arXiv subjects

Danijela Cabric

Publications and source records attributed to Danijela Cabric.

At least 19 recordsLinked to original sources

arXiv2026

Sparse Bayesian Learning Algorithms Revisited: From Learning Majorizers to Structured Algorithmic Learning using Neural Networks

Sparse Bayesian Learning is one of the most popular sparse signal recovery methods, and various algorithms exist under the SBL paradigm. However, given a performance metric and a sparse recovery problem, it is difficult to know a-priori the best algorithm to choose. This difficulty is in part due to a lack of a unified framework to derive SBL algorithms. We address this issue by first showing that the most popular SBL algorithms can be derived using the majorization-minimization (MM) principle, providing hitherto unknown convergence guarantees to this class of SBL methods. Moreover, we show that the two most popular SBL update rules not only fall under the MM framework but are both valid descent steps for a common majorizer, revealing a deeper analytical compatibility between these algorithms. Using this insight and properties from MM theory we expand the class of SBL algorithms, and address finding the best SBL algorithm via data within the MM framework. Second, we go beyond the MM framework by introducing the powerful modeling capabilities of deep learning to further expand the class of SBL algorithms, aiming to learn a superior SBL update rule from data. We propose a novel deep learning architecture that can outperform the classical MM based ones across different sparse recovery problems. Our architecture's complexity does not scale with the measurement matrix dimension, hence providing a unique opportunity to test generalization capability across different matrices. For parameterized dictionaries, this invariance allows us to train and test the model across different parameter ranges. We also showcase our model's ability to learn a functional mapping by its zero-shot performance on unseen measurement matrices. Finally, we test our model's performance across different numbers of snapshots, signal-to-noise ratios, and sparsity levels.

eess.SP↗

arXiv2026

Homomorphic Directional Beamforming with Analog True Time Delay Arrays

Recently, true-time-delay (TTD) arrays, also referred to as joint phase-time arrays (JPTA), have been investigated for low-cost frequency-dependent beamforming capabilities to enable various applications, including beam-squint correction, fast beam training, and serving multiple user equipment (UE)s by frequency band to direction mapping, termed as split beampatterns. Several heuristics and optimization-based solutions have been proposed to determine TTD array parameters settings. However, they have practical limitations due to either computationally demanding optimization procedures, requirements for extremely large memory look-up tables, or degradations due to the beam-squint effect. In this article, we propose a novel split-beampattern generation algorithm based on the observed homomorphism between TTD array configuration matrices and corresponding beampatterns. First, we rigorously analyze the beampattern synthesis process and demonstrate the observed homomorphism and mathematical structure. Then, we propose the Homomorphic Directional Beamforming (HDB) algorithm to approximate the desired split beampatterns by utilizing a generator beampattern dictionary that requires a dictionary size orders of magnitude lower than existing approaches without ignoring the beam squint. With extensive simulations, we show that the proposed algorithm can provide a practical implementation with low memory and low computational cost requirements. In addition, HDB design provides close to uniform beamforming gains among UEs in different subbands, enabling fairness in power allocation.

eess.SP↗

arXiv2026

The Radon Transform, True Time Delay Beamforming, and Ultra-Wideband Antenna Arrays (Invited Paper)

The FR3 band has emerged as the major focus of 6G wireless research. FR3 cellular operation presents the challenge of extreme bandwidth combined with physically large antenna arrays. In this regime, conventional phase-shift beamforming entails a loss of coherence (beam-squint), and has to be replaced by true time delay beamforming (TTD). It happens that TTD is mathematically equivalent to taking the Radon transform of the space/time measurements. We exploit fifty years of research in the application of the Radon transform to computer tomography and to seismic exploration to elucidate the workings of TTD. We use the Radon transform combined with semblance detection and Radon slowness filtering to remove far-field signals from the measured space/time signals from a linear array, leaving only near-field signals. In turn we partition the array into sub-arrays. For each sub-array we estimate, via the semblance Radon transform, the angles-of-arrival of the near-field signals. We then use triangulation to estimate the coordinates of the near-field sources. Finally we integrate the original space/time data along hyperbolic trajectories to extract the individual near-field signal envelopes.

