Utilizing deep learning in chipless RFID tag detection: an investigation on high-precision mm-wave spatial tag estimation from 2D virtual imaging

Abstract

ABSTRACT Due to their high price, RFID tags are not yet widely used in applications for monitoring, tracing, and information inscribing, such as manufacturing lines, supply chains, and inventory management. The currently utilized barcode-like tracing techniques lack security, experience data limitation, are semi-automated, and are prone to external damage. Chipless RFID technology is a potential replacement, able to overcome shortcomings. However, due to the uncertainty created by the absence of a communication antenna and microchip, the detection of chipless RFID tags has a 2–5% detection error rate. The recent advancement in spatial chipless RFID technology has opened up a plethora of opportunities to use deep learning, which is becoming increasingly popular, to detect chipless RFID tags from a 2D virtual image created from the backscattered signal. In this study, we presented a comprehensive and exhaustive investigation of several deep learning techniques to improve the detection capability of deep learning-based chipless RFID tag detection. Our proposed fine-tuning methods yielded better mathematical metrics on the state-of-the-art on its original setup. A confusion matrix used to measure error rates on unseen data shows that the improved deep learning architecture we introduced works at roughly 99.99% accuracy.