Although Maxwell discovered the physical laws of electromagnetic waves about 160 years ago, accurately modeling the propagation of RF signals in large and complex electrical environments remains a persistent challenge. This complexity arises from the interactions between the RF signal and various obstacles, including reflection and diffraction. Inspired by the success of neural networks in mapping the optical field in computer vision, we introduce the neural radio-frequency radiance field, or$\mathbf{NeRF}^{2}$. This represents a continuous volumetric scene function that effectively models RF signal propagation. Remarkably, after only a sparse amount of training with signal measurements,$\mathbf{NeRF}^{2}$can accurately predict the nature and origin of signals received at any location, assuming the transmitter's position is known. Additionally, we propose the frequency-aware$\mathbf{NeRF}^{2}$to enhance channel prediction performance for wideband signals using an RF prism module. Compared to the vanilla$\mathbf{NeRF}^{2}$, the frequency-aware$\mathbf{NeRF}^{2}$achieves a 4 dB improvement in SNR for FDD OFDM channel estimation and is nearly 3.5 × faster. Functioning as a physical-layer neural network,$\mathbf{NeRF}^{2}$also supports application-layer artificial neural networks (ANNs) by generating synthetic training datasets. Our empirical results demonstrate that augmented sensing enhances the accuracy of AoA estimation, achieving an approximate 50% improvement.

Deep learning excels in advanced inference tasks using electronic neural networks (ENN), but faces energy consumption and limited computation speed challenges. To mitigate this, optical neural networks (ONNs) were developed, utilizing light for computations. However, their high manufacturing costs limited accessibility. In this work, we first introduce the binary optical neural network (BONN) - a streamlined ONN variant with binarized weights, which significantly reduces fabrication complexities and costs. Specifically, we address (i) the development of a binarization weight function aligned with backward-error propagation, and (ii) a simulation-based training for extra-large neural networks housing millions of neurons. We prototype six BONNs, each comprising four 0.8 × 0.8mm2 layers with one million 800 nm diameter neurons. Costs are cut to 0.13 USD per layer, marking a substantial decrease of 769× from previous ONNs. Experimental results reveal BONNs consume 2, 405× less power than leading ENNs while maintaining an average recognition accuracy of 74% across six datasets.

Conventional deep learning approaches for indoor localization often suffer from their reliance on high-quality training samples and display limited adaptability across varied scenarios. To address these challenges, we repurpose the Transformer model, celebrated for its profound contextual insights, to explore the underlying principles of indoor localization. Our microbenchmark results compellingly demonstrate the superiority of our approach, showing improvements of 30% to 70% across a diverse set of 50 scenarios compared to other state-of-the-art methods. In conclusion, we propose a specialized Generative Pre-training Transformer (GPT) variant, termed LocGPT, configured with 36 million parameters that are tailored to facilitate transfer learning. By fine-tuning this pre-trained model, we achieve near-par accuracy using merely half the conventional dataset, thereby heralding a pioneering stride in transfer learning within the indoor localization domain.

The emergence of high-precision indoor backscatter tag tracking in GPS-deprived environments has advanced applications from virtual reality to factory automation. Despite this, the high-precision tracking range remains limited to just a few meters, restricting the use of backscatters to the vicinity of checkpoints in warehouses, even though they possess a communication range of 50 m. We have identified that this limited localization range primarily originates from the butterfly effect in localization systems, where a slight phase measurement error gradually escalates into a substantial localization error. This article introduces two innovative phase estimation protocols to address the intrinsic challenges in achieving high-accuracy phase estimation over long-distance communication. The first, consistent phase estimator (CPE), resolves the$\boldsymbol {\pi }$-ambiguity commonly encountered with commercial radio-frequency identification readers. Building on this, CPE+ is designed to cancel flicker noise, neutral white noise, and restore spatial and temporal imbalances. Our experimental results demonstrate that CPE+ extends the range of accurate Angle of Arrival (AoA) estimation and centimeter-level localization from 8 to 15 m in stationary scenarios. It maintains decimeter-level accuracy across the entire 50-m communication range for CPE+ with two or more gateways. In dynamic scenarios, the error of CPE+ increases with tag speed, reaching a median localization error of 11.7 cm at 5 m for tag speeds of 50 cm/s.