eess.SP↗

arXiv2025

Millimeter-Wave True-Time Delay Array Beamforming with Robustness to Mobility

Ultra-reliable and low-latency connectivity is required for real-time and latency-sensitive applications, like wireless augmented and virtual reality streaming. Millimeter-wave (mmW) networks have enabled extremely high data rates through large available bandwidths but struggle to maintain continuous connectivity with mobile users. Achieving the required beamforming gain from large antenna arrays with minimal disruption is particularly challenging with fast-moving users and practical analog mmW array architectures. In this work, we propose frequency-dependent slanted beams from true-time delay (TTD) analog arrays to achieve robust beamforming in wideband, multi-user downlink scenarios. Novel beams with linear angle-frequency relationships for different users and sub-bands provide a trade-off between instantaneous capacity and angular coverage. Compared to alternative analog array beamforming designs, slanted beams provide higher reliability to angle offsets and greater adaptability to varied user movement statistics.

eess.SP↗

arXiv2024

A Coordinate Descent Approach to Atomic Norm Denoising

Atomic norm minimization is of great interest in various applications of sparse signal processing including super-resolution line-spectral estimation and signal denoising. In practice, atomic norm minimization (ANM) is formulated as semi-definite programming (SDP) that is generally hard to solve. This work introduces a low-complexity solver for a type of ANM known as atomic norm soft thresholding (AST). The proposed method uses the framework of coordinate descent and exploits the sparsity-inducing nature of atomic-norm regularization. Specifically, this work first provides an equivalent, non-convex formulation of AST. It is then proved that applying a coordinate descent algorithm on the non-convex formulation leads to convergence to the global solution. For the case of a single measurement vector of length N and complex exponential basis, the complexity of each step in the coordinate descent procedure is O(N log N ), rendering the method efficient for large-scale problems. Through simulations, the proposed solver is shown to be faster than alternating direction method of multiplier (ADMM) or customized interior point SDP solver if the problems are sparse. It is demonstrated that the coordinate descent solver can be modified for AST with multiple dimensions and multiple measurement vectors as well as a variety of general basis.

eess.SP↗

arXiv2024

GAN-RXA: A Practical Scalable Solution to Receiver-Agnostic Transmitter Fingerprinting

Radio frequency fingerprinting has been proposed for device identification. However, experimental studies also demonstrated its sensitivity to deployment changes. Recent works have addressed channel impacts by developing robust algorithms accounting for time and location variability, but the impacts of receiver impairments on transmitter fingerprints are yet to be solved. In this work, we investigate the receiver-agnostic transmitter fingerprinting problem, and propose a novel two-stage supervised learning framework (RXA) to address it. In the first stage, our approach calibrates a receiver-agnostic transmitter feature-extractor. We also propose two deep-learning approaches (SD-RXA and GAN-RXA) in this first stage to improve the receiver-agnostic property of the RXA framework. In the second stage, the calibrated feature-extractor is utilized to train a transmitter classifier with only one receiver. We evaluate the proposed approaches on the transmitter identification problem using a large-scale WiFi dataset. We show that when a trained transmitter-classifier is deployed on new receivers, the RXA framework can improve the classification accuracy by 19.5%, and the outlier detection ROC AUC by 12.0% compared to a naive approach without calibration. Moreover, GAN-RXA can further increase the closed-set classification accuracy by 5.0%, and the outlier detection ROC AUC by 12.5% compared to the RXA approach.

eess.SP↗

arXiv2023

Structured Two-Stage True-Time-Delay Array Codebook Design for Multi-User Data Communication

Wideband millimeter-wave and terahertz (THz) systems can facilitate simultaneous data communication with multiple spatially separated users. It is desirable to orthogonalize users across sub-bands by deploying frequency-dependent beams with a sub-band-specific spatial response. True-Time-Delay (TTD) antenna arrays are a promising wideband architecture to implement sub-band-specific dispersion of beams across space using a single radio frequency (RF) chain. This paper proposes a structured design of analog TTD codebooks to generate beams that exhibit quantized sub-band-to-angle mapping. We introduce a structured Staircase TTD codebook and analyze the frequency-spatial behaviour of the resulting beam patterns. We develop the closed-form two-stage design of the proposed codebook to achieve the desired sub-band-specific beams and evaluate their performance in multi-user communication networks.

eess.SP↗

arXiv2023

Deep Learning Based Active Spatial Channel Gain Prediction Using a Swarm of Unmanned Aerial Vehicles

