Large Language Model (LLM) training is increasingly concentrated in homogeneous datacenters, while private data and underutilized GPUs across universities, laboratories, and edge sites remain difficult to use. This extended abstract presents preliminary results from a geo-distributed LLM training prototype that treats networking constraints as first-order design concerns. The prototype connects three heterogeneous GPU sites via cloud-hosted parameter servers, outbound-only gRPC streams, two-stage delta compression (INT8 quantization + Huffman coding, achieving up to 4× payload reduction), and fault-tolerant rejoin. In real deployments, GPT-2 Medium pretraining achieves stable loss reduction and reaches the target loss 15.2% faster in wall-clock time than the best tested baseline; Llama3-1B pretraining remains stable under larger communication pressure; and cross-site latency traces reveal site-dependent WAN spikes of up to 200s. These results motivate adaptive networking support for synchronization, compression, placement, telemetry, and recovery in geo-distributed LLM training.

5G and beyond cellular systems embrace the disaggregation of Radio Access Network (RAN) components, exemplified by the evolution of the fronthaul (FH) connection between cellular baseband and radio unit equipment. Crucially, synchronization over the FH is pivotal for reliable 5G services. In recent years, there has been a push to move these links to an Ethernet-based packet network topology, leveraging existing standards and ongoing research for Time-Sensitive Networking (TSN). However, TSN standards, such as Precision Time Protocol (PTP), focus on performance with little to no concern for security. This increases the exposure of the open FH to security risks. Attacks targeting synchronization mechanisms pose significant threats, potentially disrupting 5G networks and impairing connectivity. In this article, we demonstrate the impact of successful spoofing and replay attacks against PTP synchronization. We show how a spoofing attack is able to cause a production-ready O-RAN and 5G-compliant private cellular base station to catastrophically fail within 2 seconds of the attack, necessitating manual intervention to restore full network operations. To counter this, we design a Machine Learning (ML)-based monitoring solution capable of detecting various malicious attacks with over 97.5% accuracy.

Airborne Base Stations (ABSs) allow for flexible geographical allocation of network resources with dynamically changing load as well as rapid deployment of alternate connectivity solutions during natural disasters. Since the radio infrastructure is carried by unmanned aerial vehicles (UAVs) with limited flight time, it is important to establish the best location for the ABS without exhaustive field trials. This paper proposes a digital twin (DT)-guided approach to achieve this goal through the following key contributions: (i) Implementation of an interactive software bridge between two open-source DTs such that the same scene is evaluated with high fidelity across NVIDIA's Sionna and Aerial Omniverse Digital Twin (AODT), highlighting the unique features of each of these platforms for this allocation problem, (ii) Design of a back- propagation-based algorithm in Sionna for rapidly converging on the physical location of the UAVs, orientation of the antennas and transmit power to ensure efficient coverage across the swarm of the UAVs, and (iii) numerical evaluation in AODT for large network scenarios (50 UEs, 10 ABS) that identifies the environmental conditions in which there is agreement or divergence of performance results between these twins. Finally, (iv) we propose a resilience mechanism to provide consistent coverage to mission-critical devices and demonstrate a use case for bi-directional flow of information between the two DTs.

Automated warehouses involve robots that move across the floor, avoiding obstacles while remaining connected via an access point (AP) to a central controller that instructs the robots. The complex propagation environment and presence of metallic surfaces results in spotty coverage, which changes over time as the location of stored products and machinery changes. Thus, maintaining an assured connectivity to APs while performing navigation is a challenge, although it is needed to relay local sensor data from the robots to the controller and receive directions from the latter.$\rm{DARWIN}$, involves creating a digital twin of the warehouse for training the robots by jointly optimizing the navigation and avoiding wireless dead-spots.$\rm{DARWIN}$has three key capabilities: First, it captures the features of both physical and RF environments in the digital world. Second, it allows real-time updating of the digital twin if significant disparity is detected compared to the physical environment. Finally, it includes a reinforcement learning algorithm that jointly optimizes navigation and network resource management, while accounting for handover and outage. We validate$\rm{DARWIN}$on an emulation environment consisting of Robot Operating System and Gazebo platforms along with real-world RF measurements. Results reveal that$\rm{DARWIN}$reduces the number of steps by 43% compared to choosing the closest AP, while detecting environmental changes with maximum 96% accuracy to maintain a high-fidelity digital twin.

