IEEE RFID-TA 2026 logo
IEEE
Time (Denver) Mesa A Mesa B Mesa C Chapel

Tuesday, June 16

08:20 am-09:00 am Conference Opening
09:00 am-10:00 am Tu1: Tutorial 1   NRDZ Workshop 1
10:00 am-10:30 am     Posters  
10:30 am-12:10 pm Tu2: Tutorial 2   NRDZ Workshop 2
12:10 pm-01:30 pm     Posters  
01:30 pm-03:10 pm Tu3: Tutorial 3   NRDZ Workshop 3
03:10 pm-03:40 pm     Posters  
03:40 pm-05:20 pm Tu4: Tutorial 4   NRDZ Workshop 4
05:20 pm-06:00 pm NextNAV All Hands Meeting    
06:00 pm-07:30 pm Welcome Reception

Wednesday, June 17

08:20 am-10:00 am W_P_1: Plenary Keynotes 1    
10:30 am-12:10 pm W_A_1: General Track W_C_1: Special Session: Location-Aware Empowered Systems: Wireless Technologies and New Concepts for Location Sensing, Motion Capture, and Pattern Recognition  
01:30 pm-03:10 pm Workshops 1    
03:40 pm-04:30 pm Workshops 2    
04:30 pm-05:10 pm Plenary Patron Talks    
05:20 pm-06:20 pm W_A_2: Special Session: Radio Frequency Identification (RFID) for High-Consequence Environments 1    
07:00 pm-09:30 pm Networking Dinner

Thursday, June 18

08:20 am-10:00 am T_P_1: Plenary Keynotes 2    
10:30 am-12:10 pm T_A_1: Special Session: Wide-Spectrum and Digital-Twin-Enabled RFID Sensing: From Chirp-Modulated Backscatter to Cyber-Physical Intelligence T_C_1: Special Session: Radio Frequency Identification (RFID) for High-Consequence Environments  
01:30 pm-03:10 pm T_A_2: Special Session: Beyond Conventional Backscatter Communications T_B_3: Special Session: AI-Powered RFID and IoT Systems for Edge Intelligence and the Internet of Bodies  
03:40 pm-05:20 pm T_A_3: Special Session: RFID enabled sensors: From Integrated circuit (IC) design to system implementation T_C_3: Special Session: Sustainable Pathways in Electronics, IoT and RFID: Materials, Devices, Systems, and Beyond  
05:20 pm-06:00 pm Awards Announcement    
06:00 pm-06:45 pm Workshop 3 - RFID Jepardy    

Tuesday, June 16

Tuesday, June 16 8:20 - 9:00

Conference Opening

Room: Mesa A, Mesa B
8:20 Message from the CRFID President
Luca Catarinucci (University of Salento, Italy)

Welcome to IEEE RFID 2026

Tuesday, June 16 9:00 - 10:00

NRDZ Workshop 1

Room: Chapel

Tu1: Tutorial 1

Room: Mesa A, Mesa B
9:00 The RF in RFID
Daniel Dobkin (Enigmatics, USA)

Radio Frequency Identification is, unsurprisingly, a radio technology. To understand it you need to understand what radio waves are, and how they are generated, propagate, and get detected. In this tutorial we review when radio can be more useful than light for identifying objects. We provide a simplified view of radio and antennas based on vector potentials and current sources to gain an intuitive understanding of what an antenna does and how it works, leading to the Friis equation for quantitation of transmitted and received signals. We examine why you need to modulate a signal, why specialized modulations are useful in passive RFID, and what you lose as a consequence. We introduce the structure of packets used in UHF RFID and Bluetooth Low Energy signaling, followed by a brief examination of how the radio medium is allocated for RFID tags and readers. We then examine the closely-related task of finding something after you've identified it, and how real environments complicate this problem with diffraction, reflection, absorption, and consequent multipath propagation effects.

Tuesday, June 16 10:00 - 10:30

Posters

Room: Mesa C
BeeSMART: RFID-Enabled Edge System for Context-Aware Beehive Monitoring and Control
Aiden Zhao (Louisiana State University & Caddo Parish Magnet High School, USA)

BeeSMART is a beehive monitoring system that integrates edge nodes with passive and semi-passive UHF RFID sensor tags for scalable, low-power, low-cost sensing across hive clusters. RFID-based temperature, humidity, and hive ID data provide distributed, cluster-level environmental awareness that enables context-aware decision making and enhances local swarm and mite detection. Pilot results show that cluster-level RFID sensing combined with edge-based control stabilizes hive conditions and supports targeted interventions.

RFIDSentinel: Differentially Private Federated Learning over Synthesized Backscatter Fingerprints for Real-Time Multi-Attack Detection in Dense UHF RFID Deployments
Vihaan Sawardekar (Marquette High School, USA)

The widespread deployment of passive Ultra-High-Frequency (UHF) Radio Frequency Identification (RFID) systems across pharmaceutical serialization, retail logistics, cold-chain monitoring, and critical asset tracking has introduced a large and insufficiently secured attack surface. The stateless architecture and ultra-constrained power budget (1-8 μW) of Class-1 Generation-2 (EPC Gen2) transponders render them inherently vulnerable to a range of adversarial exploits, including tag cloning, relay attacks, inventory replay, phantom tag injection, and Denial-of-Interrogation (DoI). Conventional cryptographic countermeasures-such as challenge-response authentication, hash-locking, and pseudonym randomization-remain impractical under the strict energy and computational limitations imposed by the ISO/IEC 18000-63 standard. Physical-layer security (PLS) techniques, which exploit stochastic variations in backscatter modulation as device-specific fingerprints, provide a promising alternative; however, existing approaches suffer from degraded performance in dense multi-reader environments, sensitivity to inter-session channel variability, and reliance on centralized aggregation of raw in-phase/quadrature (I/Q) data, introducing both privacy and scalability challenges.

This research project presents a software-defined federated learning framework with differential privacy for scalable physical-layer security in UHF RFID systems. The proposed approach eliminates dependence on physical RFID hardware throughout development, training, and evaluation, while addressing the limitations of prior PLS methods through three tightly integrated components: a stochastic backscatter emulation engine, a privacy-preserving federated learning protocol, and a multi-task deep neural architecture.

First, a high-fidelity baseband emulation engine is developed to synthesize EPC Gen2 interrogation sessions in accordance with ISO/IEC 18000-63 timing specifications. The received signal from each virtual tag is modeled as a stochastic convolutional process incorporating a complex-valued backscatter coefficient drawn from IC-family-specific Nakagami-m fading distributions, a Miller-4 subcarrier waveform (Tari = 6.25 μs), a simulated reader antenna impulse response, and additive complex Gaussian noise. The emulator captures variability across multiple commercial integrated circuit families and generates a large-scale dataset comprising 840,000 interrogation sessions across 12,000 virtual tag identities, partitioned into training, validation, and test sets. All data are represented as complex-valued time-series signals, enabling fully reproducible experimentation without reliance on physical readers, antennas, or tags.

Second, to reflect realistic multi-site deployments with strict data locality constraints, a distributed learning framework based on synchronous Federated Averaging (FedAvg) is implemented across 48 simulated edge-reader clients. To ensure formal privacy guarantees, Rényi Differential Privacy (RDP) is incorporated through per-sample gradient clipping (C = 1.0) and calibrated Gaussian noise injection (σ = 0.8), achieving (ε = 2.3, δ = 10⁻⁵)-differential privacy. Each client performs multiple local training epochs per communication round over 300 global rounds, enabling collaborative model optimization while ensuring that raw I/Q fingerprint data remain confined to local partitions. Only privacy-preserving gradient updates are exchanged and aggregated.

Third, a multi-task neural architecture is designed to jointly perform tag identity verification and anomaly detection. The model processes 256-sample I/Q windows corresponding to complete EPC read cycles and employs a depthwise-separable one-dimensional convolutional encoder for hierarchical spectral-temporal feature extraction, followed by a bidirectional gated recurrent unit (GRU) to capture temporal dependencies. The shared representation is fed into two task-specific heads: a 12,000-class softmax classifier for identity recognition and a seven-class sigmoid-based detector covering cloning, relay attacks, DoI, inventory replay, phantom injection, reader impersonation, and bit-level manipulation. Joint optimization is achieved using a weighted composite loss function.

Experimental evaluation under simulated dense-reader interference conditions (up to 16 co-located readers at SNR = 3 dB) demonstrates substantial performance gains. The framework achieves a mean tag identification accuracy of 97.8% (±0.4%, 95% confidence interval), significantly outperforming non-federated deep learning and prior PLS baselines. Anomaly detection attains a macro-averaged true positive rate of 97.8% with a false positive rate of 0.41%, including 99.3% detection accuracy for tag cloning. The incorporation of differential privacy incurs only a modest accuracy reduction relative to non-private federated training, while maintaining strong formal guarantees. Simulated inference latency satisfies EPC Gen2 real-time constraints.

Overall, this research project demonstrates that robust, scalable, and privacy-preserving physical-layer security for UHF RFID systems can be achieved entirely through a software-defined paradigm, establishing a foundation for next-generation secure RFID deployments.

Real-Time Tag Localization using Augmented Reality and Neural Networks
Charles Harper Rhett (Auburn University, USA)

Introduction One of the most significant unsolved problems in the RFID industry is tag localization. That is, how can RFID tags be located quickly and reliably using novel technologies? Traditionally solving this problem has required significant time from experienced radio frequency engineers to develop complex mathematical models. Our goal has been to eliminate that overhead. We use custom neural networks to develop our models instead, trained on data generated in Augmented Reality (AR) to solve localization for modern retail antennas.

Methods When it comes to using neural networks to develop a mathematical model, the problem pivots from requiring talented engineers to requiring reliable training data. We generate this training data by using an Augmented Reality headset to associate real-world tags with their digital twins as a system for ground truth. This ground truth is then paired with a single antenna's movements and signal strength readings (RSSI) as it moves throughout a space. Using this data, we train our neural network to associate tag signal strength with tag position, which can effectively be used to localize tags in a 3-dimensional space.

Results When localizing tags, the user is given a handheld RFID reader and an augmented reality headset. They then proceed to walk around a space while the handheld reader registers tag reads to the headset. Within moments, RFID tags will begin to localize virtually into the user's display. At our current stage of research, the tags localize with an average error of less than half a meter. Discussion & Conclusion Our research is not yet conclusive, and we have many more improvements to make and tests to run. Thus far, we have tested our localization pipeline on one tag inlay type in one enclosed space. We have been careful to abstract the space from the data before processing, but additional environments and tag inlays are imperative for further verification of these techniques. Regardless, using augmented reality to associate real-world tags with their virtual equivalents shows significant promise for the future of tag localization.

Acknowledgement I am very grateful for the guiding hand of Justin Patton, Auburn University's RFID Lab director who gave me the opportunity to create this project. I am additionally thankful for the work done by Jian Zhang and Chris Turner, who inspired the idea. And finally, I would like to thank my colleagues Calvin Hirschler, Adrian Bennett, Sam Clark, and Daniel Speal for their incredible support and contributions.

Neutron Domino Integration with Arduino and RFID
Linnhtet Htoon (University of California, Los Angelos, USA); John Koltes Gatesman, Brendon Parsons, Kilkee Flynn and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Radio frequency identification (RFID) has been demonstrated as an increasingly appealing tool for inventory management across many industries. Los Alamos National Laboratory (LANL) aims to increase the efficiency of its current inventory management system by implementing RFID technology. In addition, we aim to leverage RFID infrastructure to also collect data from specific sensors. RFID is planned to be implemented in a scalable, automated manner to make the inventory process more efficient and enable enhanced monitoring capabilities. Real-time data collection is implemented using a microcontroller communicating with a sensor that can transfer sensor data to an integrated RFID chip. The goal is to minimize the size and power intake of the microcontroller. This poster describes the sensor data transfer application and the integration of sensor data transfer over RFID.

Transforming Inventory Management Through Spatial Data and Visual Feedback
Calvin Hirschler (Auburn University, USA)

Introduction RFID technology is becoming the backbone of modern retail inventory management, yet the physical act of taking inventory remains inefficient due to a lack of visual feedback. Associates typically rely on simple lists and audio cues from handheld scanners without spatial awareness of their scan coverage or accuracy, resulting in missed items and redundant labor. STAR (Scanning Tags in Augmented Reality) addresses these issues by coupling a spatial computing client with a robust web analytics platform to digitize the entire inventory lifecycle. Methods The system is divided into two distinct operational tools. The Augmented Reality client transforms the inventory process by rendering the effects of invisible RF signals as real-time data visualizations. These visualizations are overlaid on the physical environment, which allows associates to easily locate where missing items are in real time. Users may also interact with the current inventory lists using hand-tracking gestures, enabling precise, hands-free viewing of complex inventory categories while maintaining spatial awareness. Complementing the headset, a web-based dashboard can serve as a post-inventory command center. This platform provides clear visibility of cycle count data, such as products scanned, locations and counts, as well as spatial data, such as the position and rotation of the handheld scanner and operator. Results Initial system validation was conducted through a proof-of-concept pilot in a retail clothing store. Preliminary data gathered from the cycle count successfully populated the management dashboard. This data can be reviewed to find coverage patterns, identify training opportunities, and improve the store's ordering process. Discussion & Conclusion By synchronizing the associate's spatial experience with the manager's analytical oversight, STAR establishes a new standard for accuracy and accountability in inventory management. Acknowledgment I would like to thank the Auburn University RFID Laboratory staff for their support in making this project possible. I specifically acknowledge the invaluable guidance of Justin Patton, Daniel Speal, and Harper Rhett. Furthermore, I recognize the foundational hard work of Arpan Srivastava, who kickstarted the project, and the significant technical contributions of Sam Clark.

