Robust Chipless RFID Detection Using Complex Natural Frequency Along With the k-Nearest Neighbor Algorithm

Abstract

This paper proposes a detection technique for the chipless RFID system. In the proposed technique, the experiments for measuring the scattering responses of all possible tags were conducted first in a free-space anechoic chamber in order to avoid the effect of unwanted signals due to the environment. The responses of all possible tags were exploited in order to extract poles, including natural frequencies and damping factors, by using the short-time matrix pencil method. All extracted poles successively chosen from the late-time portions were exploited to create the decision boundary by using the k-nearest neighbor algorithm. In order to validate the robustness of the proposed detection technique, experiments with the chipless RFID system with tags attached to containers, i.e. parcel and plastic boxes, were conducted. Poles extracted from the response of the tag attached to a container were fed to the decision boundary for ID detection. The poles that had fallen into the region labeled as logic "1" were detected as logic "1," and vice versa. The experiment results showed that the attachment of the tags to the containers caused a change in the poles. The conventional technique using only natural frequencies has exhibited poor performance regarding tag ID detection. On the other hand, the proposed detection technique achieved a 100% detection rate, although the extracted poles used to detect the bit logic were disturbed by the container. The experimental results confirm the superiority of the proposed system over conventional chipless RFID detection. Moreover, the proposed technique can be considered a robust detection technique.

Complex Natural Resonance-Based Chipless RFID Multi-Tag Detection Using One-Dimensional Convolutional Neural Networks

“…A chipless RFID tag was designed and implemented solely for the purpose of demonstrating the proposed technique. The tag used in this study consists of a rectangular metallic patch loaded with three slot resonators, following the designs outlined in [13] and [25]. It is important to note that the proposed technique can be applied to other tags designed based on resonance frequency, where the tag's unique identifier is encoded within its resonant frequency, as seen in examples in [26]- [27].…”

“…parameters, including L1, L2, L3, L4, w, and s, were optimized to achieve three distinct resonant frequencies, namely 3.928, 4.896, and 6.424 GHz. These resonant frequencies were illustrated by notch frequencies in the S21, corresponding to those in [13]. The size values for L1, L2, L3, L4, w, and s, were set at 12, 10.5, 9, 7.5, 0.75, and 0.4 mm, respectively.…”

“…Antenna calibration was carried out as the initial step in order to mitigate the effects due to antenna mutual coupling and unflat antenna response. Following the procedure in [13], a large metal plate with dimensions of 50 cm × 50 cm served as the reference Hplate(ω). This plate was positioned in the same location as the tag, allowing the measurement of the transfer function of the reference Hplate(ω).…”

“…However, the STMPM does have limitations in terms of fixed resolution in time and frequency. In order to address these limitations and to further boost its performance, we have proposed innovative improvements, such as incorporating a knearest neighbor (k-NN) algorithm to establish decision boundaries and to facilitate the decoding of tag responses [13]. These advancements show great potential in elevating the capabilities of chipless RFID systems and advancing their application in diverse scenarios.…”

A Review of Chipless RFID Measurement Methods, Response Detection Approaches, and Decoding Techniques

“…One of the limitations of the STMPM, though, is that it has fixed resolution in time and frequency [290,292,304,334]. Improvements to the STMPM method have also been proposed, including a k-nearest neighbor algorithm in order to create decision boundaries and decode the tag response [220].…”