Full-time study

4 years

doc. Ing. Martin Štumpf, Ph.D.

Chairman :
doc. Ing. Martin Štumpf, Ph.D.
Councillor internal :
prof. Ing. Aleš Prokeš, Ph.D.
doc. Ing. Jiří Petržela, Ph.D.
doc. Ing. Jaroslav Láčík, Ph.D.
doc. Ing. Roman Šotner, Ph.D.
doc. Ing. Tomáš Götthans, Ph.D.
prof. Dr. Ing. Zbyněk Raida
Councillor external :
Ing. Ondřej Číp, Ph.D.
doc. Ing. Milan Polívka, Ph.D.

Provide doctoral education to graduates of a master's degree in electronics and communication technologies. To deepen students' theoretical knowledge in selected parts of mathematics and physics and to give them the necessary knowledge and practical skills in applied informatics and computer science. To teach them the methods of scientific work.

The Ph.D. graduate will be able to solve scientific and complex technical problems in the field of electronics and communications. Graduates of the doctoral program "Electronics and Communication Technologies" will be competent to work in the field of electronics and communication technology as scientists and researchers in fundamental or applied research, as high-specialists in development, design, and construction in many R&D institutions, electrical and electronic manufacturing companies and producers and users of communication systems and devices, where they will be able to creatively use modern computer, communication, and measurement technique.

The doctors are able to solve independently scientific and complex engineering tasks in the area of electronics and communications. Thanks to the high-quality theoretical education and specialization in the study program, graduates of doctoral studies are sought as specialists in in the area of electronic engineering and communications. Graduates of the doctoral program will be able to work in the field of electronics and communications technology as researchers in fundamental or applied research, as specialists in development, design and construction in various research and development institutions, electrotechnical and electronic manufacturing companies, where they will be able to creative exploit modern computing, communication and measuring technologies.

Doctoral studies are carried out in agreement with the individual study plan, which will prepare supervisor together with the doctoral student at the beginning of the study. The individual study plan specifies all the duties given by the BUT Study and Examination Rules, which the doctoral student must fulfill to finish his study successfully. These duties are scheduled into entire the study period. They are classified by points and their fulfilment is checked at fixed deadlines. The student enrolls and performs examination from compulsory subjects (Modern digital wireless communication, Modern electronic circuit design), at least from two compulsory-elective subjects aimed at the dissertation area, and at least from two optional courses such as English for PhD students, Solutions for Innovative Entries, Scientific Publishing from A to Z).
The students may enroll for the state exam only if all the examinations specified in his/her individual study plan have been completed. Before the state exam, the student prepares a short version of dissertation thesis describing in detail the aims of the thesis, state of the art in the area of dissertation, eventually the properties of methods which are assumed to be applied in the research topics solution. The defense of the short version of thesis, which is reviewed, is the first part of the state exam. In the next part of the exam the student has to prove deep theoretical and practical knowledges in the field of electrical engineering, electronics, communication techniques, fundamental theory of circuits and electromagnetic field, signal processing, antenna and high-frequency techniques. The state exam is oral and, in addition to the discussion on the dissertation thesis, it also consists of areas related to compulsory and compulsory elective courses.
The student can ask for the dissertation defense after successful passing the state exam and after fulfilling all conditions for termination of studies such as participation in teaching, scientific and professional activities (creative activities), and a study or a work stay at a foreign institution no shorter than one month, or participation in an international project.