RFID 'DataBridge' Interface
John Koltes Gatesman, Linn-Htet Htoon, Richard Beichler, Kilkee Flynn, Adrielly Hokama Razzini, Brendon Parsons, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

This paper builds on the idea of computational RFID, describing the RFID DataBridge, a flexible interface that employs the semi-passive EM4325 RFID tag and the EPC Gen 2 protocol to communicate data. The unique capabilities of the RFID DataBridge allow it to support existing processes, provide alternative processes that increase robustness and reduce human interaction around critical instrumentation utilizing existing infrastructure around UHF RFID.

A Survey of Gamma Irradiation Effects on UHF RFID Tags
Kilkee Flynn, Brendon Parsons, Adrielly Hokama Razzini, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

Radiation hardness of radiofrequency identification (RFID) tags is an important consideration in many industrial and research applications including nuclear material container tracking. The tracking of nuclear material containers in glovebox environments presents a unique challenge for utilization of RFID technology for inventory management. In order to effectively select tags for this implementation radiation hardness testing must be performed to evaluate performance and lifetime. This paper outlines the literature review conducted to evaluate vulnerable portions of RFID integrated circuits (ICs) to ionizing radiation and the preliminary results of a radiation hardness study using Ra-226 to supply a cumulative dose of more than 16.5 Gy in Si over the course of over 1,600 hours. The results of the study were null, meaning that none of the tags tested displayed a change in performance throughout the duration of the study.

Tuesday, June 16 10:30 - 12:10

NRDZ Workshop 2

Room: Chapel

Tu2: Tutorial 2

Room: Mesa A, Mesa B
10:30 Energy Havesting
Gregory Durgin (Georgia Tech, USA)

Passive radio frequency identification depends on the ability to deliver power to the tag with radio waves instead of current on a wire. To accomplish this feat, the tag needs to have an antenna, and circuitry to match the antenna impedance to the circuitry that converts the radio wave to a DC signal. We examine the distinctions between near-field and far-field configurations for delivering power to the tag, and multiple-inductor approaches to stretch the near-field. We review various increasing-complexity schemes for rectifying the RF signal to get DC out, from a single diode to complex charge pumps and voltage boosters. We introduce power-optimized waveforms for improved rectifier performance, and examine how CMOS devices can be exploited to replace classic PN diodes. We end with a brief review of more exotic devices for conversion, and thermodynamic limits for any device.

11:20 Tag IC Circuits and Protocols
Brian Degnan (IC Analytica, LLC, USA)

Passively RFID is the ultimate constrained system due to area, time, cost and function. This tutorial gives an overview of the RFID IC does after it receives power from the antenna. The transistor is mentioned, but the focus is on what the choice matrix is as a circuit designer and user of the ICs, which unwinds the paradox between laboratory behavior and the showroom floor.

Tuesday, June 16 12:10 - 1:30

Posters

Room: Mesa C
BeeSMART: RFID-Enabled Edge System for Context-Aware Beehive Monitoring and Control
Aiden Zhao (Louisiana State University & Caddo Parish Magnet High School, USA)

BeeSMART is a beehive monitoring system that integrates edge nodes with passive and semi-passive UHF RFID sensor tags for scalable, low-power, low-cost sensing across hive clusters. RFID-based temperature, humidity, and hive ID data provide distributed, cluster-level environmental awareness that enables context-aware decision making and enhances local swarm and mite detection. Pilot results show that cluster-level RFID sensing combined with edge-based control stabilizes hive conditions and supports targeted interventions.

RFIDSentinel: Differentially Private Federated Learning over Synthesized Backscatter Fingerprints for Real-Time Multi-Attack Detection in Dense UHF RFID Deployments
Vihaan Sawardekar (Marquette High School, USA)

The widespread deployment of passive Ultra-High-Frequency (UHF) Radio Frequency Identification (RFID) systems across pharmaceutical serialization, retail logistics, cold-chain monitoring, and critical asset tracking has introduced a large and insufficiently secured attack surface. The stateless architecture and ultra-constrained power budget (1-8 μW) of Class-1 Generation-2 (EPC Gen2) transponders render them inherently vulnerable to a range of adversarial exploits, including tag cloning, relay attacks, inventory replay, phantom tag injection, and Denial-of-Interrogation (DoI). Conventional cryptographic countermeasures-such as challenge-response authentication, hash-locking, and pseudonym randomization-remain impractical under the strict energy and computational limitations imposed by the ISO/IEC 18000-63 standard. Physical-layer security (PLS) techniques, which exploit stochastic variations in backscatter modulation as device-specific fingerprints, provide a promising alternative; however, existing approaches suffer from degraded performance in dense multi-reader environments, sensitivity to inter-session channel variability, and reliance on centralized aggregation of raw in-phase/quadrature (I/Q) data, introducing both privacy and scalability challenges.

This research project presents a software-defined federated learning framework with differential privacy for scalable physical-layer security in UHF RFID systems. The proposed approach eliminates dependence on physical RFID hardware throughout development, training, and evaluation, while addressing the limitations of prior PLS methods through three tightly integrated components: a stochastic backscatter emulation engine, a privacy-preserving federated learning protocol, and a multi-task deep neural architecture.

First, a high-fidelity baseband emulation engine is developed to synthesize EPC Gen2 interrogation sessions in accordance with ISO/IEC 18000-63 timing specifications. The received signal from each virtual tag is modeled as a stochastic convolutional process incorporating a complex-valued backscatter coefficient drawn from IC-family-specific Nakagami-m fading distributions, a Miller-4 subcarrier waveform (Tari = 6.25 μs), a simulated reader antenna impulse response, and additive complex Gaussian noise. The emulator captures variability across multiple commercial integrated circuit families and generates a large-scale dataset comprising 840,000 interrogation sessions across 12,000 virtual tag identities, partitioned into training, validation, and test sets. All data are represented as complex-valued time-series signals, enabling fully reproducible experimentation without reliance on physical readers, antennas, or tags.

Second, to reflect realistic multi-site deployments with strict data locality constraints, a distributed learning framework based on synchronous Federated Averaging (FedAvg) is implemented across 48 simulated edge-reader clients. To ensure formal privacy guarantees, Rényi Differential Privacy (RDP) is incorporated through per-sample gradient clipping (C = 1.0) and calibrated Gaussian noise injection (σ = 0.8), achieving (ε = 2.3, δ = 10⁻⁵)-differential privacy. Each client performs multiple local training epochs per communication round over 300 global rounds, enabling collaborative model optimization while ensuring that raw I/Q fingerprint data remain confined to local partitions. Only privacy-preserving gradient updates are exchanged and aggregated.

Third, a multi-task neural architecture is designed to jointly perform tag identity verification and anomaly detection. The model processes 256-sample I/Q windows corresponding to complete EPC read cycles and employs a depthwise-separable one-dimensional convolutional encoder for hierarchical spectral-temporal feature extraction, followed by a bidirectional gated recurrent unit (GRU) to capture temporal dependencies. The shared representation is fed into two task-specific heads: a 12,000-class softmax classifier for identity recognition and a seven-class sigmoid-based detector covering cloning, relay attacks, DoI, inventory replay, phantom injection, reader impersonation, and bit-level manipulation. Joint optimization is achieved using a weighted composite loss function.

Experimental evaluation under simulated dense-reader interference conditions (up to 16 co-located readers at SNR = 3 dB) demonstrates substantial performance gains. The framework achieves a mean tag identification accuracy of 97.8% (±0.4%, 95% confidence interval), significantly outperforming non-federated deep learning and prior PLS baselines. Anomaly detection attains a macro-averaged true positive rate of 97.8% with a false positive rate of 0.41%, including 99.3% detection accuracy for tag cloning. The incorporation of differential privacy incurs only a modest accuracy reduction relative to non-private federated training, while maintaining strong formal guarantees. Simulated inference latency satisfies EPC Gen2 real-time constraints.

Overall, this research project demonstrates that robust, scalable, and privacy-preserving physical-layer security for UHF RFID systems can be achieved entirely through a software-defined paradigm, establishing a foundation for next-generation secure RFID deployments.

Real-Time Tag Localization using Augmented Reality and Neural Networks
Charles Harper Rhett (Auburn University, USA)

Introduction One of the most significant unsolved problems in the RFID industry is tag localization. That is, how can RFID tags be located quickly and reliably using novel technologies? Traditionally solving this problem has required significant time from experienced radio frequency engineers to develop complex mathematical models. Our goal has been to eliminate that overhead. We use custom neural networks to develop our models instead, trained on data generated in Augmented Reality (AR) to solve localization for modern retail antennas.

Methods When it comes to using neural networks to develop a mathematical model, the problem pivots from requiring talented engineers to requiring reliable training data. We generate this training data by using an Augmented Reality headset to associate real-world tags with their digital twins as a system for ground truth. This ground truth is then paired with a single antenna's movements and signal strength readings (RSSI) as it moves throughout a space. Using this data, we train our neural network to associate tag signal strength with tag position, which can effectively be used to localize tags in a 3-dimensional space.

Results When localizing tags, the user is given a handheld RFID reader and an augmented reality headset. They then proceed to walk around a space while the handheld reader registers tag reads to the headset. Within moments, RFID tags will begin to localize virtually into the user's display. At our current stage of research, the tags localize with an average error of less than half a meter. Discussion & Conclusion Our research is not yet conclusive, and we have many more improvements to make and tests to run. Thus far, we have tested our localization pipeline on one tag inlay type in one enclosed space. We have been careful to abstract the space from the data before processing, but additional environments and tag inlays are imperative for further verification of these techniques. Regardless, using augmented reality to associate real-world tags with their virtual equivalents shows significant promise for the future of tag localization.

Acknowledgement I am very grateful for the guiding hand of Justin Patton, Auburn University's RFID Lab director who gave me the opportunity to create this project. I am additionally thankful for the work done by Jian Zhang and Chris Turner, who inspired the idea. And finally, I would like to thank my colleagues Calvin Hirschler, Adrian Bennett, Sam Clark, and Daniel Speal for their incredible support and contributions.

Neutron Domino Integration with Arduino and RFID
Linnhtet Htoon (University of California, Los Angelos, USA); John Koltes Gatesman, Brendon Parsons, Kilkee Flynn and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Radio frequency identification (RFID) has been demonstrated as an increasingly appealing tool for inventory management across many industries. Los Alamos National Laboratory (LANL) aims to increase the efficiency of its current inventory management system by implementing RFID technology. In addition, we aim to leverage RFID infrastructure to also collect data from specific sensors. RFID is planned to be implemented in a scalable, automated manner to make the inventory process more efficient and enable enhanced monitoring capabilities. Real-time data collection is implemented using a microcontroller communicating with a sensor that can transfer sensor data to an integrated RFID chip. The goal is to minimize the size and power intake of the microcontroller. This poster describes the sensor data transfer application and the integration of sensor data transfer over RFID.

Transforming Inventory Management Through Spatial Data and Visual Feedback
Calvin Hirschler (Auburn University, USA)

Introduction RFID technology is becoming the backbone of modern retail inventory management, yet the physical act of taking inventory remains inefficient due to a lack of visual feedback. Associates typically rely on simple lists and audio cues from handheld scanners without spatial awareness of their scan coverage or accuracy, resulting in missed items and redundant labor. STAR (Scanning Tags in Augmented Reality) addresses these issues by coupling a spatial computing client with a robust web analytics platform to digitize the entire inventory lifecycle. Methods The system is divided into two distinct operational tools. The Augmented Reality client transforms the inventory process by rendering the effects of invisible RF signals as real-time data visualizations. These visualizations are overlaid on the physical environment, which allows associates to easily locate where missing items are in real time. Users may also interact with the current inventory lists using hand-tracking gestures, enabling precise, hands-free viewing of complex inventory categories while maintaining spatial awareness. Complementing the headset, a web-based dashboard can serve as a post-inventory command center. This platform provides clear visibility of cycle count data, such as products scanned, locations and counts, as well as spatial data, such as the position and rotation of the handheld scanner and operator. Results Initial system validation was conducted through a proof-of-concept pilot in a retail clothing store. Preliminary data gathered from the cycle count successfully populated the management dashboard. This data can be reviewed to find coverage patterns, identify training opportunities, and improve the store's ordering process. Discussion & Conclusion By synchronizing the associate's spatial experience with the manager's analytical oversight, STAR establishes a new standard for accuracy and accountability in inventory management. Acknowledgment I would like to thank the Auburn University RFID Laboratory staff for their support in making this project possible. I specifically acknowledge the invaluable guidance of Justin Patton, Daniel Speal, and Harper Rhett. Furthermore, I recognize the foundational hard work of Arpan Srivastava, who kickstarted the project, and the significant technical contributions of Sam Clark.

RFID 'DataBridge' Interface
John Koltes Gatesman, Linn-Htet Htoon, Richard Beichler, Kilkee Flynn, Adrielly Hokama Razzini, Brendon Parsons, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

This paper builds on the idea of computational RFID, describing the RFID DataBridge, a flexible interface that employs the semi-passive EM4325 RFID tag and the EPC Gen 2 protocol to communicate data. The unique capabilities of the RFID DataBridge allow it to support existing processes, provide alternative processes that increase robustness and reduce human interaction around critical instrumentation utilizing existing infrastructure around UHF RFID.

