Space AI Seminar Series
September 2024 to December 2024, Bradford-Renduchintala Centre for Space AI, University of Bradford
The invited speakers are the academic experts in the following areas:
- Wireless communications
- Modern Network Technologies
- Artificial Intelligence & Machine Learning
- Digital Signal Processing
- Cybersecurity
About the Space AI Research Seminar Series
Organized by the Bradford-Renduchintala Centre for Space AI, this seminar series brings together experts and researchers to explore collaborative opportunities, share their latest findings, and inspire innovative ideas in Space AI and related fields. Our aim is to organize a series of four different research seminars in hybrid over four months from September to December 2024. The expert speakers will deliver their talks on their particular area of expertise.
Seminar 2: Phase Shift Optimisation for Reconfigurable Intelligent Surface-based 6G Networks
| Time | 12:00 - 13:00 PM on Monday 28/10/2024 |
| Location | Horton D5.09, University of Bradford |
| Abstract | The phase shift or reflection matrix configuration has a significant impact on the system performance of Reconfigurable Intelligent Surface (RIS)-aided wireless networks. This presentation will delve into different techniques for the optimization of the RIS phase shifts – from analytical formulations to heuristic methods and machine learning-driven algorithms. Network performance results for RIS-aided 6G networks based on Fourier Transform, Cosine Similarity of the Cascade Channels and random phase shifts will be presented, using different network configurations, system models and architectures, performance metrics and application use cases. Performance comparison of the results with the mathematical upper bound will be evaluated. The talk will give different insights on the optimization of RIS-aided networks for 6G and beyond. |
| Speaker | Dr Sherif Busari is currently a Research Fellow at the Bradord-Renduchintala Centre for Space AI, University of Bradford, UK. He received his B.Eng. and M.Eng. degrees in electrical and electronic engineering from the Federal University of Technology Akure, Nigeria, in 2011 and 2015, respectively. He received his Ph.D. in telecommunications in 2020 under the joint doctoral program in telecommunications of the Universities of Minho, Aveiro, and Porto (MAP-tele), Portugal. He was formerly a Lecturer at the Federal University of Technology Akure, Nigeria, a postdoctoral researcher at the Instituto de Telecomunicações, Portugal and the University of Algarve, Portugal. His research interests include millimeter-wave and THz communications, massive MIMO, reconfigurable intelligent surfaces, beamforming and machine learning for 5G/6G networks and beyond. |
Seminar 1: Computational Intelligence for Digital Signal Processing: Theory and Applications
| Time | 12:00 - 13:00 PM on Monday 30/09/2024 |
| Location | Horton D5.09, University of Bradford |
| Abstract | Research in Digital Signal Processing has already shifted towards data-driven models. However, several DSP problems still need to be addressed using analytical models. Therefore, Computational Intelligence, a broad umbrella that encompasses machine learning, fuzzy sets and systems, and conventional analytic models can be leveraged as an efficient tool to tackle several DSP problems, where data-driven models are not sufficient to provide an interpretable/explainable solution. Thus, in this talk, some examples of computational intelligence models are presented, where it is shown that the theory provides a robust solution to the problems addressed, namely:
As case studies, the results of application of the developed models on some real-life problems are presented, such as: a) anomalous sound detection for car traffic surveillance, b) machine fault detection based on audio signals, and c) speech & music signal reconstruction and enhancement. Further applications can be extended to other types of signals, including space applications, where the presented models may be applied, such as outlier detection, noise reduction, source separation, compressive sensing, … etc |
| Speaker | Dr Zied Mnasri received his BEng and MEng degrees in electrical and computer engineering from the University of Tunis El Manar. After several years working in industry, he completed his PhD thesis in 2011 at the same university when he was appointed as an assistant professor at the National School of Engineering in Tunisia. From 2015 to 2018, he has led a joint Tunisian-French research project in collaboration with the University of Lorraine, France, to create an integrated system for “Arabic Text-to-Speech using Deep Learning”. Between 2018 and 2021, he was an adjunct professor at the University of Genoa, Italy, then, from 2021 to 2024 he was assistant professor at the University of Naples “L'Orientale”, where he has been working on several signal and image processing projects, such as “Multimodal Emotion Recognition”, “Anomalous Sound Detection for Audio Surveillance” and “Archaeological Artefact Detection and Classification”. Recently, in March 2024, he joined the University of Bradford, Faculty of Engineering and Digital Technology, as assistant professor in computer science. As part of these teaching and research activities, Zied has supervised several doctoral, master's and graduate students and had more than 50 publications. He is currently guest associate editor of the journal “Frontiers in Digital Health” and has been a member of the technical programme committee, co-organizer of special sessions and guest speaker at several conferences and events. He is also a member of IEEE and EURASIP (European Association of Signal Processing). |
Contact
Dr Vuong Mai
Assistant Professor
[email protected]
Location
Horton Building, D5.09
University of Bradford
Bradford
West Yorkshire
BD7 1DP
UK