The doctoral studies of a student follow the Individual Study Plan (ISP), which is defined by the supervisor and the student at the beginning of the study period. The ISP is obligatory for the student, and specifies all duties being consistent with the Study and Examination Rules of BUT, which the student must successfully fulfill by the end of the study period. The duties are distributed throughout the whole study period, scored by credits/points and checked in defined dates. The current point evaluation of all activities of the student is summarized in the “Total point rating of doctoral student” document and is part of the ISP. At the beginning of the next study year the supervisor highlights eventual changes in ISP. By October, 15 of each study year the student submits the printed and signed ISP to Science Department of the faculty to check and archive.
Within the first four semesters the student passes the exams of compulsory, optional-specialized and/or optional-general courses to fulfill the score limit in Study area, and concurrently the student significantly deals with the study and analysis of the knowledge specific for the field defined by the dissertation thesis theme and also continuously deals with publishing these observations and own results. In the follow-up semesters the student focuses already more to the research and development that is linked to the dissertation thesis topic and to publishing the reached results and compilation of the dissertation thesis.
By the end of the second year of studies the student passes the Doctor State Exam, where the student proves the wide overview and deep knowledge in the field linked to the dissertation thesis topic. The student must apply for this exam by April, 30 in the second year of studies. Before the Doctor State Exam the student must successfully pass the exam from English language course.
In the third and fourth year of studies the student deals with the required research activities, publishes the reached results and compiles the dissertation thesis. As part of the study duties is also completing a study period at an abroad institution or participation on an international research project with results being published or presented in abroad or another form of direct participation of the student on an international cooperation activity, which must be proved by the date of submitting the dissertation thesis.
By the end of the winter term in the fourth year of study the students submit the elaborated dissertation thesis to the supervisor, who scores this elaborate. The final dissertation thesis is expected to be submitted by the student by the end of the fourth year of the studies.
In full-time study form, during the study period the student is obliged to pass a pedagogical practice, i.e. participate in the education process. The participation of the student in the pedagogical activities is part of his/her research preparations. By the pedagogical practice the student gains experience in passing the knowledge and improves the presentation skills. The pedagogical practice load (exercises, laboratories, project supervision etc.) of the student is specified by the head of the department based on the agreement with the student’s supervisor. The duty of pedagogical practice does not apply to students-payers and combined study program students. The involvement of the student in the education process within the pedagogical practice is confirmed by the supervisor in the Information System of the university.

1. AI-based Estimation of Signal Coverage and Performance in Cellular and Wireless Networks

   In contemporary industries, there is a growing need for robust technical platforms capable of handling large volumes of data generated by various sensors, while maintaining high levels of reliability. Cellular and wireless networks have emerged as vital components in meeting these requirements. As the adoption of these networks continues to expand, it becomes increasingly important to understand factors such as signal coverage, reliability, and capacity to optimize performance and ensure seamless connectivity, especially in complex environments such as manufacturing facilities or trains (inside). The utilization of professional hardware equipment and software tools is often necessary to facilitate the collection and analysis of data from these networks [1]-[4]. Recent research [3, [4] suggests that machine and deep learning (ML and DL) technologies could offer effective solutions for estimating signal coverage provided by cellular networks and improving forecasting capabilities in terms of cellular network performance. This work is focused on research in the development of advanced ML and DL algorithms for estimating signal coverage and performance in recent (4G/5G) and upcoming (6G) cellular and possibly wireless networks. The initial phase involves defining the essential Key Performance Indicators (KPIs) associated with measuring and evaluating the performance of 4G/5G networks, as well as establishing principles for conducting long-term measurements to collect data. A portable measurement setup equipped with suitable hardware and software tools will be developed to facilitate the long-term collection and processing of data from indoor and outdoor measurements. During these measurements, various environmental factors will be examined (such as the time of day and its impact on network load due to population mobility), which can affect the quality of radio connections in wireless communications. These collected data, among others, will be used to construct coverage maps for the measured areas. Leveraging the multitude of parameters available, ML and DL architectures will be employed to extract and learn more features from the data. The research will focus on developing, validating, and optimizing artificial intelligence models and algorithms (ML and DL) to improve the prediction of cellular and wireless signal quality and coverage under various scenarios and transmission conditions. The ML/DL algorithms must strike a balance between complexity, accuracy, and efficiency. They are expected to be implemented in Python or MATLAB using available libraries (such as PyTorch, Keras, TensorFlow) and toolboxes (such as Deep Learning Toolbox), respectively. Ultimately, the dataset obtained from long-term measurement campaigns, along with the ML/DL models and algorithms, will be made freely available to the wider scientific community. This approach ensures not only the reproducibility of the achieved results but also serves as the foundation for further research and development in the field of cellular and wireless communications. References [1] V. Raida et al., "On the Stability of RSRP and Variability of Other KPIs in LTE Downlink – An Open Dataset," GLOBECOM 2020–2020 IEEE Global Communications Conference, Taipei, Taiwan, 2020, pp. 1-6, doi: 10.1109/GLOBECOM42002.2020.9348145. [2] M. Rochman and et al., " A comprehensive analysis of the coverage and performance of 4G and 5G deployments," Computer Networks, vol. 237, pages 110060, 2023, doi: 10.1016/j.comnet.2023.110060. [3] L. Zhang, et al., "Machine Learning-Based Integrated Wireless Sensing and Positioning for Cellular Network," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-11, 2023, Art no. 5501011, doi: 10.1109/TIM.2022.3224513. [4] M. A. Khanand et al., " Real-time throughput prediction for cognitive Wi-Fi networks," Journal of Network and Computer Applications, vol. 150, pages 102499, 2020, doi: 10.1016/j.jnca.2019.102499.