A Survey of Gamma Irradiation Effects on UHF RFID Tags
Kilkee Flynn, Brendon Parsons, Adrielly Hokama Razzini, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

Radiation hardness of radiofrequency identification (RFID) tags is an important consideration in many industrial and research applications including nuclear material container tracking. The tracking of nuclear material containers in glovebox environments presents a unique challenge for utilization of RFID technology for inventory management. In order to effectively select tags for this implementation radiation hardness testing must be performed to evaluate performance and lifetime. This paper outlines the literature review conducted to evaluate vulnerable portions of RFID integrated circuits (ICs) to ionizing radiation and the preliminary results of a radiation hardness study using Ra-226 to supply a cumulative dose of more than 16.5 Gy in Si over the course of over 1,600 hours. The results of the study were null, meaning that none of the tags tested displayed a change in performance throughout the duration of the study.

Tuesday, June 16 1:30 - 3:10

NRDZ Workshop 3

Room: Chapel

Tu3: Tutorial 3

Room: Mesa A, Mesa B
1:30 Circuits and Cryptography
Brian Degnan (IC Analytica, LLC, USA)

We will explore the cost and benefits of cryptography on the RFID tags from both a technical and economic standpoint.

2:00 Middleware / Applications
Jeffrey Dungen (ReelyActive, Canada)

RFID hardware generates data that can be used for plenty of applications, but the interfaces and the data itself may not lend themselves directly to application software. That's where middleware comes in, bridging the gap between hardware and software, and fostering interoperability across vendors and technologies, so that real-time data about "things" in the physical world can be readily applied. This tutorial will present the motivations behind middleware, primarily in the context of RAIN RFID and Bluetooth Low Energy, including practical considerations and real-world examples. Discussion will extend to real-time location, wireless sensing and digital twins to enable digital representations of entire physical spaces. The tutorial will conclude with common applications using event-driven programming, databases, dashboards, AI and all-in-one platforms.

Tuesday, June 16 3:10 - 3:40

Posters

Room: Mesa C
A Survey of Gamma Irradiation Effects on UHF RFID Tags
Kilkee Flynn, Brendon Parsons, Adrielly Hokama Razzini, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

Radiation hardness of radiofrequency identification (RFID) tags is an important consideration in many industrial and research applications including nuclear material container tracking. The tracking of nuclear material containers in glovebox environments presents a unique challenge for utilization of RFID technology for inventory management. In order to effectively select tags for this implementation radiation hardness testing must be performed to evaluate performance and lifetime. This paper outlines the literature review conducted to evaluate vulnerable portions of RFID integrated circuits (ICs) to ionizing radiation and the preliminary results of a radiation hardness study using Ra-226 to supply a cumulative dose of more than 16.5 Gy in Si over the course of over 1,600 hours. The results of the study were null, meaning that none of the tags tested displayed a change in performance throughout the duration of the study.

RFID 'DataBridge' Interface
John Koltes Gatesman, Linn-Htet Htoon, Richard Beichler, Kilkee Flynn, Adrielly Hokama Razzini, Brendon Parsons, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

This paper builds on the idea of computational RFID, describing the RFID DataBridge, a flexible interface that employs the semi-passive EM4325 RFID tag and the EPC Gen 2 protocol to communicate data. The unique capabilities of the RFID DataBridge allow it to support existing processes, provide alternative processes that increase robustness and reduce human interaction around critical instrumentation utilizing existing infrastructure around UHF RFID.

Transforming Inventory Management Through Spatial Data and Visual Feedback
Calvin Hirschler (Auburn University, USA)

Introduction RFID technology is becoming the backbone of modern retail inventory management, yet the physical act of taking inventory remains inefficient due to a lack of visual feedback. Associates typically rely on simple lists and audio cues from handheld scanners without spatial awareness of their scan coverage or accuracy, resulting in missed items and redundant labor. STAR (Scanning Tags in Augmented Reality) addresses these issues by coupling a spatial computing client with a robust web analytics platform to digitize the entire inventory lifecycle. Methods The system is divided into two distinct operational tools. The Augmented Reality client transforms the inventory process by rendering the effects of invisible RF signals as real-time data visualizations. These visualizations are overlaid on the physical environment, which allows associates to easily locate where missing items are in real time. Users may also interact with the current inventory lists using hand-tracking gestures, enabling precise, hands-free viewing of complex inventory categories while maintaining spatial awareness. Complementing the headset, a web-based dashboard can serve as a post-inventory command center. This platform provides clear visibility of cycle count data, such as products scanned, locations and counts, as well as spatial data, such as the position and rotation of the handheld scanner and operator. Results Initial system validation was conducted through a proof-of-concept pilot in a retail clothing store. Preliminary data gathered from the cycle count successfully populated the management dashboard. This data can be reviewed to find coverage patterns, identify training opportunities, and improve the store's ordering process. Discussion & Conclusion By synchronizing the associate's spatial experience with the manager's analytical oversight, STAR establishes a new standard for accuracy and accountability in inventory management. Acknowledgment I would like to thank the Auburn University RFID Laboratory staff for their support in making this project possible. I specifically acknowledge the invaluable guidance of Justin Patton, Daniel Speal, and Harper Rhett. Furthermore, I recognize the foundational hard work of Arpan Srivastava, who kickstarted the project, and the significant technical contributions of Sam Clark.

Neutron Domino Integration with Arduino and RFID
Linnhtet Htoon (University of California, Los Angelos, USA); John Koltes Gatesman, Brendon Parsons, Kilkee Flynn and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Radio frequency identification (RFID) has been demonstrated as an increasingly appealing tool for inventory management across many industries. Los Alamos National Laboratory (LANL) aims to increase the efficiency of its current inventory management system by implementing RFID technology. In addition, we aim to leverage RFID infrastructure to also collect data from specific sensors. RFID is planned to be implemented in a scalable, automated manner to make the inventory process more efficient and enable enhanced monitoring capabilities. Real-time data collection is implemented using a microcontroller communicating with a sensor that can transfer sensor data to an integrated RFID chip. The goal is to minimize the size and power intake of the microcontroller. This poster describes the sensor data transfer application and the integration of sensor data transfer over RFID.

Real-Time Tag Localization using Augmented Reality and Neural Networks
Charles Harper Rhett (Auburn University, USA)

Introduction One of the most significant unsolved problems in the RFID industry is tag localization. That is, how can RFID tags be located quickly and reliably using novel technologies? Traditionally solving this problem has required significant time from experienced radio frequency engineers to develop complex mathematical models. Our goal has been to eliminate that overhead. We use custom neural networks to develop our models instead, trained on data generated in Augmented Reality (AR) to solve localization for modern retail antennas.

Methods When it comes to using neural networks to develop a mathematical model, the problem pivots from requiring talented engineers to requiring reliable training data. We generate this training data by using an Augmented Reality headset to associate real-world tags with their digital twins as a system for ground truth. This ground truth is then paired with a single antenna's movements and signal strength readings (RSSI) as it moves throughout a space. Using this data, we train our neural network to associate tag signal strength with tag position, which can effectively be used to localize tags in a 3-dimensional space.

Results When localizing tags, the user is given a handheld RFID reader and an augmented reality headset. They then proceed to walk around a space while the handheld reader registers tag reads to the headset. Within moments, RFID tags will begin to localize virtually into the user's display. At our current stage of research, the tags localize with an average error of less than half a meter. Discussion & Conclusion Our research is not yet conclusive, and we have many more improvements to make and tests to run. Thus far, we have tested our localization pipeline on one tag inlay type in one enclosed space. We have been careful to abstract the space from the data before processing, but additional environments and tag inlays are imperative for further verification of these techniques. Regardless, using augmented reality to associate real-world tags with their virtual equivalents shows significant promise for the future of tag localization.

Acknowledgement I am very grateful for the guiding hand of Justin Patton, Auburn University's RFID Lab director who gave me the opportunity to create this project. I am additionally thankful for the work done by Jian Zhang and Chris Turner, who inspired the idea. And finally, I would like to thank my colleagues Calvin Hirschler, Adrian Bennett, Sam Clark, and Daniel Speal for their incredible support and contributions.

RFIDSentinel: Differentially Private Federated Learning over Synthesized Backscatter Fingerprints for Real-Time Multi-Attack Detection in Dense UHF RFID Deployments
Vihaan Sawardekar (Marquette High School, USA)

The widespread deployment of passive Ultra-High-Frequency (UHF) Radio Frequency Identification (RFID) systems across pharmaceutical serialization, retail logistics, cold-chain monitoring, and critical asset tracking has introduced a large and insufficiently secured attack surface. The stateless architecture and ultra-constrained power budget (1-8 μW) of Class-1 Generation-2 (EPC Gen2) transponders render them inherently vulnerable to a range of adversarial exploits, including tag cloning, relay attacks, inventory replay, phantom tag injection, and Denial-of-Interrogation (DoI). Conventional cryptographic countermeasures-such as challenge-response authentication, hash-locking, and pseudonym randomization-remain impractical under the strict energy and computational limitations imposed by the ISO/IEC 18000-63 standard. Physical-layer security (PLS) techniques, which exploit stochastic variations in backscatter modulation as device-specific fingerprints, provide a promising alternative; however, existing approaches suffer from degraded performance in dense multi-reader environments, sensitivity to inter-session channel variability, and reliance on centralized aggregation of raw in-phase/quadrature (I/Q) data, introducing both privacy and scalability challenges.

This research project presents a software-defined federated learning framework with differential privacy for scalable physical-layer security in UHF RFID systems. The proposed approach eliminates dependence on physical RFID hardware throughout development, training, and evaluation, while addressing the limitations of prior PLS methods through three tightly integrated components: a stochastic backscatter emulation engine, a privacy-preserving federated learning protocol, and a multi-task deep neural architecture.

First, a high-fidelity baseband emulation engine is developed to synthesize EPC Gen2 interrogation sessions in accordance with ISO/IEC 18000-63 timing specifications. The received signal from each virtual tag is modeled as a stochastic convolutional process incorporating a complex-valued backscatter coefficient drawn from IC-family-specific Nakagami-m fading distributions, a Miller-4 subcarrier waveform (Tari = 6.25 μs), a simulated reader antenna impulse response, and additive complex Gaussian noise. The emulator captures variability across multiple commercial integrated circuit families and generates a large-scale dataset comprising 840,000 interrogation sessions across 12,000 virtual tag identities, partitioned into training, validation, and test sets. All data are represented as complex-valued time-series signals, enabling fully reproducible experimentation without reliance on physical readers, antennas, or tags.

Second, to reflect realistic multi-site deployments with strict data locality constraints, a distributed learning framework based on synchronous Federated Averaging (FedAvg) is implemented across 48 simulated edge-reader clients. To ensure formal privacy guarantees, Rényi Differential Privacy (RDP) is incorporated through per-sample gradient clipping (C = 1.0) and calibrated Gaussian noise injection (σ = 0.8), achieving (ε = 2.3, δ = 10⁻⁵)-differential privacy. Each client performs multiple local training epochs per communication round over 300 global rounds, enabling collaborative model optimization while ensuring that raw I/Q fingerprint data remain confined to local partitions. Only privacy-preserving gradient updates are exchanged and aggregated.

Third, a multi-task neural architecture is designed to jointly perform tag identity verification and anomaly detection. The model processes 256-sample I/Q windows corresponding to complete EPC read cycles and employs a depthwise-separable one-dimensional convolutional encoder for hierarchical spectral-temporal feature extraction, followed by a bidirectional gated recurrent unit (GRU) to capture temporal dependencies. The shared representation is fed into two task-specific heads: a 12,000-class softmax classifier for identity recognition and a seven-class sigmoid-based detector covering cloning, relay attacks, DoI, inventory replay, phantom injection, reader impersonation, and bit-level manipulation. Joint optimization is achieved using a weighted composite loss function.

Experimental evaluation under simulated dense-reader interference conditions (up to 16 co-located readers at SNR = 3 dB) demonstrates substantial performance gains. The framework achieves a mean tag identification accuracy of 97.8% (±0.4%, 95% confidence interval), significantly outperforming non-federated deep learning and prior PLS baselines. Anomaly detection attains a macro-averaged true positive rate of 97.8% with a false positive rate of 0.41%, including 99.3% detection accuracy for tag cloning. The incorporation of differential privacy incurs only a modest accuracy reduction relative to non-private federated training, while maintaining strong formal guarantees. Simulated inference latency satisfies EPC Gen2 real-time constraints.

Overall, this research project demonstrates that robust, scalable, and privacy-preserving physical-layer security for UHF RFID systems can be achieved entirely through a software-defined paradigm, establishing a foundation for next-generation secure RFID deployments.

BeeSMART: RFID-Enabled Edge System for Context-Aware Beehive Monitoring and Control
Aiden Zhao (Louisiana State University & Caddo Parish Magnet High School, USA)

BeeSMART is a beehive monitoring system that integrates edge nodes with passive and semi-passive UHF RFID sensor tags for scalable, low-power, low-cost sensing across hive clusters. RFID-based temperature, humidity, and hive ID data provide distributed, cluster-level environmental awareness that enables context-aware decision making and enhances local swarm and mite detection. Pilot results show that cluster-level RFID sensing combined with edge-based control stabilizes hive conditions and supports targeted interventions.

