Nadeem Rather
Runner-Up
What encouraged you to submit your application to the 2023 Postgraduate Research Publication of the Year?
I have always been motivated to submit a publication to the Postgraduate Research Publication of the Year due to the prestige associated with the recognition and the opportunity to showcase the significant findings from my research. I believe this provides a chance to share the findings with the wider Tyndall community, which can lead to collaborations or the generation of new ideas. The support from my supervisors, who believed in the impact of my work, also encouraged me to make the submission.
What inspired you to choose the subject of your paper?
I have always been fascinated by electromagnetic (EM) waves. Antennas enable us to generate these EM radio waves at desired frequencies, which propagate through space. The idea of transmitting energy wirelessly and how it is used in our daily lives and the connectivity it enables, fascinates me. During my PhD, I had the opportunity to work on antenna devices that can re-radiate energy back to the reader antenna, containing information. I wanted to explore the idea of using Artificial Intelligence (AI), a powerful emerging tool, to enhance this process. This led me to explore the integration of EM and AI, forming the basis of my research questions and paper.
What’s your paper about and how did you prepare for it? What role did research excellence play in your approach?
My paper, titled “Deep-Learning-Assisted Robust Detection Techniques for a Chipless RFID Sensor Tag,” presents a new approach for robust reading of identification (ID) and sensor data from chipless radio frequency ID (CRFID) sensor tags. For the first time, machine-learning (ML) and deep-learning (DL) regression modelling techniques were applied to a dataset of measured radar cross-section (RCS) data derived from large-scale robotic measurements of custom-designed, 3-bit CRFID sensor tags. The research paper explores AI methods to accurately detect information encoded within an EM signature re-radiated from CRFID tags. These tags encode binary data and sensing information, which is decoded by the reader. Due to the absence of battery and electronic components, these tags and their associated EM signatures are prone to noise and variations due to varying read ranges and physical tag deformations. To develop these tags for real-world scenarios, we developed AI models that can learn from various patterns, such as how the signature appears when the tag is bent on a cylinder or a corner. This enabled the AI models to recognize the correct information from varying surface deformation states.
The selection for Research Publication of the Year is extremely competitive. What is your advice for those aspiring for nomination next year?
My advice is to submit your work with confidence. Be proud of every aspect of your paper. It boosts your confidence and motivates you to make significant advancements in your research. Thoroughly understand and present your findings, ensuring your research is original and impactful.
What is the single most significant support Tyndall has been able to offer you in achieving your research goals?
Tyndall has provided a platform for me to achieve things I have always dreamed of. The most significant support has been the access to state-of-the-art laboratories and equipment, which was important to conduct my experiments. The expertise and guidance from my supervisors were invaluable, offering me insights and directions that significantly enhanced the quality of my research. I am thankful for the opportunity that Tyndall provided, helping me realise my potential. I tried to do my best during my PhD, and I look forward to continuing this effort. I am proud to have pursued my PhD at Tyndall and am grateful for the numerous opportunities it has provided, enabling me to grow both professionally and personally.
Nadeem Rather, Roy B. V. B. Simorangkir, John L. Buckley, Brendan O’Flynn, and Salvatore Tedesco, ‘Deep-Learning-Assisted Robust Detection Techniques for a Chipless RFID Sensor Tag’, IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-10, 2024, Art no. 2502710.