Evaluation of a U-Shaped Convolutional Neural Network for RCS based Chipless RFID Systems

Rather, Nadeem; Simorangkir, Roy B. V. B.; Buckley, John L.; O’Flynn, Brendan; Tedesco, Salvatore

Abstract

In this paper, for the first time, a one-dimensional convolutional neural network using a U-shaped architecture is evaluated in the context of radar cross section (RCS) based chipless RFID (CRFID) systems. A 3-bit CRFID tag is utilised to create eight discernible RCS signatures representing identification numbers. A dataset of 9,600 measured RCS signatures was utilised for training, validating, and testing the model. The dataset was collected by placing the tag on varying surface shapes, orientations, and read ranges to enable robust detection. The root mean square error (RMSE) metric was used to assess the model’s performance. The achieved RMSE was 0.11 (1.5%). The low RMSE score demonstrates the effectiveness that this type of architecture has in accurately detecting and generalizing the encoded information from the RCS signatures.

Citation

Rather, N., Simorangkir, R. B. V. B., Buckley, J. L., O’Flynn, B., & Tedesco, S. (2023, September). Evaluation of a U-Shaped Convolutional Neural Network for RCS based Chipless RFID Systems. Presented at 2023 IEEE International Conference on RFID Technology and Applications (RFID-TA), Aveiro, Portugal

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2023 IEEE International Conference on RFID Technology and Applications (RFID-TA)
• Start Date: Sep 4, 2023
• End Date: Sep 6, 2023
• Acceptance Date: Sep 4, 2023
• Online Publication Date: Oct 27, 2023
• Publication Date: Oct 27, 2023
• Deposit Date: May 7, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 2377-018X
• Book Title: 2023 IEEE 13th International Conference on RFID Technology and Applications (RFID-TA)
• ISBN: 9798350333541
• DOI: https://doi.org/10.1109/rfid-ta58140.2023.10290467
• Public URL: https://durham-repository.worktribe.com/output/2434191