Mobile payments have grown significantly recently, driven by their contactless feature that minimizes COVID-19 transmission risks. While NFC offers more security and convenience than barcodes and benefits those with amblyopia, many smartphones lack NFC due to module shortages or security decisions. In this work, we present${\sf MagCode}$, an innovative method connecting NFC readers with cameras, allowing users to enjoy NFC payment security using prevalent camera technology. At the heart of${\sf MagCode}$is the harmless magnetic interference on the CMOS image sensor of a smartphone placed nearby the NFC reader, resulting in a group of barcode-like stripes appearing on the captured images. We take advantage of these stripes to encode the data and achieve simplex communication from an NFC reader to an NFC-denied or NFC-disabled smartphone. In particular, we developed a comprehensive suite of protocols spanning from the physical layer to the transport layer, and we rigorously tested our proof-of-concept prototype on 11 different smart devices. Our extensive evaluations showcase a maximum throughput of 2.58 kbps–surpassing magnetometer-based alternatives by a factor of 58–and demonstrate an average data exchange time of 1.3 seconds for mobile payment transactions between an NFC reader and a smartphone.

Physical-layer identification uses manufacturing variations to create unique identifiers for each device. A decade ago, this concept was applied to RFID tags using backscatter frequency drift (BFD), a specific kind of ‘fingerprint’ determined by the difference between the actual backscatter signal received and the expected backscatter link frequency (BLF). However, BFD has been undervalued due to its low performance in tag identification, achieving less than 30% accuracy. In this study, we reevaluate BFD, focusing on the issue of frequency resolution as the cause of its poor performance. The problem doesn't lie in the BFD's uniqueness, but in the inferior way we measure the frequency of a backscatter signal, which is limited by the current air interface protocol. This situation is akin to trying to identify human fingerprints using low-quality imaging. We propose a practical solution to improve the frequency resolution from kilohertz to sub-hertz, without requiring hardware or protocol changes. Our findings show that this high-resolution BFD approach significantly enhances the distinguishability to 99.4% and the identification accuracy to 94% when tested on a dataset of 7,135 RFID tags across nine models.

Mobile payment has achieved explosive growth in recent years due to its contactless feature, which lowers the infection risk of COVID-19. In the market, near-field communication (NFC) and barcodes have become the de facto standard technologies for mobile payment. The NFC-based payment outperforms barcode-based payment in terms of security, usability, and convenience. It is especially more user-friendly for the amblyopia group. Unfortunately, NFC functionality is unavailable in nearly half of smartphones in the market nowadays due to the shortage of NFC modules or being disabled for security reasons.

Mobile payments have experienced a significant surge in recent years, primarily due to their contactless feature that mitigates the risk of COVID-19 transmission. In this landscape, NFC-based payment outperforms barcode-based payment in terms of security, usability, and convenience. It is especially more user-friendly for the amblyopic community. Unfortunately, NFC functionality is unavailable in nearly half of the smartphones in the market nowadays due to the shortage of NFC modules or being disabled for security reasons.

Although Maxwell discovered the physical laws of electromagnetic waves 160 years ago, how to precisely model the propagation of an RF signal in an electrically large and complex environment remains a long-standing problem. The difficulty is in the complex interactions between the RF signal and the obstacles (e.g., reflection, diffraction, etc.). Inspired by the great success of using a neural network to describe the optical field in computer vision, we propose a neural radio-frequency radiance field, NeRF2, which represents a continuous volumetric scene function that makes sense of an RF signal's propagation. Particularly, after training with a few signal measurements, NeRF2 can tell how/what signal is received at any position when it knows the position of a transmitter. As a physical-layer neural network, NeRF2 can take advantage of the learned statistic model plus the physical model of ray tracing to generate a synthetic dataset that meets the training demands of application-layer artificial neural networks (ANNs). Thus, we can boost the performance of ANNs by the proposed turbo-learning, which mixes the true and synthetic datasets to intensify the training. Our experiment results show that turbo-learning can enhance performance with an approximate 50% increase. We also demonstrate the power of NeRF2 in the field of indoor localization and 5G MIMO.

Physical-layer identification is to exploit inherent randomness introduced during manufacturing to endow a unique fingerprint to a physical entity. A classic fingerprint, called backscatter frequency drift (BFD), was explored a decade ago for the physical-layer identification of RFID tags. The BFD is defined as the offset between the frequency of the backscatter signal actually received from a tag and the requested backscatter link frequency (BLF). As a context-free fingerprint, the BFD is being seriously underestimated due to its terrible performance in tag classification or identification (e.g., accuracy < 30%). In this work, we revisit BFD from the perspective of frequency resolution to pinpoint the reason behind its underperformance. Namely, the low accuracy is not because BFD is insufficiently unique in nature but rather due to the low-resolution measurement of the frequency of a backscatter signal, which is mainly constrained by the current air interface protocol. This challenge is analogous to the recognition of human fingerprints via low-resolution and blurry imaging devices. To address this issue, we propose a practical solution to improve the frequency resolution from kHz to sub-Hz, without any modification of hardware or protocols. The results demonstrate the distinguishability of high-resolution BFD is significantly increased to 99.4% and the identification accuracy is raised to 94% when in the face of 7,135 RFID tags of nine models.