   Tutor: Polák Ladislav, doc. Ing., Ph.D.

2. Memetic Algorithms for Multi-objective Optimization of EM Structures

   The vast majority of design tasks are multi-objective where we try to minimize/maximize several parameters of the designed system simultaneously. These parameters are often in conflict and it is advantageous to know the shape of the Pareto front expressing the trade-off between the parameters [1]. Existing global algorithms for multi-objective optimization can find trade-off solutions lying close to the Pareto front, but they work very inefficiently. Therefore, it is proposed to combine them with local algorithms (e.g., Newton's method, conjugate gradient method, etc.) that converge very quickly to local minima, but require only a single-objective formulation. Thus, the subject of this Ph.D. thesis will be to develop a so-called memetic algorithm [2] that appropriately combines global multi-objective algorithms with efficient local algorithms. The memetic algorithm will be implemented in the FOPS toolbox [3] written in MATLAB. Then, the memetic algorithm will be used to design advanced EM components such as antennas, filters, etc.
   [1] DEB, Kalyanmoy. Multi-objective optimization using evolutionary algorithms. Wiley paperback series. Chichester: John Wiley, c2001. ISBN 0-471-87339-X.
   [2] CAPEK, Miloslav; JELINEK, Lukas; KADLEC, Petr a GUSTAFSSON, Mats. Optimal Inverse Design Based on Memetic Algorithms—Part I: Theory and Implementation. Online. IEEE Transactions on Antennas and Propagation. 2023, roč. 71, č. 11, s. 8806-8816. ISSN 0018-926X. Dostupné z: https://doi.org/10.1109/TAP.2023.3308587. [cit. 2024-03-19].
   [3] MAREK, Martin; KADLEC, Petr a ČAPEK, Miloslav. FOPS: A new framework for the optimization with variable number of dimensions. Online. International Journal of RF and Microwave Computer-Aided Engineering. 2020, roč. 30, č. 9. ISSN 1096-4290. Dostupné z: https://doi.org/10.1002/mmce.22335. [cit. 2024-03-19].

   Tutor: Kadlec Petr, doc. Ing., Ph.D.

3. Modelling the transmission environment for 6G communication systems

   The ever increasing demand for high-mobility, high-speed and reliable communication systems brings new challenges to wireless communications. A promising solution to these challenges is offered by 6G systems, which involve the convergence of two key technologies: communication and sensing, referred to as Integrated Sensing and Communication (ISAC). ISAC can perform several functions simultaneously, such as data transmission, motion detection, environmental sensing, or locating and tracking objects, people or devices.
   Because ISAC consolidates the two aforementioned systems into a single platform, it reduces the need for dedicated hardware, spectrum requirements (both systems typically operate in the same frequency band) and overall power consumption. Another positive feature of ISAC systems is the ability to mitigate interference using adaptive techniques, as it can dynamically allocate its resources based on current needs. ISAC systems can also use beamforming techniques to direct the signal or sensing energy to a specific area or target. In this way, signals are not dispersed over a wide area, reducing interference with other systems and allowing more efficient use of the available spectrum.
   However, designing a communication system for ISAC requires a detailed understanding of the communication channel, which is a dynamic and complex medium influenced by a number of factors, including nature of the environment (city, traffic roads, vegetation), interference, mobility, and the type of sensors used. There are a number of channel models that have been developed either for communication purposes or for sensing [1], [2]. However, many of them are not suitable for ISAC as they describe the environment in isolation, do not have sufficient accuracy, or are not well adapted for high-dynamic scenarios. Channel modeling suited to the complex needs of ISAC are just at the beginning.
   The aim of the work will be to analyze the propagation of signals in prospective channels for 6G (in the millimeter wave band), to create and verify new models of communication channels suitable for integration into ISAC, to measure radar cross section (RCS), to analyze the propagation in different weather conditions (rain, snow, ice, influence of vegetation in different seasons). The main objective of the research will be to create hybrid models combining deterministic and stochastic approaches using artificial intelligence.
   The research will be carried out by a team with many years of experience in this field and in collaboration with teams from Austria, USA, Poland and India [3], [4]. We are expecting research support mainly from national projects and internships at the workplaces of the above-mentioned teams.