Tuesday, June 16 3:40 - 5:20

NRDZ Workshop 4

Room: Chapel

Tu4: Tutorial 4

Room: Mesa A, Mesa B
3:40 Applied RFID: Tires & PLCs
Kevin Berisso (University of Memphis, USA)

Tires: The U.S. Federal Motor Carrier Safety Administration is trying to determine if passive RFID Tire Pressure Management Systems are a viable alternative to powered solutions. A brief discussion of the background, current options, and intended path for the testing of RAIN RFID based sensing will be presented, allowing opportunities for the audience to not only provide thoughts and suggestions, but to keep informed on the progress towards a working proof of concept.

PLCs: Every use case for RFID implicitly, if not explicitly, acknowledges the need to have RFID tagging occur as far up the supply chain as possible allowing for users to gain maximum benefit from its use. However, the stated intentions often fail to reflect reality, with company after company still incorporating a variant of "slap and ship." Thanks to Zebra's latest firmware, the barriers to incorporating RFID in the manufacturing environment have been significantly reduced, allowing for seamless integration of RFID into automation solutions. Join us as we explore the reality of integrating RFID into automation solutions and demonstrate some ways in which RFID is able to better interact with machine automation.

4:50 Time permitting, a brief discussion of neuromorphic RFID will also be included in the tutorial session.
Daniel Dobkin (Enigmatics, USA)

Discussing the latest advances and potential for RFID beyond conventional CMOS.

Tuesday, June 16 5:20 - 6:00

NextNAV All Hands Meeting

Room: Mesa A, Mesa B

Tuesday, June 16 6:00 - 7:30

Welcome Reception

Room: Pool

Wednesday, June 17

Wednesday, June 17 8:20 - 10:00

W_P_1: Plenary Keynotes 1

Room: Mesa A, Mesa B
8:20 What's Preventing RFID from Mass Adoption
Mark Roberti (USA)

Each year for the past two decades, pundits have announced that this is the year radio frequency identification takes off, and each year, the pundits have been wrong. Mandates from Walmart didn't spur mass adoption. Regulations requiring the tracking of unique doses of medicines didn't get companies to deploy RFID. Massive improvements in the performance of passive UHF RFID systems and dramatically lower prices for tags and readers hasn't led to mass adoption-even in the apparel retail industry, which has led all sectors in deploying the technology.

So, what's preventing RFID from becoming as ubiquitous as the bar code?

Mark Roberti covered RFID technology for 25 years, first as the founder and editor of RFID Journal, and more recently as president of the RFID Professional Institute. He has spoken with hundreds of companies interested in deploying RFID, with solution providers creating products for the market and researchers in the labs. In this presentation, he will share his thoughts on why RFID hasn't reached mass adoption, what needs to be done to accelerate the current growth of RFID and insights into the market opportunities currently being overlooked.

9:00 Announcements

General conference announcements

9:15 RFID everywhere, all the time
Rafael Pous (Universitat Pompeu Fabra, Spain)

In 2000, Professor Sanjay Sarma, founder of the Auto-ID Center, co-authored the white paper "The Networked Physical World - Proposals for Engineering the Next Generation of Computing, Commerce & Automatic Identification." It articulated the following vision:

"The Auto-ID Center envisions a world in which all electronic devices are networked and every object, whether it is physical or electronic, is electronically tagged with information pertinent to that object. We envision the use of physical tags that allow remote, contactless interrogation of their contents; thus, enabling all physical objects to act as nodes in a networked physical world…"

While the Center's stated mission was "creating the infrastructure, recommending the standards, and identifying the automated identification applications for a networked physical world," the widespread adoption of that infrastructure and those standards depended on a much broader ecosystem of stakeholders.

The adoption of Auto-ID technologies and standards by GS1, the global organization responsible for most supply chain standards, together with their continued evolution and subsequent regulatory approval by authorities such as the FCC and ETSI, laid the foundation for large-scale industrial deployment.

Now, 26 years later, we can look back and ask: what progress has been made toward enabling all physical objects to act as nodes in a networked physical world?

In this presentation, I will argue that RFID, as originally defined by the Auto-ID Labs, has far exceeded initial expectations. I will show how, in the most advanced current deployments, objects are no longer detected only occasionally and at discrete locations, but can be detected pervasively and continuously: everywhere, all the time. As a result, RFID-tagged objects can in these cases be considered permanent nodes in a physical network.

I will also present examples of how this physical network can be combined with other sensors, such as cameras and ultra-wideband (UWB), using AI-enabled sensor fusion to generate a digital twin of physical reality, a rich, dynamic dataset representing the state and evolution of objects, people, and their interactions.

In the digital world, interactions of people with digital objects, "clicks", and their AI-driven analysis ("clickstream analysis") have been a key driver of the success of most online businesses, particularly in the growth of e-commerce. In an analogous way, the use of RFID and sensor fusion to detect "cricks" (a term we coined as a portmanteau of "clicks" and "brick-and-mortar") enables AI, physical AI, to analyze, optimize, and predict the evolution of the physical world in specific contexts, especially logistics and retail.

RFID everywhere, all the time, is no longer a vision. It is already being deployed and is becoming an essential element in a world where all objects, people, and information systems are permanently connected.

Wednesday, June 17 10:30 - 12:10

W_A_1: General Track

Room: Mesa A, Mesa B
Chair: Matthew Reynolds (University of Washington, USA)
10:30 ZeroScatterPico: Bluetooth Low Energy (BLE) Backscatter Using Only Raspberry Pi Pico Digital I/O Pins
Stanley Zhang, Kevin J Ho and Matthew Reynolds (University of Washington, USA)

This paper presents an application of an unmodified Raspberry Pi (RPi) Pico as a low-power and low-cost, Bluetooth Low Energy (BLE) compatible backscatter data uplink. A ZeroScatter approach requiring zero external components is made possible by the two distinct impedance states inherent in switching between the input and output states of the general purpose input/output (GPIO) pins on the RPi Pico. The RPi Pico programmable input/output (PIO) state machine block is first configured in software to accept a binary bit-string containing a BLE advertisement packet. It then generates a frequency-shift keying (FSK) modulation using 2 MHz and 3 MHz subcarriers, representing data bits ‘0' and ‘1', respectively, to backscatter BLE advertising packets when the Pico is illuminated by a 2423.5 MHz carrier from an external carrier wave (CW) source.

During experimental validation, an unmodified Apple iOS device is used as a BLE receiver using a commercial BLE scanner app. We validated the BLE packet performance over-the-air by measuring the Received Signal Strength Indicator (RSSI) in a bistatic configuration at a fixed separation distance of 1.6 meters.

10:50 All-Digital Bluetooth Low Energy (BLE) Backscatter ASIC using Standard I/O Pad Drivers in 180 nm CMOS
Ryan H Lee, Ling-An Kate Tseng, Te Min Yu, Andrew Pan and Jiayi Wang (University of Washington, USA); James Rosenthal (Switzerland); Kevin J Ho, Ang Li and Matthew Reynolds (University of Washington, USA)

This paper presents an application specific integrated circuit (ASIC) that implements Bluetooth Low Energy (BLE) advertising transmission with an all-digital backscatter approach. The ASIC toggles a standard digital I/O pin between tri-state and ground. These two logic states yield different RF impedances, which creates backscatter modulation at programmable subcarrier frequencies. An incident 2.4 GHz carrier wave is then backscatter modulated with these subcarrier frequencies to transmit 1 Mbps BLE formatted data in a BLE advertising channel. The ASIC logic is synthesized from Verilog RTL using a standard cell library in a TSMC 180 nm CMOS process. The ASIC occupies an active area of only 0.085 mm2. This ASIC was validated by transmitting in BLE Channel 37, centered on 2402 MHz. Operating with a 12 MHz external clock, the ASIC consumed 1.85 mW of power. This was split between 1.25 mW (67.5%) used for I/O and 601 uW (32.5%) used for digital core logic. With a carrier wave power of +28 dBm and a 3 cm antenna, the ASIC achieved a transmit range of up to 1 m, as received by an unmodified iPhone without any software or firmware modifications.

11:10 Remote Antenna Impedance Estimation Using a UHF RFID Chip
Nicolas Barbot (University Grenoble Alpes & Grenoble INP, France); Jesse T Tuominen and Antti Paukkunen (Voyantic, Finland); Jasmin Grosinger (University of Siegen, Germany); Pavel Nikitin (Impinj, USA & University of Washington, USA)

This paper shows that it is possible to estimate the impedance of a remote antenna connected to a UHF RFID chip. The proposed method relies on the measurement of four backscattered field values and the knowledge of only two load impedance values. The field values can be obtained using the autotuning functionality available in modern UHF RFID chips. The method does not make any assumption about the antenna geometry and can be performed multiple times to obtain the impedance of the antenna over a given bandwidth (or any other parameter). More importantly, the method is not limited by the number of autotune capacitors in the chip. The method allows one to directly transform a UHF RFID tag into a sensor if the relation between the antenna impedance and a physical quantity is known. Thanks to the proposed method, a significant part of the UHF RFID tags already deployed in the field can be transformed into sensors.

11:30 Fully Integrated Backside-Illuminated Photosensitive RFID Tag for Optical Threshold Detection
Taotao Wu, Yu Lu and Hanyang Wang (Fudan University, China); Yinan Chen (Shanghai Quanray Electronics Co., Ltd., China); Hao Min (State Key Lab of ASIC & System, Fudan University, China)

Photosensitive RFID tags enable optical sensing applications while preserving the passive and low-cost nature. Conventional solutions rely on off-chip photo detectors, which increase footprint and cost, whereas on-chip optical detection is challenging under standard flip-chip packaging. This paper presents a fully integrated photosensitive RFID tag with backside illumination for optical threshold detection. The backside illumination scheme avoids the front-side optical blockage inherent to flip-chip packaging and ensures direct on-chip photosensing compatibility. But it suffers from significant optical attenuation in silicon. Therefore, the photosensor employs an active pixel that adopts a CMOS-compatible p+/n-well/p-sub photodiode with a large, deep depletion region for efficient charge collection, and a subthreshold capacitive transimpedance amplifier (CTIA) for high conversion gain. A subsequent asynchronous dynamic voltage detector provides threshold judgment with negligible static power. Fabricated in 130-nm CMOS, the on-chip sensor core occupies 0.007 mm2 and consumes 34.7 nW from a 0.8-V supply. Measurement results show that the photosensitive RFID tag achieves 6-bit programmable optical threshold detection across an illuminance range from near darkness to approximately 2200 lux.

11:50 An Always-ON Batteryless RFID Sensor Label Using Digital MEMS Sensor Arrays for Continuous Environmental Monitoring
Navid Yazdi (Michigan State University, USA); Casey Wallace (SiTime Corp., USA); Weibin Zhu (Evigia, USA)

This paper presents an Always-ON batteryless RFID sensor label platform that enables continuous environmental monitoring. Unlike conventional RFID sensor tags that operate only within the RF reader field or rely on batteries or auxiliary energy harvesters, the proposed sensor performs continuous sensing and data logging outside the RF field for periods of up to several weeks. The system is enabled by arrays of digital MEMS sensor switches that extract the energy required for switching directly from the sensed physical parameter, together with ultra-energy-efficient single-transistor MEMS-CMOS non-volatile memory (NVM). By eliminating continuous biasing, analog front-ends, and sampled acquisition, the energy required for sensing and digital data storage is reduced by approximately 100-1000x, allowing extended operation using only on-chip isolated stored charge. Environmental data are stored on-chip and retrieved during subsequent RFID interrogation. The demonstrated sensor arrays support temperature and humidity sensing, with operating ranges of −10 °C to 80 °C and 20%-90% relative humidity, respectively. A batteryless NFC-based RFID temperature sensor label with multi-level digital output for vial temperature monitoring is demonstrated. The proposed architecture enables compact, low-cost smart sensor labels compatible with existing RFID infrastructure and is well suited for supply-chain and cold-chain IoT applications.

W_C_1: Special Session: Location-Aware Empowered Systems: Wireless Technologies and New Concepts for Location Sensing, Motion Capture, and Pattern Recognition

Organizers: Andrea Motroni (University of Pisa, Italy), Emanuele Tavanti (University of Pisa, Italy), Jian Zhang (Kennesaw State University, GA, USA), Xiangyu Wang (University of Alabama, AL, USA), Guoyi Xu (University of Rhode Island, RI, USA)
Room: Mesa C
Chair: Andrea Motroni (University of Pisa, Italy)
10:30 QLSTM: A Quantum LSTM for Real-Time Mobile RFID Tag Tracking with Velocity Estimation
Bernard Amoah (Auburn University, USA); Jian Zhang (Kennesaw State University, USA); Shiwen Mao, Senthilkumar Periaswamy and Justin Patton (Auburn University, USA)

Accurate real-time tracking of mobile RFID tags with velocity estimation remains challenging due to phase noise, multipath interference, Doppler effects, and strict latency constraints. While classical Long Short-Term Memory (LSTM) models can capture temporal correlations in RFID measurements, they often struggle with nonlinear phase dynamics and phase-velocity coupling inherent to RF propagation. This paper presents a Quantum-Enhanced LSTM (QLSTM), a hybrid quantum-classical architecture for phase-based RFID tracking with joint position and velocity estimation. The proposed approach integrates multi-reader RFID phase measurements with variational quantum circuits employing data re-uploading and structured entanglement to extract compact temporal representations, followed by a lightweight classical decoder for real-time inference. Experiments on both simulated motion trajectories and real RFID data collected using commercial readers and USRP-based SDR platforms demonstrate that QLSTM achieves up to 23% lower position error and 31% improved velocity estimation accuracy compared to classical LSTM baselines, while maintaining inference latency below 20 ms. These results indicate that quantum-enhanced temporal modeling can improve RFID tracking performance in regimes dominated by phase periodicity, Doppler-induced dynamics, and nonlinear motion.

