CSN group members Professor Mark Beach and Dr Tommaso Cappello are currently in Denver, Colorado from 19^th to 24^th June to spread the word about the University of Bristol’s research capabilities in the field of RF and microwaves at the IEEE’s premiere conference, the International Microwave Symposium (IMS) 2022.

Two technical papers will be presented (We2C-3 and We1C-3) including one on the SWAN Prosperity Partnership’s RF fingerprinting work, as detailed below. They will also be presenting one workshop paper (WMG-6) and staffing a University of Bristol Booth (#12078).

Take a look at the full technical agenda here: https://ims-ieee.org/technical-program

The CSN booth will include a display of the following posters:

• Frequency Division Duplexing by Agile Waveform Cancellation (Leo Laughlin et al)
• Power Efficient DPD Linearization (Gautam Jindal et al)
• Detection of Cyber Attack on Transmitters Featuring Predistortion (Gavin Watkins)
• Multi-bit Digital Power Amplifier (Jiteng Ma et al)
• Modular Design and Characterization of a Reconfigurable Sequential Power Amplifier (Sarmad Ozan et al)
• Dynamic Spectrum Access (DSA) to Supplement Licensed Spectrum (Simon Wilson et al)
• High Dynamic Range Low Noise Amplifiers (Samad Ozan et al)
• LoRa: Reported Signal Parameters to Aid Rogue Sensor Detection (Jack Stride et al)

RF Fingerprinting Work to be Presented

Dr Manish Nair’s paper on “RF Fingerprinting of LoRa Transmitters Using Machine Learning with Self-Organizing Maps for Cyber Intrusion Detection” will be presented by Mark Beach in the We2C on AI/ML for RF and mmWave Applications session on Wednesday 22^nd June. The paper was co-authored by Tommaso Cappello, Shuping Dang, Vaia Kalokidou and Mark Beach and arises from the SWAN Prosperity Partnership’s programme of research.

The paper abstract can be found below:

In this paper, a novel unsupervised machine learning (ML) algorithm is presented for the expeditious RF fingerprinting of LoRa modulated chirps. Identification based on received signal strength indicator (RSSI) alone is unlikely to yield a robust means for sensor authentication within critical infrastructure deployment. Here, an unsupervised ML algorithm is used to rapidly train an artificial neural network (ANN) matrix creating self-organizing maps (SOMs) for each authentic transmitter and a potential rogue node. A general classifier can be trained on the SOMs for precisely profiling each transmitter as either genuine or rogue. By means of experimental validation, this methodology demonstrated cent-percent success in recognizing each transmitter, either being a real or a rogue node.

‌

A key focus of Manish’s work has been conducting state-of-the-art research in frequency agile, blocker resilient and multi-band radio frequency (RF) receiver front-end analogue circuit technology, focussing on sub-6GHz applications embracing Secure by Design methodologies.

Beyond his personal research aims, Manish supports various teaching and research activities within the University. These include multiple final year MSc projects, undergraduate students groups undertaking their research projects as well as teaching assistant and lecturing work.

The CSN Group is part of the Smart Internet Lab – a renowned research centre for Information and Communications Technology (ICT).

‌