   [1] T. Liu, K. Guan, D. He, P. T. Mathiopoulos, K. Yu, Z. Zhong, and M. Guizani, “6g integrated sensing and communications channel modeling: Challenges and opportunities,” IEEE Vehicular Technology Magazine, vol. 19, no. 2, pp. 31–40, 2024.
   [2] Z. Wei, J. Jia, Y. Niu, L. Wang, H. Wu, H. Yang, and Z. Feng, “Integrated sensing and communication channel modeling: A survey,” IEEE Internet of Things Journal, pp. 1–14, 2024.
   [3] A. F. Molisch, C. F. Mecklenbr¨auker, T. Zemen, A. Prokes, M. Hofer, F. Pasic, and H. Ham-moud, “Millimeter-wave v2x channel measurements in urban environments,” IEEE Open Journal of Vehicular Technology, vol. 6, pp. 520–541, 2025.

   [4] Hammoud, J. M. Kelner, C. Zi´olkowski, T. Zemen, C. Mecklenbr¨auker, and A. Prokes, “Characterizing the 80 ghz channel in static scenarios: Diffuse reflection, scattering, and transmission through trees under varying weather conditions,” IEEE Access, vol. 12, pp. 144 738–144 749, 2024.

   Tutor: Prokeš Aleš, prof. Ing., Ph.D.

4. Novel analog blocks, concepts and methods for sensing and processing of electrical and nonelectrical quantities

   The integrated circuits are very important for processing of signals from sensors and sensor readouts as a part of modern physical layer of communication systems [1], [2]. They offer significant minimization of system area and low power consumption. Therefore, these concepts are highly useful for biomedical applications (blood analysis – presence of various chemicals, bio-impedances measurement and evaluation, etc. [3], [4]), in mechanics (distance influences capacity) [5], etc. This topic includes study of utilization of discrete of-the-shelf as well as integrated active building cells and blocks (amplifiers, converters, generators, flip-flop circuits, etc.) and study of features of currently available types of sensors for various physical quantities. The recommendations, requirements, models, methodologies and specific solutions for various specific active sensor readouts and processing of signals are expected to be formulated for proposals of novel and advanced systems. General goals of this work can be found in: 1) proposal of novel analog blocks (discrete as well as integrated) for signal processing, 2) design of novel system on chip for sensing purposes, 3) proposal of methods for advanced and improved analog signal processing (including active elements, blocks and parts of system), 4) advanced integer- and fractional-order modeling of sensing systems (and features of sensed subjects/materials/tissues/liquids), and corresponding tasks. The initial state of work concentrates on review of state of the art in discussed areas and results achieved at the workplace. It allows to find the most suitable specific topic (methodology, verification and measurement, modeling, discrete/integrated analog/mixed low-power or complex systems design) fitting to interests of candidate. These activities expect involvement in experimental work (in frame of projects of basic research – cooperation with research team including foreign experts) on design and implementation of integer-order as well as fractional-order circuits [4], modules (sensing readouts) [5] and components in discrete or integrated form and writing and dissemination of publications. This specialization offers significant enhancement of skills and competences in work with modern software tools (PSpice, Cadence Virtuoso/Spectre) of analog/mixed design approaches and further experience in detailed principles of advanced circuit solutions including cooperation on design of application specific integrated circuit. References [1] R. Sotner, J. Jerabek, L. Polak, J. Petrzela, W. Jaikla and S. Tuntrakool, “Illuminance Sensing in Agriculture Applications Based on Infra-Red Short-Range Compact Transmitter Using 0.35 um CMOS Active Device.” IEEE Access, vol. 8, pp. 18149-18161, 2020, doi: 10.1109/ACCESS.2020.2966752 [2] R. Sotner, L. Polak, J. Jerabek, “Low-cost remote distance and height sensing analog device for laboratory agriculture environments.” Measurement Science and Technology, online first, 2022, doi: 10.1088/1361-6501/ac543c [3] C. Vastarouchas, C.Psychalinos, A.S. Elwakil, A.A.Al-Ali, “Novel Two-Measurements-Only Cole-Cole Bio-Impedance Parameters Extraction Technique.” Measurement, vol. 131, pp. 394–399, 2019. doi: 10.1016/j.measurement.2018.09.008 [4] S. Kapoulea, C. Psychalinos, A. S. Elwakil, “Realization of Cole-Davidson function-based impedance models: Application on Plant Tissues.” Fractal and Fractional Journal, vol. 4, 54, 2020. doi: 10.3390/fractalfract4040054 [5] L. Polak, R. Sotner, J. Petrzela, J. Jerabek, “CMOS Current Feedback Operational Amplifier-Based Relaxation Generator for Capacity to Voltage Sensor Interface.” Sensors, vol. 18, 4488, 2018. doi: 10.3390/s18124488