Prediction of wireless channel gain (CG) across space is a necessary tool for many important wireless network design problems. In this paper, we develop prediction methods that use environment-specific features, namely building maps and CG measurements, to achieve high prediction accuracy. We assume that measurements are collected using a swarm of coordinated unmanned aerial vehicles (UAVs). We develop novel active prediction approaches which consist of both methods for UAV path planning for optimal measurement collection and methods for prediction of CG across space based on the collected measurements. We propose two active prediction approaches based on deep learning (DL) and Kriging interpolation. The first approach does not rely on the location of the transmitter and utilizes 3D maps to compensate for the lack of it. We utilize DL to incorporate 3D maps into prediction and reinforcement learning for optimal path planning for the UAVs based on DL prediction. The second active prediction approach is based on Kriging interpolation, which requires known transmitter location and cannot utilize 3D maps. We train and evaluate the two proposed approaches in a ray-tracing-based channel simulator. Using simulations, we demonstrate the importance of active prediction compared to prediction based on randomly collected measurements of channel gain. Furthermore, we show that using DL and 3D maps, we can achieve high prediction accuracy even without knowing the transmitter location. We also demonstrate the importance of coordinated path planning for active prediction when using multiple UAVs compared to UAVs collecting measurements independently in a greedy manner.

eess.SP↗

arXiv2023

REM-U-net: Deep Learning Based Agile REM Prediction with Energy-Efficient Cell-Free Use Case

Radio environment maps (REMs) hold a central role in optimizing wireless network deployment, enhancing network performance, and ensuring effective spectrum management. Conventional REM prediction methods are either excessively time-consuming, e.g., ray tracing, or inaccurate, e.g., statistical models, limiting their adoption in modern inherently dynamic wireless networks. Deep-learning-based REM prediction has recently attracted considerable attention as an appealing, accurate, and time-efficient alternative. However, existing works on REM prediction using deep learning are either confined to 2D maps or use a limited dataset. In this paper, we introduce a runtime-efficient REM prediction framework based on u-nets, trained on a large-scale 3D maps dataset. In addition, data preprocessing steps are investigated to further refine the REM prediction accuracy. The proposed u-net framework, along with preprocessing steps, are evaluated in the context of the 2023 IEEE ICASSP Signal Processing Grand Challenge, namely, the First Pathloss Radio Map Prediction Challenge. The evaluation results demonstrate that the proposed method achieves an average normalized root-mean-square error (RMSE) of 0.045 with an average of 14 milliseconds (ms) runtime. Finally, we position our achieved REM prediction accuracy in the context of a relevant cell-free massive multiple-input multiple-output (CF-mMIMO) use case. We demonstrate that one can obviate consuming energy on large-scale fading measurements and rely on predicted REM instead to decide on which sleep access points (APs) to switch on in a CF-mMIMO network that adopts a minimum propagation loss AP switch ON/OFF strategy.

cs.NI↗

arXiv2023

RadYOLOLet: Radar Detection and Parameter Estimation Using YOLO and WaveLet

Detection of radar signals without assistance from the radar transmitter is a crucial requirement for emerging and future shared-spectrum wireless networks like Citizens Broadband Radio Service (CBRS). In this paper, we propose a supervised deep learning-based spectrum sensing approach called RadYOLOLet that can detect low-power radar signals in the presence of interference and estimate the radar signal parameters. The core of RadYOLOLet is two different convolutional neural networks (CNN), RadYOLO and Wavelet-CNN, that are trained independently. RadYOLO operates on spectrograms and provides most of the capabilities of RadYOLOLet. However, it suffers from low radar detection accuracy in the low signal-to-noise ratio (SNR) regime. We develop Wavelet-CNN specifically to deal with this limitation of RadYOLO. Wavelet-CNN operates on continuous Wavelet transform of the captured signals, and we use it only when RadYOLO fails to detect any radar signal. We thoroughly evaluate RadYOLOLet using different experiments corresponding to different types of interference signals. Based on our evaluations, we find that RadYOLOLet can achieve 100% radar detection accuracy for our considered radar types up to 16 dB SNR, which cannot be guaranteed by other comparable methods. RadYOLOLet can also function accurately under interference up to 16 dB SINR.

