The planned one-year research will focus on the development and evaluation of energy-efficient IoT systems based on modern sensor technologies and advanced communication protocols. The primary emphasis will be on testing commercial and experimental devices utilizing LoRaWAN and BLE technologies under real-world conditions, alongside the development of autonomous IoT units capable of long-term field operation. In parallel, software modules based on machine learning and deep learning techniques will be developed to detect environmental changes such as parking space occupancy or soil moisture variation, with a focus on minimizing energy consumption.

In the area of RFID technologies, the research will include the simulation of passive RFID tags with multilevel modulation and coding schemes, as well as testing of bistatic communication systems using previously developed simulation models. A series of laboratory measurements are planned to validate these models and characterize the performance of developed solutions. Furthermore, coding schemes for multilevel modulation will be explored, followed by the development of a prototype RFID tag and testing in realistic environments.

The third research domain involves the application of deep learning and high-performance computing for the analysis of large-scale, heterogeneous datasets, with a particular focus on bioinformatics. The goal is to develop advanced models for the analysis of complex biological data and apply them to relevant scientific and biomedical challenges.