   Tutor: Šotner Roman, doc. Ing., Ph.D.

5. Optical waveforms for satellite links

   Free-space optical communication enables secure and high-throughput satellite links, used within the industry in operational and planned satellite constellations. At the same time, the optical waveforms for the atmospheric and free-space links remain a central topic of research. Coherent optical communications increase optical signal-to-noise ratio compared to non-coherent links whilst opening up the design space for digital signal processing techniques and higher modulation formats. In addition, more efficient channel pre- and post-compensation schemes are developed allowing for a further increase in throughput and spectral efficiency. The thesis concentrates in the initial part on state-of-the-art review and proposes concepts for efficient optical waveforms, which are experimentally verified and discussed within the context of optical satellite networks. The aim is to define most suitable methodology for trade-off between the existing (heritage) and novel modulation, coding and on-board signal processing techniques to address topics of interoperability with other applications and systems, scalability to future needs as well as system complexity. It is therefore essential to well define the use case of the study. The core part of the thesis should focus on validation and verification of the proposed technique(s) by means of analysis and tests. The experimental verification needs to consider realistic environmental effects such as (in minimum) atmospheric disturbances, Doppler effect and rate and radiation. Finally, the system and payload integration of the technique shall be considered to derive a complete (sub)system design. References: [1] Poliak, J. et al., Demonstration of 1.72 Tbit/s optical data transmission under worst-case turbulence conditions for ground-to-geostationary satellite communications, IEEE COMMUNICATIONS LETTERS, VOL. 22, NO. 9, 1818-1821, 2018. [2] Conroy, P. et al., Demonstration of 40 GBaud intradyne transmission through worst-case atmospheric turbulence conditions for geostationary satellite uplink, Appl. Opt., OSA, 2018, 57, 5095-5101. [3] La Torre, Gianluca et al. (2024) A spectral shaping approach to generate power vectors for optical ground-to-space links. In: Environmental Effects on Light Propagation and Adaptive Systems VII 2024, 13194. [4] Surof, Janis, Poliak, Juraj (2022) Precise Time Transfer for High Throughput Satellite Communications Links In: 56th Annual Precise Time and Time Interval Systems and Applications Meeting, PTTI 2025.

   Tutor: Hudcová Lucie, doc. Ing., Ph.D.

6. Optimization of Accuracy and Robustness of Hybrid Localization Systems for Indoor and Outdoor Environments

   Precise localization is a key component of modern applications in industry, logistics, autonomous systems, and the Internet of Things (IoT). While outdoor localization systems utilizing LPWAN technologies provide wide-area coverage with low energy consumption [1], their accuracy is limited [2]. Conversely, indoor localization systems (RTLS), typically based on UWB technology [3], offer high accuracy but with a restricted range. The aim of this project is to optimize the accuracy and robustness of hybrid localization systems [4] that combine these technologies to enable seamless coverage in both indoor and outdoor environments while maintaining high energy efficiency.