10:50 Multitarget UHF-RFID and LiDAR Sensor Fusion Safety System for Collision Avoidance
Emanuele Tavanti, Andrea Motroni, Glauco Cecchi and Paolo Nepa (University of Pisa, Italy); Davide Gattamelata, Daniele Puri and Leonardo Vita (Italian Institute for Insurance Against Accidents at Work - INAIL, Italy); Laura Tomassini (INAIL, Italy)

This work presents and validates in an indoor setting a multitarget UHF-RFID + LiDAR sensor fusion safety system for collision avoidance to track workers and other moving obstacles operating close to machinery in construction sites. The system is based on the application of the Dynamic Time Warping (DTW) algorithm using LiDAR point clouds and RFID phase data to recognize each obstacle and classify the correct nature of the target (e.g., worker, static obstacle, etc.).

11:10 Tag-to-Tag Range Estimation for Passive Backscattering Tags
Manavjeet Singh, Yang Xie and Abeer Ahmad (Stony Brook University, USA); Milutin Stanacevic (SUNY Stony Brook, USA); Samir R. Das and Petar M. Djurić (Stony Brook University, USA)

We consider battery-less, passive RF tags that communicate among themselves via backscattering an external RF signal. Unlike traditional RFID or similar backscatter-based systems, they lack active readers, but are capable of direct tag-to-tag communication. We address the tag-to-tag ranging problem in such tag networks - challenged by the absence of active radio processing. Accurate ranging is critical for leveraging the dense web of tag-to-tag connections in downstream applications, most notably localization. We address the ranging problem via a frequency-domain phase-difference of arrival (FD-PDoA) technique along with a data-driven technique to address phase estimation errors. In multipath-rich indoor environments, the proposed method achieves a median ranging error of ≈7 cm for inter-tag distances up to 2 meters.

11:30 AI-Native Detection and Localization of UAS via Multi-Antenna ELF Passive Sensing
Ravisha Hapuarachchi, Anuththa Rathnayaka, Thamindu Virajith and Duleen Wickramasriya (University of Ruhuna, Sri Lanka); Dilshara Herath (University of Peradeniya, Sri Lanka & University of Ruhuna, Electrical and Information Engineering, Sri Lanka); Chatura Seneviratne (University of Ruhuna, Sri Lanka); Arjuna Madanayake (Florida International University, USA)

The increased use of Micro-UAS requires the development of effective localization methods to mitigate escalating privacy and security risks. Traditional active sensing techniques are susceptible to discovery or evasion. This paper addresses the gap in drone localization by proposing an AI-enhanced passive RF sensing system that capitalizes on the ELF magnetic signatures emitted by the brushless DC motors used in UASs. Building on the foundation of ELF sensing, the proposed methodology introduces a novel localization functionality within a predefined target area and extends the detection range beyond 10m (typical indoor operations). It involves the design and test of an optimized ELF receiver antenna arrays that capture ELF signals emitted from small UAS operating indoors, despite challenges posed by high ambient ELF electromagnetic noise. Multiple loop antennas were designed and experimentally characterized, both indoors and outdoors. Drone ELF signatures were analyzed using the spectral correlation function (SCF) based digital signal processing. SCF can clearly separate signatures from drone-present and environment-only cases and reveal distinct spectral patterns for different drone models in the multidimensional SCF signal domain. These SCF images are stacked to form a tensor, which in turn is applied as the input to CNN models, which were used to localize the drone in a real-world 5m x 5m grid. Customized EfficientNetB0 AI implementation reached an overall accuracy of 90% with the highest cell-level accuracy at 96%. The results confirm that ELF-based passive RF sensing combined with SCF and deep learning is a viable alternative for short-range UAV detection and coarse 2D localization.

11:50 Simultaneously Reading and Ranging an EPC Gen2 RFID Tag
Santosh Nagaraj (San Diego State University, USA)

In this paper, a new method to accurately estimate the distance of an RFID tag from a reader within milliseconds, and with only 2 MHz of bandwidth, is described. It is based on the general principles of a Frequency Modulated Continuous Wave (FMCW) radar. However, classical FMCW method is not suitable for ranging with small bandwidths owing to the limitation imposed by the Fast Fourier Transform (FFT) bin width. In this paper, a frequency discriminator based receiver is used instead of the FFT to bypass the bin limitation. Sinusoidal frequency modulation is used instead of a chirp to ensure continuous variation of the interrogator frequency with a compact bandwidth. Longer observation times enable high range accuracy even with relatively small bandwidths. The method presented in this paper is compatible with the Slotted Aloha protocol that is used in the RAIN/EPC standard. Simulations with indoor wireless channel models corroborate the operating principles and confirm range accuracy.

Wednesday, June 17 1:30 - 3:10

Workshops 1

Room: Mesa A, Mesa B
1:30 Toward Scalable and Energy-Efficient Connectivity for 3GPP Ambient IoT via Bistatic RFID
Patricia Bower (HaiLa Technologies Inc, Canada)

The rapid expansion of the Internet of Things (IoT) demands scalable and energy-efficient connectivity for billions of low-power devices. The emerging Ambient IoT (AIoT) concept, currently under study by 3GPP, seeks to enable massive machine-type communications through backscatter technology operating in licensed cellular bands. Conventional CW-based approaches increase power consumption and system complexity, motivating new paradigms that exploit ambient cellular signals for bistatic or ambient backscatter communication. This session will highlight recent advances, challenges, and standardization efforts in AIoT design, with emphasis on ambient signal reuse, cross-layer optimization, and sustainable connectivity strategies toward realizing pervasive and energy-efficient IoT networks.

2:20 RFID Reader Design: A Deep Dive into Echo Cancellation in the GS1 Gen2 Protocol
Alpaslan Demir, Mahmudul H Bhuiyan and Pratheik Ajit (Zebra Technologies, USA)

Covered Topics: Introduction to RFID systems, reader architecture, backscattering concept/antenna mismatch, cascaded receive chain noise figure, mixers constraints, basics of GS1 Gen2V3 protocol (including power ramp)

This intensive one-hour workshop provides a focused look at a critical challenge in modern RFID reader design: echo cancellation. We will quickly cover the fundamentals of RFID reader architecture and backscattering before diving into the core trade-offs between in-chip and external echo cancellation methods. The session will also touch upon key aspects of the GS1 Gen2 protocol, such as power ramp requirements, and conclude with a brief demonstration and Q&A.

Wednesday, June 17 3:40 - 4:30

Workshops 2

Room: Mesa A, Mesa B
3:40 The ID in RFID
Andrew Morehead (GS1 US Inc, USA)

In this workshop, we'll connect "what to encode" with "how it gets read," so teams can make implementation decisions that scale and remain interoperable. Participants will learn how GS1 identifiers (like a GTIN) and optional data using GS1 Application Identifiers are represented in RFID tags via the GS1 EPC Tag Data Standard (TDS)-including the distinction between data-carrier-neutral representations (e.g., URIs) and the RFID-specific binary EPC encodings. We'll also cover how the TDS is improving alignment between RFID and 2D barcodes, including support for streamlined encoding, improved translation via Tag Data Translations (TDT), and new capabilities introduced in TDS 2.3-most notably the ability to encode a host name directly on the tag. This helps expand use cases with newer EPC schemes (like SGTIN+ and date-prioritized DSGTIN+) to improve interoperability with GS1 barcodes and support efficient capture of additional data like dates, lot/batch, and country of origin directly during inventory operations. Attendees will leave with a shared vocabulary, and a standards-aligned approach to planning RFID deployments.

Wednesday, June 17 4:30 - 5:10

Plenary Patron Talks

Room: Mesa A, Mesa B
4:30 RecoHand by Teijin Frontier

Gold Patron Presentation

4:45 Los Alamos National Laboratory
Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Diamond Patron Presentation

Wednesday, June 17 5:20 - 6:20

W_A_2: Special Session: Radio Frequency Identification (RFID) for High-Consequence Environments 1

Organizers: Alessandro Cattaneo (Los Alamos National Laboratories, US), Justin Strait (Los Alamos National Laboratories, US), Brendon Parsons (Los Alamos National Laboratories, US)
Room: Mesa A, Mesa B
5:20 Fast Uncertainty-Aware Localization of Passive RFID Tags
Andrew Cooper (Virginia Polytechnic Institute and State University, USA); Justin Strait, Mary Frances Dorn, Brendon Parsons and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Localizing radio-frequency identification (RFID) tags based on available signal information has been an area of interest to researchers for tracking assets of interest. Phase angle information elicited during communication between an antenna and a passive RFID tag is known to be correlated with both the radio wave's frequency and the relative distance of the tag. However, performing localization in indoor environments is challenging due to the presence of noisy signal information induced by multi-path propagation. This issue is exacerbated in environments with metallic surfaces that are conducive to signal scattering. To properly capture the relationship between radio wave frequency, phase angle, and the corresponding tag distance, we propose a hierarchical modeling approach with a robust wrapped Gaussian process (WGP) framework for regressing noisy phase angle measurements on radio wave frequency. We then use a neural inference approach for mapping phase angle behavior to expected distance based on our model's assumed data-generating mechanism. By introducing a computationally reasonable training cost up-front, we are able to make quick and accurate range estimates with available phase angle measurements. We validate our methods on field experiments conducted in a nuclear materials laboratory environment.

5:40 Improved Efficiency of Nuclear Material Item Inventories when using RFID
Emily Stark, Kilkee Flynn, Adrielly Hokama Razzini, Brendon Parsons, Alessandro Cattaneo and Rollin Lakis (Los Alamos National Laboratory, USA)

Nuclear material item inventories are labor-intensive manual tasks requiring careful verification that every item in an inventory area is accounted for. One common way to perform this task is by cross-referencing identification numbers which can be complex and long. We present results from a basic exercise that compares doing a manual, visual inventory task to performing the task with RFID technology. Inventory areas were set up with variables numbers of items to confirm. On average, the efficiency improved by 16x-67x when using RFID.

6:00 RFID Antenna Modeling and Validation in Complex Glovebox Environments for Nuclear Production Applications
Moisés Felipe Silva (Los Alamos National Laboratory, USA); Allison M Davis (Los Alamos National Laboratory & Purdue University, USA); Marian Anghel, Andrew Chrysler, Brendon Parsons and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

RFID systems can support tracking and monitoring tasks in nuclear process work, but placing reader antennas near gloveboxes introduces electromagnetic effects that are not easy to predict. The metal structure, the glass window, and the confined volume alter antenna behavior, and repeated testing inside these facilities are often limited by safety controls and access restrictions. A dependable HFSS model would allow engineers to study these conditions without constant access to the site. This work examines whether a model of the Vulcan P12 reader antenna can meet that need. We created two HFSS cases, one in free space and one against the glass window of an aluminum glovebox and collected matching vector network analyzer measurements. The comparison shows that the models do not match the measurements exactly, yet they capture the key trends, including the shift in resonance and the change in return loss caused by the glovebox. These findings indicate that the models are suitable for early-stage evaluation of RFID behavior in constrained nuclear settings, with further refinement required for precise prediction.

Wednesday, June 17 7:00 - 9:30

Networking Dinner

Boxcar, 133 West Water Street

Thursday, June 18

Thursday, June 18 8:20 - 10:00

T_P_1: Plenary Keynotes 2

Room: Mesa A, Mesa B
8:20 Patron Talk: AsReader

Introduction to AsReader

8:35 Patron Talk: Auburn University RFID Lab

Patron Talk: Auburn University RFID Lab

8:50 Patron Talk: Avery Dennison

Patron Talk: Avery Dennison

9:05 Announcements

General conference announcements

9:20 The Evolution of Chipless RFID
Richard R. Fletcher (MIT, USA & Massachusetts General Hospital, USA)

While the electromagnetic response of materials has been studied for at least 200 years, the field we now know as "Chipless RFID" was created in the 1990s out of a need for a low-cost (<$0.05) RFID tag. Throughout the late 20th century, we witnessed the emergence of materials for radio-wave backscatter, such as radar chaffe, and 1-bit tags for Electronic Article Surveillance (EAS) for library books and store security. However, multi-bit passive RFID tags could only be created with semiconductor logic ICs; and machines did not exist to be able to handle tiny IC chips and convert them to low-cost labels. During the late 1990s and early 2000s, there was a flurry of research in chipless RFID spanning a very wide range of frequencies (77 Hz to 26 GHz) and physical mechanisms. By the late 2000s, the manufacturing problem of low-cost IC labels was mostly solved, and interest in chipless multi-bit RFID waned; however, the physical mechanisms of chipless RFID were adopted by the RFID community as a way to make crude RFID sensors. By the late 2010s, interest in chipless sensors also waned, as more commercial RFID IC chips emerged with support for external sensors and integrated A/D converters.
As with chip-based RFID, the academic field of chipless RFID that exists today has migrated to operation predominantly in the UHF and low-GHz microwave bands, with the market for RFID now dominated by chip-based solutions. However, a persistent market for chipless RFID has continued to remain in the fields of anti-counterfeiting and extreme environments where chip-based solutions cannot be used. In this presentation, I will give a short review of the evolution of chipless RFID and the different families of tags. I will also present an example commercial success story of a chipless RFID sensor tag design that I patented in 1996, which was licensed to biomedical companies and is still being used today as a biomedical implant to monitor pulmonary arterial pressure in people with congestive heart failure, and which continues to save many thousands of lives yearly and continues to save significant medical costs for hospitals.
Even though the "golden age" of chipless RFID may be in the past, many opportunities still remain for new types of chipless RFID to meet demanding application requirements. New types of low-cost RFID reader designs, signal processing, and artificial intelligence now enables access to new materials signatures; and new types of electro-optical and smart materials now provide new mechanisms for encoding information. While the commercial and academic RFID field seems mired in UHF back-scatter technologies, it is imperative to break out of this thought bubble and continue to explore other frequencies of operation, other types of electromagnetic coupling, other types of representation besides frequency, and other types of materials. Several research groups, including the MIT Auto-ID Lab, have also begun to explore "Hybrid" RFID tags, which combine both chip and chipless components to create new families of RFID labels. The field of chipless RFID has also taught us that chipless signatures exist naturally in many materials and devices in our environment. By designing a "Smart Reader" that can operate at all RF frequencies, as well as optical frequencies, ultrasound, and molecular sensing in the form of olfaction, it is now possible to consider "Smart Reader" appliances that employ detection methods that are not only chipless, but also "tagless," in order to automatically identify and sense the objects, materials, food, and living things in our environment. The future is only limited by our imagination.