Cross-Technology Communication (CTC) is an emerging technology that enables physical-layer direct communication from a WiFi sender to other Internet of Things (IoT) receivers via waveform emulation. The previous works use the reverse engineering to find the appropriate WiFi payload that can emulate the waveform similar to the desired IoT packet in the format of the IoT protocol (e.g., ZigBee). Unfortunately, the reverse engineering approach suffers from many limitations, such as being non-reversible and unscalable, misaligning symbols, and over-relying on empiricism. In this work, we present XiTuXi, a one-size-fits-all solution to automatically achieve the CTC by taking advantage of the neural machine translation (NMT), inspired by the task comparability between CTC and homophony-based cross-linguistic communication. We employ a well-known NMT model called Transformer to learn the bit-sequence to bit-sequence translation rationale behind the CTC without human intervention. Particularly, we introduce the forward engineering to address the dilemma of acquiring training datasets. By using XiTuXi, we achieved the CTC with 30 protocol combinations (ie., 802.11b, g, n, ax, ah Å ZigBee, Bluetooth, LoRa, and Sigfox) effortlessly, which ultimately liberates the experts from previous tedious tasks.

Physical-layer identification aims to identify wireless devices during RF communication by exploiting the imperfections of their radio circuitry, i.e., hardware fingerprint. Previous work proposed several hardware fingerprints for RFIDs (e.g., TIE, ABD, PSD, etc). However, these proposed fingerprints suffer from either unscalability or acquisition inefficiency. This work presents RF-DNA, a new hardware fingerprint composed of millions of Dual Natural Attributes (DNA) organized in a helical structure, where a pair of DNA represents a tag's intrinsic response at some frequency. We take advantage of the frequency agnostic phenomenon that a commercial RFID tag can respond within a wider band than the regulated, to acquire 10X more features than previous fingerprints. At the heart of this work are the context-free acquisition approach to extracting DNA from backscatter signals; and the accurate DNA matching algorithm for verifying a tag's identity. A total of 160,000 RF-DNA instances were collected from 16,000 tags using a customized automatic acquisition system. We subsequently carried out large-scale experiments to test the identification accuracy of RF-DNA and previously proposed fingerprints. Our comprehensive evaluation reveals that RF-DNA can achieve a mean accuracy of 95.98%. In contrast, those of previous fingerprints fall to 60% below when in face of thousands of tags.

Estimating the angle-of-arrival (AoA) of an RF source by using a large-sized antenna array is a classical topic in wireless systems. However, AoA tracking systems are not yet used for Internet of Things (IoT) in the real world due to their unaffordable cost. Many efforts, such as a time-sharing array, emulated array, and sparse array, were recently made to cut the cost. This work introduces a log-spiral antenna belt ( LSAB ), a new novel sparse “planar array” that could estimate the AoA of an IoT device in 3D space by using a few antennas connected to a single timeshare channel. Unlike the conventional arrays, LSAB deploys antennas on a log-spiral-shaped belt in a non-linear manner, following the theory of minimum resolution redundancy newly discovered in this work. One physical 8 × 8 uniform planar array (UPA) and four logical sparse arrays, including LSAB , were prototyped to validate the theory and evaluate the performance of sparse arrays. The extensive benchmark demonstrates that the performance of LSAB was comparable to that of a UPA, with similar degree of resolution; and LSAB could provide over 40% performance improvement than existing sparse arrays. We also prototyped a second LSAB adapted to an RFID system for localizing RFID tags at centimeter-level accuracy.

Backscatter networks are becoming a promising solution for embedded sensing. In these networks, backscatter sensors are deeply implanted inside objects or living beings and form a deep backscatter network (DBN). The fundamental challenges in DBNs are the significant attenuation of the wireless signal caused by environmental materials (e.g., water and bodily tissues) and the miniature antennas of the implantable backscatter sensors, which prevent existing backscatter networks from powering sensors beyond superficial depths. This study presents RiCharge, a turbocharging solution that enables powering up and communicating with DBNs through a single augmented RF source, which allows existing backscatter sensors to serve DBNs at zero startup cost. The key contribution of RiCharge is the turbocharging algorithm that utilizes RF surges to induce constructive power surges at deep backscatter sensors in accordance with the FCC regulations, for overcoming the turn-on voltage barrier. RiCharge is implemented in commodity devices, and the evaluation result reveals that RiCharge can use only a single RF source to power up backscatter sensors at 60 m distance in the air (i.e., 10x longer than a commercial off-the-shelf reader) and 50 cm-depth under water (i.e., 2x deeper than the previous record).