eess.SP↗

arXiv2023

ProSpire: Proactive Spatial Prediction of Radio Environment Using Deep Learning

Spatial prediction of the radio propagation environment of a transmitter can assist and improve various aspects of wireless networks. The majority of research in this domain can be categorized as 'reactive' spatial prediction, where the predictions are made based on a small set of measurements from an active transmitter whose radio environment is to be predicted. Emerging spectrum-sharing paradigms would benefit from 'proactive' spatial prediction of the radio environment, where the spatial predictions must be done for a transmitter for which no measurement has been collected. This paper proposes a novel, supervised deep learning-based framework, ProSpire, that enables spectrum sharing by leveraging the idea of proactive spatial prediction. We carefully address several challenges in ProSpire, such as designing a framework that conveniently collects training data for learning, performing the predictions in a fast manner, enabling operations without an area map, and ensuring that the predictions do not lead to undesired interference. ProSpire relies on the crowdsourcing of transmitters and receivers during their normal operations to address some of the aforementioned challenges. The core component of ProSpire is a deep learning-based image-to-image translation method, which we call RSSu-net. We generate several diverse datasets using ray tracing software and numerically evaluate ProSpire. Our evaluations show that RSSu-net performs reasonably well in terms of signal strength prediction, 5 dB mean absolute error, which is comparable to the average error of other relevant methods. Importantly, due to the merits of RSSu-net, ProSpire creates proactive boundaries around transmitters such that they can be activated with 97% probability of not causing interference. In this regard, the performance of RSSu-net is 19% better than that of other comparable methods.

cs.NI↗

arXiv2022

Multiband Massive IoT: A Learning Approach to Infrastructure Deployment

We consider a novel ultra-narrowband (UNB) low-power wide-area network (LPWAN) architecture design for uplink transmission of a massive number of Internet of Things (IoT) devices over multiple multiplexing bands. An IoT device can randomly choose any of the multiplexing bands to transmit its packet. Due to hardware constraints, a base station (BS) is able to listen to only one multiplexing band. Our main objective is to maximize the packet decoding probability (PDP) by optimizing the placement of the BSs and frequency assignment of BSs to multiplexing bands. We develop two online approaches that adapt to the environment based on the statistics of (un)successful packets at the BSs. The first approach is based on a predefined model of the environment, while the second approach is measurement-based model-free approach, which is applicable to any environment. The benefit of the model-based approach is a lower training complexity, at the risk of a poor fit in a model-incompatible environment. The simulation results show that our proposed approaches to band assignment and BS placement offer significant improvement in PDP over baseline random approaches and perform closely to the theoretical upper bound.

eess.SP↗

arXiv2022

Machine Learning Prediction for Phase-less Millimeter-Wave Beam Tracking

Future wireless networks may operate at millimeter-wave (mmW) and sub-terahertz (sub-THz) frequencies to enable high data rate requirements. While large antenna arrays are critical for reliable communications at mmW and sub-THz bands, these antenna arrays would also mandate efficient and scalable initial beam alignment and link maintenance algorithms for mobile devices. Low-power phased-array architectures and phase-less power measurements due to high frequency oscillator phase noise pose additional challenges for practical beam tracking algorithms. Traditional beam tracking protocols require exhaustive sweeps of all possible beam directions and scale poorly with high mobility and large arrays. Compressive sensing and machine learning designs have been proposed to improve measurement scaling with array size but commonly degrade under hardware impairments or require raw samples respectively. In this work, we introduce a novel long short-term memory (LSTM) network assisted beam tracking and prediction algorithm utilizing only phase-less measurements from fixed compressive codebooks. We demonstrate comparable beam alignment accuracy to state-of-the-art phase-less beam alignment algorithms, while reducing the average number of required measurements over time.

eess.SP↗

arXiv2022

Distributed Transmit Beamforming: Analyzing the Maximum Communication Range

Distributed transmit beamforming is a technique that adjusts the signals from cooperating radios to combine coherently at a destination radio. To achieve coherent combining, the radios can exchange preambles with the destination for frequency synchronization and signal phase adjustment. At the destination, coherent combining leads to a beamforming (BF) gain. The BF gain can extend the communication range by countering the path loss that increases with the distance from the destination. While ideally the maximum range can be trivially calculated from the BF gain, in reality, the BF gain depends on the distance because, at a larger distance, lower SNR of the exchanged preambles causes higher synchronization and phase estimation errors, which in turn degrades the BF gain. In this paper, considering the BF gain degradation for a destination-led BF protocol, we calculate the maximum communication range to realize a desired post-BF SNR by analyzing the relation between the pre-BF SNR and the BF gain. We show that increasing the preamble lengths or increasing the destination power can significantly increase the maximum range while just increasing the number of radios gives diminishing range extension.