Thursday, June 18 10:30 - 12:10

T_A_1: Special Session: Wide-Spectrum and Digital-Twin-Enabled RFID Sensing: From Chirp-Modulated Backscatter to Cyber-Physical Intelligence

Organizers: Shiva Nageswaran (Auburn University, US), Xiangyu Wang (University of Alabama, AL, USA), Jian Zhang (Kennesaw State University, GA, USA)
Room: Mesa A, Mesa B
Chair: Xiangyu Wang (University of Alabama, USA)
10:30 Zero-Shot Quantum Localization: Transferring Knowledge from RFID to WiFi/BLE/UWB Systems
Bernard Amoah (Auburn University, USA); Jian Zhang (Kennesaw State University, USA); Shiwen Mao, Senthilkumar Periaswamy and Justin Patton (Auburn University, USA)

Indoor localization systems suffer from high deployment costs due to technology- and environment-specific fingerprinting requirements. This paper presents Zero-Shot Quantum Localization (ZSQL), a framework that enables cross-technology indoor localization without labeled data in the target domain by transferring knowledge learned from RFID systems to WiFi, Bluetooth Low Energy (BLE), and Ultra-Wideband (UWB). RFID serves as a phase-rich, densely labeled source modality, enabling scalable transfer across heterogeneous RF technologies. ZSQL integrates physics-informed feature extraction, domain-adversarial learning, and variational quantum circuits (VQCs) to learn domain-invariant representations that capture shared electromagnetic propagation characteristics. Experimental results using real RFID data demonstrate mean localization errors of 1.6m (WiFi), 0.99m (BLE), and 1.19m (UWB) without any target-domain labels, approaching few-shot performance while eliminating calibration overhead. This work highlights RFID's role as a transferable sensing foundation and demonstrates the potential of hybrid quantum-classical learning for scalable, multitechnology indoor localization.

10:50 GrLoc: Geometry-Aware RFID Localization with Digital-Twin Fusion for Robust Field Deployment
Yongshuai Wu (Kennesaw State University, USA); Christopher Turner (Auburn University, USA); Jian Zhang (Kennesaw State University, USA); Shiwen Mao (Auburn University, USA); Shaoen Wu (Kennesaw State University, USA); Senthilkumar Periaswamy and Justin Patton (Auburn University, USA)

Fast and reliable RFID tag localization is essential for large-scale inventory operations in realistic retail and warehouse environments. While prior RFID localization systems have achieved centimeter-level accuracy under laboratory calibration, such performance depends on fixed multi-antenna arrays, homogeneous tags, and controlled signal conditions. However, those assumptions do not hold in field deployments. This paper introduces GrLoc, a geometry-aware RFID localization framework designed for handheld and uncalibrated use. GrLoc fuses RFID measurements with real-time depth sensing to construct a 3D digital twin of the surrounding environment, within which geometric validity constraints ensure that estimated tag positions remain inside physically occupied volumes. By filtering physically impossible hypotheses in this digital-twin space before applying the RF observation model, GrLoc substantially reduces multipath-induced ambiguity and achieves consistent, interpretable localization across diverse environments. The framework also provides a digital-twin covariance visualization that represents each tag's confidence region as a 3D ellipsoid, enabling intuitive uncertainty interpretation. Experiments in retail and office environments show up to 79.4% error reduction and over 99% confidence-region coverage, demonstrating that geometry-constrained, uncertainty-aware RFID localization offers deployable robustness rather than laboratory-limited precision.

11:10 Carrier Cancellation for RFIDs with Augmented CW Used in Passive Integrated Sensing and Communication (PISAC)
Yuchen Jiang (Southern University of Science and Technology, China); Yulong Liu (Southern University of Science and Technology, China & The Hong Kong Polytechnic University, Hong Kong); Rusong Yang (Southern University of Science and Technology, China); Lulu Xu (Loughborough University, United Kingdom (Great Britain)); Terry Tao Ye (The Chinese University of Hong Kong, Shen Zhen, China & Southern University of Science and Technology, China)

Integrated Sensing and Communication (ISAC) techniques can also be used in passive RFID system through the exploitation of the channel information from the carrier continuous waves (CW). However, UHF Gen2 protocol uses only simple cosine-based CW, where only limited information can be extracted. Recently, Augmented Carrier Waveforms (AugCW), such as OFDM and FMCW, have been used as carrier waves in passive RFID systems. Although AugCWs can carry more fine-grained channel features, they also introduce much higher side channel interferences that deteriorate the effectiveness of traditional carrier-cancellation techniques for backscattered signals. In this paper, we propose PISAC, a Passive Integrated Sensing and Communication framework, together with a new carrier cancellation technique to estimate and subtract the carrier interference leakage and restore the backscattered signal. Furthermore, we propose an adaptive AugCW selection strategy and derive an RFID-based Fresnel zone model to demonstrate the sensing capability with AugCW. Extensive simulations and software-defined radio (SDR) experiments demonstrate that PISAC significantly improves EPC decoding rates under strong interference from AugCW while enabling robust, fine-grained human activity recognition.

11:30 SlotSense: Counting-Free RFID Tag Density Inference via Temporal Slot Analysis
Soundarya Korlapati and Shiva Nageswaran (Auburn University, USA); Jian Zhang (Kennesaw State University, USA); Senthilkumar Periaswamy and Justin Patton (Auburn University, USA); Xiangyu Wang (University of Alabama, USA)

Radio Frequency Identification (RFID) technology has been widely used for several decades and has evolved into a foundational component of modern identification, tracking, and inventory systems. However, existing RFID inventory systems are primarily rely on the explicit identification of every Electronic Product Code (EPC) to estimate tag populations. This counting-based approach is inherently slow and inefficient in dense environments. To address this gap, this paper proposes a time-domain approach for estimating RFID tag density by analyzing reader-side temporal behavior. Rather than counting tags, the proposed method infers the proportions of singleton slots by constraining adjacent reader events to correspond to one slot durations using inter-read timing statistics. The resulting singleton-slot ratio serves as an indirect indicator of local tag density. Importantly, the approach relies solely on standard reader timestamps and does not require low-level reader data. Experimental results demonstrate that the proposed method reliably captures collision dynamics across varying tag densities, enabling practical shelf-level density estimation for next-generation retail RFID systems.

11:50 ID Beyond the IC: Hybrid Chip-Chipless UHF RFID Tags Employing Wideband Backscatter Fingerprints
Fatima Villa-Gonzalez (Massachusetts Institute of Technology, USA); Richard R. Fletcher (MIT, USA & Massachusetts General Hospital, USA); Heyi Li (MIT, USA); Rahul Bhattacharyya (Massachusetts Institute of Technology, USA); Sanjay Sarma (MIT Auto-ID Center, USA)

This paper demonstrates that conventional UHF RFID tags exhibit distinctive, antenna-dependent wideband linear time-invariant backscatter fingerprints in addition to their standard chip-modulated response. By interrogating commercial RFID tags over a wide frequency span and under varying power levels, we extract two complementary spectral signatures that unify principles from UHF and chipless RFID. Experiments across multiple antenna geometries demonstrate that these wideband fingerprints are repeatable and discriminative, enabling enhanced post-consumer item identification and traceability, as well as additional security, throughout the tag's lifecycle.

T_C_1: Special Session: Radio Frequency Identification (RFID) for High-Consequence Environments

Organizers: Alessandro Cattaneo (Los Alamos National Laboratories, US), Justin Strait (Los Alamos National Laboratories, US), Brendon Parsons (Los Alamos National Laboratories, US)
Room: Mesa C
Chair: Justin Strait (Los Alamos National Laboratory, USA)
10:30 Early experiments to evaluate radio tomographic imaging capabilities of an UWB system in high-consequence environments
Allison M Davis (Los Alamos National Laboratory & Purdue University, USA); Brendon Parsons and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Reliable inventory tracking of nuclear materials remains challenging due to the nature of the highly reflective, multipath-rich environments in which they are deployed. Both passive and active RFID technology have been explored to improve tracking capabilities in these settings. However, prior work has largely focused on general detection and 2D localization and assumes that all containers are individually tagged. Radio tomographic imaging (RTI) offers a complementary sensing modality by enabling device-free detection and localization of non-tagged objects through radio-frequency signal attenuation, with the potential to estimate geometric characteristics beyond a single centroid location. This work presents early experimental results implementing a traditional RTI framework using ultra-wideband hardware in a small, controlled, high-consequence environment. Using a simple UWB node network, spatial attenuation maps are reconstructed from RSS-derived measurements and evaluated against the placement of a metallic obstruction. Although preliminary, the results demonstrate the feasibility of UWB-based RTI as a complementary tool that could augment existing RFID infrastructure and motivate further investigation into more robust reconstruction and modeling approaches.

10:50 Performance characterization of commercial on-metal UHF RFID Labels on Curved Metal Surfaces
Shiva Nageswaran and Soundarya Korlapati (Auburn University, USA); Brendon Parsons, Rollin Lakis and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Metallic mounting surfaces remain one of the most challenging environments for UHF RFID tag operation due to strong electromagnetic coupling that alters antenna impedance and radiation characteristics. While numerous studies have proposed antenna designs to mitigate these effects, limited work has examined the performance variability of commercially available on-metal RFID tags under deployment-representative conditions. This paper presents an experimental evaluation of two off-the-shelf folded on-metal RFID label designs, focusing on performance variability across tag populations, mounting geometries, and orientations. Measurements were conducted in free space, on flat metal plates, and on cylindrical metal containers to represent realistic applications. Results show that while resonance shape and center frequency remain relatively consistent, non-negligible variation in sensitivity is observed across repeated trials and tag orientations. Orientation sweeps on curved metal surfaces further reveal that worst-case performance does not necessarily correspond to intuitive "backside" orientations. These findings highlight the importance of considering performance distributions, rather than single-sample measurements, when designing and qualifying RFID systems for metal-rich environments.

11:10 Statistical Performance Modeling of RFID Inventory Processes
Justin Strait, Mary Frances Dorn, Kilkee Flynn, Robert Migliori, Brendon Parsons, Rollin Lakis and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

In nuclear facilities, modern inventory systems which enable RFID technology have been proposed to accelerate tracking of assets. Prior to regular inventory rounds, assets must be "commissioned" with passive RFID tags, which requires establishing a one-to-one correspondence between asset and tag. We outline and formally evaluate a proposed hybrid barcodeRFID commissioning process for nuclear material containers. Using principles from statistical design and analysis of experiments, we explore commissioning error rates and process step times as a function of controllable settings, taking into account relevant uncontrollable environmental factors. Broadly, this work presents a formal experimental design and analysis framework for preliminary studies of RFID-enabled processes.

11:30 An RFID-enabled tamper-indicating device to maintain continuity of knowledge on nuclear material
Adrielly Hokama Razzini, Brendon Parsons, John Koltes Gatesman, Kilkee Flynn, Rollin Lakis and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Maintaining continuity of knowledge for nuclear materials relies on tamper-indicating devices (TIDs) that can reliably detect and report unauthorized access while minimizing inspection burden and occupational exposure. Conventional safeguards seals remain vulnerable to defeat and often depend on subjective visual inspection, limiting scalability and auditability. This paper presents the design, fabrication, and preliminary evaluation of an RFID-enabled tamper-indicating seal prototype that integrates irreversible physical tamper response with machine-readable state reporting. The prototype employs sacrificial carbon trace elements patterned on a flexible polyimide substrate, monitored by a microcontroller and coupled to a UHF RFID integrated circuit for non-contact interrogation using standard reader infrastructure. Tamper events are detected through permanent changes in electrical resistance compared against established baselines and are reported via the RFID interface during routine inventory operations. Experimental results demonstrate successful registration and reporting of tamper events when the seal is removed, validating the feasibility of binding physical tamper evidence to RFID-based identification and state reporting. This first-generation prototype serves as a proof of concept and highlights a path toward RFID-enabled TIDs that reduce reliance on manual inspection, improve auditability, and support safer, more efficient safeguards verification.