Artificial Intelligence (AI)-native receivers provide lower bit error rate (BER) compared to the traditional receiver, if they are deployed on the same data distribution as their training set. A major research problem is the uncertainty of whether a particularly trained AI-native receiver maintains its superior performance over the traditional receiver in different deployment environments. To this end, we propose VERITAS as a joint measurement-recovery post deployment framework for AI-native transceivers that continuously looks for distribution shifts in the received pilots and triggers finite re-training spurts. VERITAS leverages a novel out-of-distribution algorithm to detect potential changes in the channel profile, transmitter speed, and delay spread. As soon as such a change is detected, a traditional (reference) receiver is activated, which runs for a period of time in parallel to the AI-native receiver. Finally, VERTIAS compares the bit probabilities of the AI-native and the reference receivers for the same received data inputs, and decides whether or not a retraining process needs to be initiated. Our evaluations reveal that VERITAS can detect changes in the channel profile, transmitter speed, and delay spread with 99%, 97%, and 78% accuracies, respectively, followed by timely initiation of retraining for 86%, 93.3%, and 94.8% of inputs in channel profile, transmitter speed, and delay spread test sets, respectively.

Advanced beamforming techniques enable stable vehicular communication and address mmWave limitations by accurately directing the signal. However, traditional beamforming techniques struggle in high-speed vehicles due to time-intensive codebook processing and image-based feedback adjustments. Multi-modal beamforming using real-time data like GPS, cameras, and LiDAR to train the Deep Learning (DL) models can provide adaptive beam steering, improving reliability in dynamic conditions. Despite this, centralized systems involving large raw data transmission are vulnerable to saturation and malicious interference, and they neglect privacy concerns, necessitating a new framework. This paper proposes a novel federated attentionbased fusion learning framework named FedAttention for multimodal beamforming in the Internet-of-Vehicle (IoV). FedAttention further improves the model generalization ability by utilizing the CNN-Transformer architecture and making full use of the Multi-access Edge Computing (MEC) servers for the potential federated split learning to enhance efficiency. Based on the realworld datasets, FedAttention achieves 98.16 % in Top-5 accuracy and 82.09 % in Top-1 accuracy, a 26.86 % improvement compared to the current FLASH framework with less wall clock time, showing its training efficiency and robustness.

Mobile Robots (MRs), typically equipped with single-antenna radios, face many challenges in maintaining reliable connectivity established by multiple wireless access points (APs). These challenges include the absence of direct line-of-sight (LoS), ineffective beam searching due to the time-varying channel, and interference constraints. This paper presents REMARKABLE, an online learning based adaptive beam selection strategy for robot connectivity that trains kernelized bandit model directly in real-world settings of a factory floor. REMARKABLE employs reconfigurable intelligent surfaces (RISs) with passive reflective elements to create beamforming toward target robots, eliminating the need for multiple APs. We develop a method to create a beamforming codebook, reducing the search space complexity. We also develop a reconfigurable rotational mechanism to expand RIS coverage by rotating its projection plane. To address non-stationary conditions, we adopt the bandit over bandit idea that employs adaptive restarts, allowing the system to forget outdated observations and safely relearn the optimal interference-constrained beam. We show that our approach achieves a dynamic regret and the violation bound of Õ(T3/4B1/4) where T is the total time, and B is the total variation budget which captures the total changes in the environment without even assuming the knowledge of B. Finally, experimental validation with custom-designed RIS hardware and mobile robots demonstrates 46.8% faster beam selection and 94.2% accuracy, outperforming classical methods across diverse mobility settings.

We present a passive reconfigurable intelligent surface (RIS)-assisted beamforming system operating at 900 MHz, enhanced with vision-based environmental sensing for real-time adaptation of the reflected beam direction. In our setup, the RIS enables signals from a given transmitter to reach a mobile user by setting the appropriate weights for the RIS elements in real time. To handle dynamic conditions, we deploy an 8-bit Integer (INT8) quantized Convolutional Neural Network (CNN) at the receiver smartphone that utilizes images from the camera to infer the optimal RIS beam index given the transient angular difference between the RIS and the smartphone. By using such an out-of-modality image sensor, we avoid an exhaustive search through the entire codebook of beams. We demonstrate the system on Qualcomm's Snapdragon 8 Gen 3 mobile platform hardware with CNN optimization through the open source AI Model Efficiency Toolkit (AIMET). Our demo reveals that carefully optimized machine learning models at the network edge can enable low-latency and computationally efficient RIS beamforming for practical wireless deployments.

The dynamic nature of wireless environments presents significant challenges for machine learning (ML) models in real-world radio frequency applications, where impairments such as noise, fading, and frequency shifts disrupt performance. To address these challenges and build trust in ML models, we present Augmented Input Resilience Analysis (AURA), a test framework designed for IQ-based RF models to rigorously assess ML model performance by simulating RF impairments and identifying critical vulnerabilities. AURA systematically applies test-time augmentations to provide a detailed examination of model strengths and weaknesses. Key contributions include (1) Score-CAM adapted to 1D IQ in time and a frequency-selective variant to localize spectral features, and (2) embedding similarity evaluation to quantify distribution shifts caused by impairments. By integrating these methods, AURA enhances interpretability, promoting trust in ML decision-making. We demonstrate AURA's utility in exposing critical vulnerabilities in well-cited models, such as over-reliance on power-based features, including instances where random noise is misclassified as a legitimate signal with 99.7% accuracy. AURA also evaluates remediation strategies, such as noise classes, which reduce misclassifications to less than 1% in the noise augmentation case. This framework aims to advance the design of trustworthy and resilient AI-driven systems for future RF ML technologies.