   The research will focus on two key areas: improving accuracy and reducing errors caused by signal propagation, and enhancing resilience against security threats. In the first area, a systematic analysis of factors affecting localization accuracy will be conducted, including multipath effects, signal absorption and scattering in various environments, and the optimization of data fusion across different frequency bands in a hybrid system. Furthermore, methods for adaptive error correction and algorithms for improving measurement accuracy through the combination of localization techniques will be proposed.

   The second area will address the robustness of localization systems against interference, spoofing, and jamming. The vulnerabilities of hybrid systems will be analyzed, and methods for attack detection and mitigation will be developed, including signal redundancy, appropriate encryption, spectral analysis, and cross-verification from multiple independent sources. Emphasis will be placed on utilizing standardized methods for secure localization, such as those defined in IEEE 802.15.4z. The research will integrate theoretical modeling with experimental validation in real-world conditions.

   [1] A. Povalac, J. Kral, H. Arthaber, O. Kolar and M. Novak, "Exploring LoRaWAN Traffic: In-Depth Analysis of IoT Network Communications," in Sensors 2023, 23, 7333. https://doi.org/10.3390/s23177333

   [2] Y. Li et al., "Toward Location-Enabled IoT (LE-IoT): IoT Positioning Techniques, Error Sources, and Error Mitigation," in IEEE Internet of Things Journal, vol. 8, no. 6, pp. 4035-4062, 15 March15, 2021, doi: 10.1109/JIOT.2020.3019199.

   [3] S. Gezici et al., "Localization via ultra-wideband radios: a look at positioning aspects for future sensor networks," in IEEE Signal Processing Magazine, vol. 22, no. 4, pp. 70-84, July 2005, doi: 10.1109/MSP.2005.1458289.

   [4] F. Bonafini et al., "Evaluating indoor and outdoor localization services for LoRaWAN in Smart City applications," 2019 II Workshop on Metrology for Industry 4.0 and IoT (MetroInd4.0&IoT), Naples, Italy, 2019, pp. 300-305, doi: 10.1109/METROI4.2019.8792901.

   Tutor: Povalač Aleš, doc. Ing., Ph.D.

7. Security risks of 6G and 5G NTN Radio Access Networks

   In the coming years, the radio access networks are expected to evolve towards sixth-generation systems, while massive expansion into the area of so-called non-terrestrial networks is also foreseen. This expected evolution brings with it not only new signal processing concepts (e.g. OTFS techniques) and new applications (e.g. integration of simultaneous communication and sensing), but also new security threats.

   The goal of the PhD study is to analyze the security risks of these emerging systems from a physical layer perspective (spoofing of messages, privacy leakage, eavesdropping, etc.), and then to design, implement and verify selected countermeasures.

   In the framework of the study, we expect the student to be involved in international COST action 6G-PHYSEC, the national INTER-COST project, eventually ESA projects. An internship at one of the collaborating foreign institutes is also envisaged.

   [1] R. Zavorka, R. Marsalek, J. Vychodil, E. Zöchmann, G. Ghiaasi and J. Blumenstein, Deep Neural Network-Based Human Activity Classifier in 60 GHz WLAN Channels, 2022 IEEE Globecom Workshops (GC Wkshps), Rio de Janeiro, Brazil, 2022, pp. 1304-1309, doi: 10.1109/GCWkshps56602.2022.10008586.

   [2] Harvanek M, Bolcek J, Kufa J, Polak L, Simka M, Marsalek R. Survey on 5G Physical Layer Security Threats and Countermeasures. Sensors. 2024; 24(17):5523. https://doi.org/10.3390/s24175523

   Tutor: Maršálek Roman, prof. Ing., Ph.D.