eess.SP↗

arXiv2022

Energy Efficiency Tradeoffs for Sub-THz Multi-User MIMO Base Station Receivers

Sub-terahertz (sub-THz) antenna array architectures significantly impact power usage and communications capacity in multi-user multiple-input multiple-output (MU-MIMO) systems. In this work, we compare the energy efficiency and spectral efficiency of three MU-MIMO capable array architectures for base station receivers. We provide a sub-THz circuits power analysis, based on our review of state-of-the-art D-band and G-band components, and compare communications capabilities through wideband simulations. Our analysis reveals that digital arrays can provide the highest spectral efficiency and energy efficiency, due to the high power consumption of sub-THz active phase shifters or when SNR and system spectral efficiency requirements are high.

eess.SP↗

arXiv2022

Rainbow-link: Beam-Alignment-Free and Grant-Free mmW Multiple Access using True-Time-Delay Array

The millimeter-wave (mmW) communications is a key enabling technology in 5G to provide ultra-high throughput. Current mmW technologies rely on analog phased arrays to realize beamforming gain and overcome high path loss. However, due to a limited number of simultaneous beams that can be created with analog/hybrid phased antenna arrays, the overheads of beam training and beam scheduling become a bottleneck for emerging networks that need to support a large number of users and low latency applications. This paper introduces rainbow-link, a novel multiple access protocol, that can achieve low latency and massive connectivity by exploiting wide bandwidth at mmW frequencies and novel analog true-time-delay array architecture with frequency dependent beamforming capability. In the proposed design, the network infrastructure is equipped with the true-time-delay array to simultaneously steer different frequency resource blocks towards distinct directions covering the entire cell sector. Users or devices, equipped with a narrowband receiver and either a single antenna or small phased antenna array, connect to the network based on their angular positions by selecting frequency resources within their rainbow beam allocation. Rainbow-link is combined with a contention-based grant-free access to eliminate the explicit beam training and user scheduling. The proposed design and analysis show that rainbow-link grant-free access is a potential candidate for latency-critical use cases within massive connectivity. Our results show that, given less than 1e-5 probability of packet loss, a rainbow-link cell, over 1 GHz bandwidth using 64 element antenna array, attains sub-millisecond user-plane latency and Mbps user rates with an approximate 400m line-of-sight coverage and a density of up to 5 active single antenna users per second per meter square.

eess.SP↗

arXiv2022

Destination-Feedback Free Distributed Transmit Beamforming using Guided Directionality

Distributed transmit beamforming enables cooperative radios to act as one virtual antenna array, extending their communications' range beyond the capabilities of a single radio. Most existing distributed beamforming approaches rely on the destination radio sending feedback to adjust the transmitters' signals for coherent combining. However, relying on the destination radio's feedback limits the communications range to that of a single radio. Existing destination-feedback-free approaches rely on phase synchronization and knowing the node locations with sub-wavelength accuracy, which becomes impractical for radios mounted on high-mobility platforms like UAVs. In this work, we propose and demonstrate a destination-feedback-free distributed beamforming approach that leverages the radio's mobility and coarse location information in a dominant line-of-sight channel. In the proposed approach, one radio acts as a guide and moves to point the beam of the remaining radios towards the destination. We specify the radios' position requirements and verify their relation to the combined signal at the destination using simulations. A proof of concept demo was implemented using software defined radios, showing up to 9dB SNR improvement in the beamforming direction just by relying on the coarse placement of four radios.

eess.SP↗

arXiv2022

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

RF fingerprinting leverages circuit-level variability of transmitters to identify them using signals they send. Signals used for identification are impacted by a wireless channel and receiver circuitry, creating additional impairments that can confuse transmitter identification. Eliminating these impairments or just evaluating them, requires data captured over a prolonged period of time, using many spatially separated transmitters and receivers. In this paper, we present WiSig; a large scale WiFi dataset containing 10 million packets captured from 174 off-the-shelf WiFi transmitters and 41 USRP receivers over 4 captures spanning a month. WiSig is publicly available, not just as raw captures, but as conveniently pre-processed subsets of limited size, along with the scripts and examples. A preliminary evaluation performed using WiSig shows that changing receivers, or using signals captured on a different day can significantly degrade a trained classifier's performance. While capturing data over more days or more receivers limits the degradation, it is not always feasible and novel data-driven approaches are needed. WiSig provides the data to develop and evaluate these approaches towards channel and receiver agnostic transmitter fingerprinting.

eess.SP↗