored area or battlefield, and
- b) to develop an aerial research platform (LPB) based on two types of carriers—fixed-wing aircraft and helicopter—to enable demonstration of the SDZZ functionality in a maritime environment, i.e., a high-humidity environment with salt fog and strong wind gusts, characterized by highly dynamic conditions.
Specific objectives:
Development of the architecture of a multi-sensor threat detection and imaging system based on: a visible light camera (VIS), a cooled thermal night camera with a bolometric array (IR), a laser designator (LD) for laser-guided weapons, a laser rangefinder (LRF), and a target tracking system (VT).
Development of an IT system based on machine learning technology for creating aerial battlefield maps with prioritization of targets and threats.
Development and construction of an aerial research platform based on two types of carriers: fixed-wing and rotary-wing.
Development of hardware architecture and conducting hardware-in-the-loop (HIL) simulations of two control systems for carrier platforms cooperating with the European GALILEO satellite system.
Development and creation of research models of an integrated data exchange and processing environment architecture.
Conducting flight tests of the developed threat detection and imaging system under field conditions.
Development of a feasibility study for further system development to achieve Technology Readiness Level 9 (TRL 9).
The presented publication:
2025 IEEE international conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) [Dokument elektroniczny] : 17-21 March 2025, Washington D. C., USA : proceedings 2025 | Conference paper | Author
DOI: 10.1109/PerComWorkshops65533.2025.00080
Part of ISBN: 979-8-3315-3553-7
OTHER-ID:
BPP_AGH/publ_id/160607
Contributors: Mateusz Mojżeszko; Lucyna Hajder; Piotr Hajder; Mirosław Hajder; Mateusz Liput; Robert Rogólski; Łukasz Kiszkowiak
Dynamically reconfigured system of environmental and public safety moni toring (cross-sector partnership: Boguchwała Smart City)
Project manager: Mirosław Hajder, Ph.D., Eng. mhajder@wsiz.edu.pl
UITM employees’ scientific activity was used to design and implement a monitoring system of various types of pollutants in the Boguchwała commune. The developed models and tools formed the basis of the project of a security monitoring system; UITM was invited by local government units to a cross-sector partnership in order to apply for financing of the project. The application was recognized by the Ministry of Development in 2019, thanks to which funds were obtained for the implementation of the project aimed at improving the state of environmental and public safety in the commune.
The research was aimed at:
1. Regionalization of methods and means of synthesis and analysis of environmental monitoring based on the use of the Internet of Things;
2.Development of methodological foundations for monitoring systems construction as pervasive computing solutions and cyber-physical systems;
3.Lowering the costs of designing, constructing and operating regional environmental monitoring systems.
Period of implementation: 2019–2022
Financing: from European Union means within the Operational Program Technical Assistance 2014-2020 “Boguchwała Smart City – Dynamically reconfigured system of environmental and public safety monitoring with detection of sources, issuers and separation of safety areas”
A new approach to effective training of complex intelligent systems
Project manager: Prof. Bogdan Wilamowski, Ph.D. Eng.
Successful completion of the project can solve many scientific and practical problems by replacing the traditional design approach with a new learning approach. This alternative method can have a broader meaning by finding solutions to many problems that until now were impossible to solve with traditional methods.
Period of implementation: 20.01.2016–25.06.2019
Financing: National Science Center OPUS program
Contact: jkolbusz@wsiz.edu.pl
Intelligent non-linear systems with shallow and deep architectures
Manager: Prof. Bogdan Wilamowski, Ph.D., Eng.
Recent research shows that the most popular architectures such as SLP (Single-Layer Perception) (MLP with one hidden layer) have very limited capabilities. For example, with a network of 10 SLP neurons, you can solve a Parity-9 problem while a FCC (Fully Connected Cascade) network with the same number of neurons allows to solve Parity-1023 problems. Unfortunately, popular learning algorithms (including the LM algorithm) are not capable of learning this type of compact and powerful architectures. The problems associated with the use of traditional neural networks pushed scientists to look for other directions, such as fuzzy systems, SVM (Support Vector Machine) or ELM (Extreme Learning Machines). It turns out that these complex problems can be solved using new compact architectures. Therefore, research in the project focused on networks with new compact architectures and new learning algorithms.
Period of implementation: 16.07.2014–15.01.2017
Financing: National Science Center OPUS program
Contact: jkolbusz@wsiz.edu.pl