11:50 Characterization of UHF RFID Tag Performance for SAVY-4000 Nuclear Material Storage Containers
Anthony Sadler, Brendon Parsons, Justin Strait, Rollin Lakis and Alessandro Cattaneo (Los Alamos National Laboratory, USA)

Radio Frequency Identification (RFID) technology is broadly used for supply chain management applications. Performance of RFID tags on assets is heavily dependent on the placement of the RFID tag on the asset, especially for on-metal tags, and the orientation of the tag antenna relative to the reader antenna. This paper is a comprehensive study characterizing the performance of commercially available on-metal RFID tags applied to nuclear material storage containers. The experiments were conducted using a commercially available RFID reader in a realistic multipath environment to determine the consistent tag turn on power. Key findings include the demonstration of similar performance between different container sizes and the determination of preferred tag placement on each container size. The results from the experiments can inform the design and deployment of an RFID-based inventory system to ensure robust performance in a high consequence environment.

Thursday, June 18 1:30 - 3:10

T_A_2: Special Session: Beyond Conventional Backscatter Communications

Organizers: Gregory Durgin (Georgia Tech, US), Christopher Saetia (Georgia Tech, US), Simon Hemour (University of Bordeaux), Ambuj Varshney (National University of Singapore, Singapore)
Room: Mesa A, Mesa B
Chairs: Michael J Crisp (University of Cambridge, United Kingdom (Great Britain)), Christopher Saetia (Georgia Institute of Technology, USA)
1:30 HILO: Enabling Low-power, Dual-Band Communication using Tunnel Diode Oscillators
Dhairya Shah, Rajashekar Reddy Chinthalapani, Pramuka Sooriya Patabandige and Ambuj Varshney (National University of Singapore, Singapore)

Wireless communication remains the most power-consuming operation in embedded systems. Low-power transmitters such as backscatter achieve microwatt-scale operation, but produce weak signals susceptible to in-band interference and frequency-selective fading, particularly in non-line-of-sight settings. Multi-carrier transmission can mitigate these effects by introducing spectral-domain redundancy rather than temporal-domain redundancy, thereby improving reliability without sacrificing bitrate or latency. However, conventional multi-band radios require duplicated RF chains or power-hungry synthesizers. We introduce HILO, a tunnel diode-based frontend that enables dual-band operation using a single oscillator. HILO inverts the conventional paradigm: rather than suppressing the harmonics inherent to tunnel diode nonlinearity, it harnesses them. An external device injection-locks the oscillator to a fundamental frequency, thereby simultaneously stabilizing a higher harmonic, yielding two phase-locked carriers without a second oscillator or frequency multiplier. In the transmit mode, HILO exploits self-oscillating mixing to modulate both carriers simultaneously; in the receive mode, it uses autodyne downconversion at both frequencies. By turning an inherent nonlinearity into a feature, HILO achieves dual-band links while consuming under 210 μW.

1:50 A 2.4 GHz True Time Delay (TTD) Subcarrier Beamforming Array for Spatially-Selective Bluetooth Low Energy (BLE) Backscatter
Kevin J Ho, Stanley Zhang and Matthew Reynolds (University of Washington, USA)

This paper presents an approach for creating spatially-selective Bluetooth Low Energy (BLE) backscatter signals using a subcarrier beamforming array. The subcarrier beamforming array is implemented using a Raspberry Pi (RPi) Pico programmable input/output (PIO) state machine block to introduce digitally configurable time delays, and thus phase shifts, among the subcarriers backscattered by an array of four antenna elements. The subcarriers generated by the array are frequency-shift keying (FSK) modulated using 2 MHz and 3 MHz frequencies that represent data bits '0' and '1', respectively. An external carrier wave (CW) source at 2423.5 MHz serves as the carrier that is backscattered by this array to yield BLE-compatible advertising packets that can be beam-steered under digital control, while being received by any BLE compatible device such as smartphones and tablets.

A bistastic experimental setup using an unmodified Apple iOS device with a commercial BLE scanner app was used to validate over-the-air array gain performance by measuring the Received Signal Strength Indicator (RSSI). Then, a monostatic experimental setup using a spectrum analyzer tuned to a BLE channel passband was used to validate over-the-air array directivity by introducing digitally controlled time delays among the array elements. The measured beamwidth of the main backscatter lobe was approximately 30 degrees and the beam was steerable up to 25 degrees off boresight under digital control.

2:10 Low Cost Regenerative Amplifiers for Long Range UHF RFIDs
Skanda Harisha (University of Michigan, Ann Arbor, USA); Mohamed Safawi and Jimmy G Hester (University of Michigan, USA); Aline Eid (University of Michigan, Ann Arbor, USA)

Backscatter regeneration amplifier-based tags represent a promising advancement for extending the communication range of Radio Frequency Identification (RFID) systems, owing to their impressive high-gain capabilities. Historically, the most effective designs for backscatter communication have utilized tunnel diodes, which, while capable of achieving gains greater than 40 dB, are prohibitively expensive for large-scale deployments. In this work, we present a novel reflection amplifier design utilizing a low-cost off-the-shelf Pseudomorphic High Electron Mobility Transistor (pHEMT). The design of the 900 MHz amplifier is shown and its principle of operation is described in detail, before its gain and power consumption are characterized in varying biasing conditions. The tag, interfaced with antennas, is then shown capable of transmitting digital data at a distance of 81m with 20 dB SNR. Our prototype RFID tag demonstrates a gain of up to 65 dB and a -90 dBm sensitivity, far exceeding those of tunnel diode based amplifiers, at a fraction of the cost, while consuming between 1 and 9 mW. These findings suggest that transistor based reflection amplifiers can facilitate cost-effective scaling of RFID technology, making high-performance, extended range identification systems more accessible than ever before

2:30 Pilot-Assist Backscatter Communications with a Tunnel Diode Backscatter Modulator
Christopher Saetia (Georgia Institute of Technology, USA); Gregory Durgin (Georgia Tech, USA)

Future backscatter communications systems must be designed to have versatile hardware and modulation schemes to be used in different environments with different link conditions. To decide how to adapt modulation parameters for different link conditions, analyzing backscattered pilot symbols is one simple technique to help adjust these parameters for optimal communication of data. This work, specifically, demonstrates the versatile use of pilot symbols with a higher-order tunnel diode backscatter modulator to help with several crucial actions such as: evaluating communications link quality, setting modulation order and vector symbol constellations, and decoding message at the receiver. And wireless measurements showing the whole pilot-assist process in LOS and non-LOS (thru-wall) scenarios are also detailed to show the value of pilot symbols for backscatter communications in different environments with different communication link qualities.

2:50 Terahertz 3D-Printed Mechanical Azimuth Beamsteering Using Contoured Dielectric Disk as Variable-Deflection Prism
Taegyun Noh, Bryce Chung, Withawat Withayachumnankul and Daniel Headland (Terahertz Engineering Laboratory, Adelaide University, Australia)

Beamsteering is vital in terahertz wireless applications where a directional beam is indispensable. Electronic-based terahertz phase control does not operate well due to excessive losses. Here, we present a mechanically controlled terahertz beamformer based on a 3D-printed contoured dielectric disk operating from 220 to 330 GHz. Unlike conventional terahertz beamforming techniques, the proposed architecture achieves continuous beam steering using only a single rotational motor without active phase-control components. The sinusoidal contour profile introduces a transverse phase gradient through mechanical rotation, enabling predictable angular deflection. A line-focusing and line-collimating configuration suppresses undesired steering in the orthogonal direction and preserves beam quality. The device demonstrated continuous and reversible bidirectional beam steering up to 6 degrees, while maintaining relatively stable half-power beamwidth across all rotation angles. Broadband measurements confirm consistent steering performance throughout the operation band. This passive, mechanically tunable beamforming scheme provides a simple and cost-effective solution for practical terahertz beam control.

T_B_3: Special Session: AI-Powered RFID and IoT Systems for Edge Intelligence and the Internet of Bodies

Organizers: Salvatore Tedesco (Tyndall National Institute, Ireland), Ismail Uysal (University of South Florida, FL, US), Qamer H. Abbasi (University of Glasgow, UK), Andrea Motroni (University of Pisa, Italy)
Room: Mesa C
Chairs: Ultan McCarthy (Waterford Institute of Technology, Ireland), Andrea Motroni (University of Pisa, Italy)
1:30 A Neuromorphic RF Power Sensor for Inductive Coupling IoT Systems
Rafael Cantalice (Universidade Federal de Campina Grande, Brazil); Gutemberg Gonçalves Santos Junior (UFCG VIRTUS, Brazil); Marcos Morais and Angelo Perkusich (Virtus, Brazil); Antonio M. N. Lima (Universidade Federal de Campina Grande, Brazil); Pietro M. Ferreira (Univ. Savoie Mont Blanc, Univ. Grenoble Alpes, Grenoble INP, CNRS, CROMA, Grenoble, France)

This paper presents a novel neuromorphic RF power sensor designed for inductively coupled IoT systems, such as RFID tags and implantable devices that rely on wireless power transfer. By leveraging principles of neuromorphic near-sensor computing, the proposed architecture enables ultra-low-power operation and native compatibility with Spiking Neural Networks (SNNs) and event-driven processing. The sensor employs a Pulse Width Modulation (PWM) scheme in which the duty cycle is proportional to the received RF power. This PWM signal controls a charge pump that generates an analog voltage proportional to the input power, which is subsequently converted into a spike train by a voltage-to-spike converter based on a relaxation oscillator. The resulting spike rate encodes the input power level and can be used to infer the coupling distance, supporting system-level optimization. In addition, the proposed sensor enables amplitude modulation (AM) demodulation by distinguishing binary data through spike counting, making it well suited for low-data rate communication in power-constrained neuromorphic IoT environments.

1:50 PT-Enabled Wireless PUF Tags with Contrastive 1D-CNN Embeddings for Robust Identifications
Yichong Ren and Zong-Ru Lee (University of Illinois Chicago, USA); Duc Anh Pham (University of Illinois at Chicago, USA); Jimmy Ching-Ming Chen (Wayne State University, USA); Pai-Yen Chen (University of Illinois at Chicago, USA)

We herein propose a low-cost, lightweight physical unclonable function (PUF) architecture based on a wireless parity-time (PT)-symmetric radio-frequency identification (RFID) system. Compared with a conventional RFID setup, the PT-enabled platform produces highly randomized yet robust physical signatures, enabling reliable tag identification under realistic readout variations. To quantify robustness and reliability, we formulate authentication as an enrollment-query classification problem and adopt a lightweight one-dimensional convolutional neural network (1D CNN) encoder combined with cosine-similarity nearest-neighbor (Cosine NN) matching. The resulting confusion matrices exhibit a sharply concentrated main diagonal and consistently improved accuracy (ACC) under both weak and strong perturbations. In addition, shift-robustness tests confirm strong tolerance to time misalignment, highlighting the practicality of the proposed approach for real-world interrogation conditions. Overall, these results establish PT-symmetric circuitry as an effective hardware-level mechanism for enhancing entropy and separability in low-cost wireless access control and anticounterfeiting applications.

2:10 Motion Modulation for AI-aided Simultaneous Identification of Multiple Chipless RFID tags
Andrea Motroni (University of Pisa, Italy); Salvatore Tedesco (Tyndall National Institute, Ireland); Filippo Costa (University of Pisa, Italy)

Chipless RFID technology stands out for its capability of wirelessly and remotely identifying objects with radio waves without the utilization of Integrated Circuits (ICs), being a promising and low-cost alternative to conventional RFID systems. The simultaneous identification of multiple chipless RFID tags is, however, a non-trivial problem due to mutual coupling, spectral overlap, and multi-tag interference. This paper proposes a system to first assess the number of visible tags in the scene with a Random Forest-based classifier, then exploits motion modulation to achieve simultaneous detection and decoding of all the present chipless RFID tags by applying trajectory-matched steering vector processing.

The system is validated with two polarization-converting chipless tags in an indoor environment, with tests performed with a Cartesian robot to implement the tag motion.

2:30 Collision-Resilient RFID Tag Counting under Protocol Constraints Using Lightweight Machine Learning
Sobhi Alfayoumi (Universitat Oberta de Catalunya (UOC), Spain); Selim Zighed (Universitat Oberta de Catalunya (OUC), Spain); Heyi Li (MIT, USA); Fatima Villa-Gonzalez (Massachusetts Institute of Technology, USA); Marta Gatnau Sarret (Universitat Oberta de Catalunya (UOC), Spain); Rahul Bhattacharyya (Massachusetts Institute of Technology, USA); Sanjay Sarma (MIT Auto-ID Center, USA); Joan Melià-Seguí (Universitat Oberta de Catalunya (FUOC), Spain)

Efficient tag counting in dense RFID environments necessitates accurate estimation of the number of collided tags within single protocol slots. However, current protocols discard these collisions as failures, leading to systematic resource waste. This work presents a comparative analysis of two frameworks that transform collision interference into valuable information sources using In-phase and Quadrature (IQ) signals. First, a two-stage approach combines clustering to identify constellation points with a rule-based mapping to estimate tag counts. Second, an end-to-end machine learning (ML) strategy directly predicts the number of collided tags from raw IQ data. We evaluate a spectrum of statistical and ML models, optimizing hyperparameters to balance performance against computational costs. Key metrics including accuracy, error rates, and inference latency are analyzed, strictly adhering to the timing constraints of the EPC Gen2 protocol. The findings delineate critical trade-offs between model complexity and real-time feasibility, identifying optimal candidates for deployable, collision-aware tag counting in RFID readers. For scenarios involving up to seven collided tags, the Random Forest model achieves 98% accuracy in just 69 micro-seconds, successfully meeting the T2 timing limits required for real-time RFID operation.