8. Space compression for guided wave structures at microwave frequencies

   Space compression involves a reduction of free-space distances between optical elements by a thin device/material called a spaceplate [1], [2]. Recently, it gained importance due to novel approaches in the emerging field of non-local metamaterials. The issue of size reduction becomes prominent in quasi-optical systems common to the terahertz and microwave frequency region where the physical size of the elements can be limiting factor in the design process. This project is focused on the research of the space compression for guided wave structures. The problem will be studied on two-dimensional structures such as dielectric slabs, parallel plate waveguide or substrate integrated waveguides. The main attention will be concentrated on the investigation of periodic media and their application to guided wave structures to reach desired space compression. The special attention should be also paid to manufacturing and experimental characterization of the developed structures. References: [1] RESHEF, O., et al., An optic to replace space and its application towards ultra-thin imaging systems, Nature Communication, 2021, vol. 12, art. no. 3512. [2] MRNKA, M., et al., Space squeezing optics: Performance limits and implementation at microwave frequencies. APL Photonics, 2022, vol. 7, no. 7, p. 1-7.

   Tutor: Láčík Jaroslav, doc. Ing., Ph.D.

9. Wireless Communication using Artificial Intelligence

   multiple wireless systems utilize the same RF band is expected to increase. This phenomenon, known as the coexistence of wireless communication systems, can have varying degrees of impact. In some cases, it may lead to critical issues, such as partial or complete loss of wireless services provided by communication systems, while in others, the systems can coexist without significant performance degradation [1]-[5]. Contemporary research [4], [5] suggests that machine learning (ML) and deep learning (DL) technologies could serve as effective tools for enhancing the reliability and efficiency of wireless communication systems, particularly in situations influenced by diverse transmission conditions. This work focuses on developing advanced machine learning (ML) and deep learning (DL) algorithms for classifying coexistence scenarios between different wireless communication systems based on RF signals. Initially, it is essential to define and measure various transmission scenarios for mobile and wireless communication systems operating in licensed and unlicensed RF bands. As part of these measurements, key environmental factors, such as multipath propagation, will be investigated, as they can significantly impact the quality of radio connections in wireless communications. Attention will also be given to studying parameters with the highest influence on the interfering signal's characteristics, such as idle signals and types of digital modulation. These parameters enable ML and DL architectures to learn more features from the data [4]. Subsequently, the research will focus on realizing, validating, and optimizing artificial intelligence models and algorithms (ML and DL) to enhance the efficiency and reliability of wireless communication links under different transmission conditions. The ML/DL models created will be trained and validated using data obtained from real-world, long-term measurement campaigns. The ML/DL algorithms must strike a balance between complexity, accuracy, and efficiency. They are expected to be implemented in Python or MATLAB using available libraries (such as PyTorch, Keras, TensorFlow) and toolboxes (such as Deep Learning Toolbox), respectively. Ultimately, the dataset obtained from long-term measurement campaigns, along with the ML/DL models and algorithms, will be made freely available to the wider scientific community. This approach ensures not only the reproducibility of the achieved results but also serves as the foundation for further research and development in the field of wireless communications. References [1] A. M. Voicu, L. Simić and M. Petrova, "Survey of Spectrum Sharing for Inter-Technology Coexistence," IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1112-1144, Secondquarter 2019, DOI: 10.1109/COMST.2018.2882308 [2] G. H. Derévianckine, A. Guitton, O. Iova, B. Ning, and F. Valois, „Hate or Love in the 2.4 GHz ISM band: The Story of LoRa and IEEE 802.11g,“ 2024. First Online: https://hal.science/hal-04815177v1/file/_Gwendoline___TIOT_Interference_LoRa_WiFi.pdf [3] L. Polak and J. Milos, “ Performance analysis of LoRa in the 2.4 GHz ISM band: coexistence issues with Wi-Fi,” Telecommunication Systems, vol. 74, no. 3, pp. 299-309, July 2020. DOI: 10.1007/s11235-020-00658-w [4] Y. Shi, K. Davaslioglu, Y. E. Sagduyu, W. C. Headley, M. Fowler and G. Green, "Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments," In Proc of. Int. Symp. DySPAN, Nov. 2019, pp. 1-10, DOI: 10.1109/DySPAN.2019.8935684. [5] S. Szott et al., "Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance With Machine Learning," in IEEE Communications Surveys & Tutorials, vol. 24, no. 3, pp. 1843-1893, thirdquarter 2022, doi: 10.1109/COMST.2022.3179242.

   Tutor: Polák Ladislav, doc. Ing., Ph.D.