2:50 A Cyber-Physical Security Framework and Validated Solution for RFID Item-Tag Integrity
Heyi Li (MIT, USA); Marco De Vincenzi (IIT-CNR, Italy); Fatima Villa-Gonzalez and Rahul Bhattacharyya (Massachusetts Institute of Technology, USA); Sanjay Sarma (MIT Auto-ID Center, USA)

Radio Frequency Identification (RFID) is widely used in supply chains, but most security approaches are tag-centric, assuming a trusted link between tag and item. This assumption fails under identity-transfer attacks (e.g., tag reuse, insider swaps, returns fraud) that preserve valid identifiers while altering items. This work proposes a multi-layer framework focusing on item-tag integrity, combining tag authentication, integrity fingerprinting, and contextual validation to raise attack costs through a comprehensive OWASP analysis. A key contribution is a coupling-based fingerprint using paired "tag twins" and two-stage differentiation from commodity readers, requiring no specialized hardware and with high time efficiency. Experiments achieve 83.4% accuracy for 3-11 mm spacing, 96.5% for 3/5/7mm on PVC, and 86.8% in distinguishing four tag pairs, demonstrating scalable protection.

Thursday, June 18 3:40 - 5:20

T_A_3: Special Session: RFID enabled sensors: From Integrated circuit (IC) design to system implementation

Organizers: Roc Berenguer (University of Navarra), Beriain, Andoni (Kliskatek S.L and Univ. of Navarra)
Room: Mesa A, Mesa B
Chairs: Alvaro Urain (TECNUN, Spain), Fatima Villa-Gonzalez (Massachusetts Institute of Technology, USA)
3:40 A 75 kHz Inductive Power and BPSK Backscatter Communication Link for a Battery-Free Sub-Soil Sensor
Wei-Chuan Tsai (University of Washington, USA); Angela Gajbhiye (USA); Nicole Pham and Matthew Reynolds (University of Washington, USA)

We present a 75 kHz inductive power and binary phase shift keying (BPSK) backscatter communication link for low data rate, battery-free ground-emplaced sensors. This wireless power and data transmission (WPDT) link uses inductive coupling at a relatively low frequency of 75 kHz to minimize the impact of moist soil on the link. It uplinks data to a ground-emplaced interrogator device at a bit rate of 500 bps. The sensor device is based on an Arduino Nano processor to allow easy integration of multi-purpose sensors for a wide variety of applications, while the interrogator uses a software-defined radio (SDR) approach based on the Analog Devices ADALM2000 data acquisition system, with the signal processing chain implemented in easily reconfigurable Python. We detail the system architecture and evaluate its performance through experimental validation in a lab setting at power transfer and communication ranges of up to 15 cm in air, 15 cm in dry soil (<5% water by mass) and 12 cm in wet soil (approximately 40% water by mass).

4:00 A Passive UHF RFID Voltage Sensor Tag for Wireless Battery Monitoring Systems
Karim Marouan Chaffai (Tecnun, University of Navarra, Spain); Alvaro Urain (TECNUN, Spain); Ainhoa Rezola and Andoni Beriain (Tecnun, University of Navarra, Spain); Hector Solar (Tecnun - University of Navarra, Spain); Roc Berenguer (TECNUN, Spain)

This paper presents a prototype of a UHF RFID-based wireless battery monitoring system, suitable for electric vehicle battery management and as an alternative to traditional wired solutions. The system combines a commercial ROCKY100 analog front-end for RF energy harvesting and communication with a custom digital core, implemented on a Xilinx Artix-100T FPGA, which handles EPC Gen2 protocol control and sensor interfacing. Battery voltage data is measured using the ultra-low-power MSP430FR2433 microcontroller, that is supplied exclusively by the harvested RF energy by the ROCKY100. The RFID sensor consumes a maximum of 12.5~uA during full burst operations and less than 1~uA otherwise. The proposed wireless sensor is compared with a wired solution through a standard AA alkaline battery discharge experiment at a distance of 80~cm. Results show that measured voltage difference between the RFID sensor and the wired solution is kept below 20~mV, proving its suitability for wBMSs.

4:20 Split-Ring Resonator Enhanced Detection of Liquids Using Backscatter Tags
Ryan Jones, Shuai Yang and Michael J Crisp (University of Cambridge, United Kingdom (Great Britain)); Richard Penty (Cambridge University, United Kingdom (Great Britain))

Wireless passive backscatter tags have become a popular choice for sensing due to their low cost and maintenance-free operation. One application is binary liquid detection i.e., determining whether a liquid is present in proximity to the tag. Typically, the presence of the liquid alters the dielectric properties around the tag, which alters the reflected signal's amplitude and phase. By monitoring these variations one can decide "presence" versus "absence" without any active sensing electronics on the tag itself. However, to induce a notable change in the received power or phase at the reader, the tag is typically detuned by a large amount of liquid, resulting in a reduced read range and poor liquid sensitivity. We propose an enhanced liquid detection method based on inter-tag channel estimation. A split-ring resonator (SRR) is introduced between two tags to suppress the inter-tag channel in the unloaded state. When loaded with liquid, the SRR's resonant frequency shifts, producing measurable changes in the inter-tag channel that indicate the presence of a liquid. We present the complete system design and validate the approach experimentally with emulated tags and commercial UHF RFID tags. Results demonstrate inter-tag channel changes exceeding 12 dB in magnitude under loading of only 0.5 mL of deionized (DI) water.

4:40 Material sensing using arrays of open dipole RAIN RFID tags
Fatima Villa-Gonzalez and Rahul Bhattacharyya (Massachusetts Institute of Technology, USA); Pavel Nikitin (Impinj, USA & University of Washington, USA)

This work demonstrates how open dipole (OD) RAIN RFID tags and tag-arrays can be used for material characterization in a standard compliant way. Unlike T-matched antennas, OD designs exhibit reduced resonance complexity, with a single minimum in the power-on-tag-forward (POTF) and a single maximum in the power-on-tag-reverse (POTR) response. We introduce a setup-invariant metric based on the transmitted and received reader powers at tag threshold, which preserves resonance information while eliminating the need for calibration. In addition, we demonstrate that auto-tune (AT) code changes in self-tuning ICs of OD tags provide clear and narrowband minmax transitions that remain stable over a wide range of transmit powers, providing high tuning flexibility and enabling sensing at fixed reader power. Building on this, we propose a novel approach for material sensing, leveraging the AT-code transitions within the narrow UHF RFID band using arrays of individually tuned OD tags. We demonstrate the repeatability of open dipole-based sensing using 6 commercial OD RAIN RFID tags to estimate the effective dielectric permittivity of 6 materials, obtaining lower variance than T-matched antennas for high εr dielectrics. Furthermore, we propose a custom three OD tag array capable of discriminating between four specific materials and air within the UHF band, demonstrating the sensing capability of this new method in compliance with regulatory standards.

5:00 Additively Manufactured Chipless RFID-Based Resonator for Non-Contact Plant VOC Sensing Using MXene
Mojisola Rachael Akinsiku, Md Mahamud Hasan Tusher, Danling Wang and Shuvashis Dey (North Dakota State University, USA)

This study uses passive radio frequency identification (RFID) resonators to detect volatile organic compounds (VOCs) released by plants. The resonant structures are integrated with VOC sensing smart material, MXene. The sensor works by detecting changes in the resonator's radar cross-section (RCS) response, which occurs due to interactions with materials and the environment. First, CST Studio Suite full-wave electromagnetic simulations are used to study the resonator's behavior with and without the MXene sensing material. The simulation results show that adding the sensor layer causes resonance shift and signal attenuation, indicating strong electromagnetic coupling in the sensing area. To evaluate the sensing concept, soybean leaves were cultivated in both controlled and uncontrolled environments. The introduction of soybean leaves to the baseline response elicited substantial alterations in both amplitude and resonance profiles. Soybean plants under regulated conditions exhibited more consistent and repeatable responses, whereas those in uncontrolled conditions displayed greater variability, presumably stemming from environmental stressors. The modeling and experimental findings collectively validate the utility of passive RF resonators for detecting plant-emitted VOCs and underscore the influence of cultivation conditions on RF-based plant sensing methodologies.

T_C_3: Special Session: Sustainable Pathways in Electronics, IoT and RFID: Materials, Devices, Systems, and Beyond

Organizers: Giuseppe Cantarella (University of Modena and Reggio Emilia, Italy), Shweta Agarwala (Ahmedabad University, India), Gregory Withing (University of Colorado Boulder, USA)
Room: Mesa C
Chairs: Eloise Bihar (State University of New York at Buffalo, USA), Gregory Whiting (University of Colorado Boulder, USA)
3:40 Electrochemical Sensor and Energy Storage Devices for Sustainability
Tse Nga Ng (University of California San Diego, USA); Siqi Yu (UC San Diego, USA); Lulu Yao (University of California San Diego, USA)

This work presents sensing and energy storage devices for sensor networks enabling phosphate monitoring in complex aqueous environments. A mixed-valence MoOx electrochemical sensor achieved selective phosphate detection with a detection limit of 8 μM, suitable for environmental and biological applications. The sensor used low-cost materials, simple fabrication, and low-power operation compatible with distributed sensor nodes. To meet system power requirements, zinc-ion supercapacitors were advanced using copper nanoparticle-modified current collectors to control zinc deposition and a chlorine-assisted activation process to increase cathode capacity. The resulting supercapacitor would be suitable for high-endurance applications that demand frequent cycling.

4:00 A fully polymer-based shift register for sustainable RFID applications
Fabrizio Antonio Viola (University of Cagliari, Italy); Caironi Mario (Ist Italiano Tecnol, Italy); Dario Natali (Politecnico di Milano, Italy); Giorgio Dell'Erba (Fondazione Chips - IT, Italy); Paolo Colpani and Biagio Brigante (Italy)

The growing need for sustainable electronics is driving the development of technologies that are based on low environmental-impact materials and manufacturing techniques, offering the potential to reduce both the carbon footprint of devices and the production of electronic waste. This increasing demand is particularly relevant for the Internet-of-Things and Radio-Frequency IDentification (RFID) applications, where the goal is the tagging of a large volume of objects with digital electronic devices, often designed for short-term use. In this context, printed organic electronics, based on cost-effective, low-temperature, and scalable approaches, offers an interesting solution to address this challenge. Here, we present a fully polymer-based digital logic circuit, namely a 4-bit shift register, implemented using inkjet-printed organic complementary transistors, compatible with large-area and low-cost plastic substrates. The proposed 4-bit shift register highlights the potential of printed organic electronics for sustainable digital devices for RFID applications.

4:20 Zero Waste Chipless RFID Tags Made with Zinc Tracks on Paper Substrate
Jeff Kettle (University of Glasgow, United Kingdom (Great Britain))

Presented here is a new approach for RadioFrequency Identification Devices (RFID) manufacture based on electroplated Zinc (Zn) conductive tracks transferred onto paper substrates. Zn is an earth-abundant and low-toxicity metal that offers electrical conductivity compatible with RF operation while improving prospects for reduced end-of-life management as it has the potential for controlled degradation in alkali solutions. The proposed fabrication route employs photolithographic patterning, formation of a Zn seed layer, electroplating of Zn, and a chitosan-assisted transfer of the metallic structures from an aluminium carrier to paper. Electrical characterisation is performed through one-port scattering-parameter measurements using an open-source Vector Network Analyser. The resulting devices behave as resonators and incorporate interdigitated electrodes acting as variable impedance elements for sensing. Results demonstrate that the additive Zn growth and transfer process preserves geometrical fidelity at the designed resolution and yields coils capable of stable resonance and measurable modulation of the reflection coefficient. The processing method therefore provides a viable route toward zero waste RFID tags that merge sustainable materials, low-impact fabrication, compatibility with chemical sensing techniques, as well as controlled End-of-Life management.

4:40 Wireless and on-demand drug delivery with ultrasound-responsive sustainable piezoelectric chitosan film
Gaia de Marzo (Technical University of Denmark, Denmark); Giacomo Pasquali, Frida Bejder, Matilde Manigrasso and Massimo De Vittorio (Denmark Technical University, Denmark)

Customized drug administration approaches allow for enhancing the efficacy of therapies by increasing the dose while minimizing side effects. For this reason, tailored and seamless drug delivery systems represent the new frontier of precision medicine. This work introduces a wireless platform to release drug delivery on demand from a sustainable thin and flexible piezoelectric chitosan film, which can be safely activated by medical ultrasound. The system can be potentially applied to release drugs in deep body compartments without invasive procedures. Films are loaded with an antineoplastic drug and its release is studied with two different sources of ultrasound stimuli. These results represent a strategic starting point for wireless, non-invasive and sustainable drug delivery approaches.

5:00 Biodegradable PEDOT: PSS-Wax Electronics for Electrical Sensing of Soil Microbial Activity
Eloise Bihar (State University of New York at Buffalo, USA)

Monitoring soil microbial activity is essential for assessing soil health, yet most existing methods rely on indirect laboratory assays that cannot provide real-time, in-situ measurements. In this work, we present a biodegradable printed sensor that converts microbial wax decomposition in soil into an electrical signal. The device uses a PEDOT: PSS-beeswax composite designed as a sacrificial substrate for wax-degrading microorganisms. As microbes consume the wax phase, increased water penetration alters the conductive network and produces measurable resistance changes. Sensor response follows temperature-dependent biological activity, with resistance increases of ~21.2R₀ over 6 days at 35 °C.

Thursday, June 18 5:20 - 6:00

Awards Announcement

Room: Mesa A, Mesa B

Thursday, June 18 6:00 - 6:45

Workshop 3 - RFID Jepardy

Room: Mesa A, Mesa B