Industry adoption of Artificial Intelligence (AI)-native wireless receivers, or even modular, Machine Learning (ML)-aided wireless signal processing blocks, has been slow. The main concern is the lack of explainability of these trained ML models and the significant risks posed to network functionalities in case of failures, especially since (i) testing on every exhaustive case is infeasible and (ii) the data used for model training may not be available. This paper proposes ATLAS, an AI-guided approach that generates a battery of tests for pre-trained AI-native receiver models and benchmarks the performance against a classical receiver architecture. Using gradient-based optimization, it avoids spanning the exhaustive set of all environment and channel conditions; instead, it generates the next test in an online manner to further probe specific configurations that offer the highest risk of failure. We implement and validate our approach by adopting the well-known DeepRx AI-native receiver model as well as a classical receiver using differentiable tensors in NVIDIA’s Sionna environment. ATLAS uncovers specific combinations of mobility, channel delay spread, and noise, where fully and partially trained variants of AI-native DeepRx perform suboptimally compared to the classical receivers. Our proposed method reduces the number of tests required per failure found by 19% compared to grid search for a 3-parameters input optimization problem, demonstrating greater efficiency. In contrast, the computational cost of the grid-based approach scales exponentially with the number of variables, making it increasingly impractical for high-dimensional problems.

Effective channel estimation (CE) is critical for optimizing the performance of 5G New Radio (NR) systems, particularly in dynamic environments where traditional methods struggle with complexity and adaptability. This paper introduces GraphNet, a novel, lightweight Graph Neural Network (GNN)-based estimator designed to enhance CE in 5G NR. Our proposed method utilizes a GNN architecture that minimizes computational overhead while capturing essential features necessary for accurate CE. We evaluate GraphNet across various channel conditions, from slow-varying to highly dynamic environments, and compare its performance to ChannelNet, a well-known deep learning-based CE method. GraphNet not only matches ChannelNet’s performance in stable conditions but significantly outperforms it in high-variation scenarios, particularly in terms of Block Error Rate. It also includes built-in noise estimation that enhances robustness in challenging channel conditions. Furthermore, its significantly lighter computational footprint makes GraphNet highly suitable for real-time deployment, especially on edge devices with limited computational resources. By underscoring the potential of GNNs to transform CE processes, GraphNet offers a scalable and robust solution that aligns with the evolving demands of 5G technologies, highlighting its efficiency and performance as a next-generation solution for wireless communication systems.

Machine learning (ML) models trained on synthetic waveform data frequently fail to generalize when deployed over the air (OTA), where unpredictable channel impairments—such as carrier frequency offset (CFO) and varying signal-to-noise ratio (SNR)—alter signal characteristics in ways not captured by controlled lab environments. In this paper, we systematically isolate and examine two principal drivers of this simulation-to-real gap: CFO and SNR degradation. We conduct tightly controlled OTA experiments using physically-induced frequency mismatches and two distinct methods of lowering SNR (transmit-side attenuation versus noise-floor elevation) to reveal how each approach affects classification accuracy in a simple convolutional neural network. Our results show that frequency-shift augmentation significantly improves CFO robustness, and augmenting the training data with broader SNR ranges yields up to a 39% increase in accuracy at 0dB over a baseline model. Surprisingly, the same classification trends appear when lowering SNR either by reducing transmit power or injecting Gaussian noise, underscoring that the net SNR range, rather than the mechanism of achieving it, primarily governs model performance. Finally, we publicly release our OTA datasets to encourage reproducible experimentation and continued refinement of RF data augmentation strategies.

In Vehicle-to-Everything (V2X) communication, advanced beamforming techniques address signal attenuation caused by mmWave, which provides high bandwidth and low latency. Multi-modal beamforming using Federated Learning (FL) can leverage resources like GPS, Lidar, and image data, significantly accelerating beam searching while enhancing data privacy. The heterogeneity of vehicles, however, affects the availability of computing resources for training machine learning models. Moreover, the multi-modal fusion network may contain billions of parameters, leading to extended training time for FL. To address these challenges, this paper proposes a novel Deep Reinforced Federated Split Learning framework (DRFSL) tailored for multi-modal beamforming with different sub-model architectures. DRFSL efficiently utilizes MEC computing and adapts the collaborative and distributed training to dynamic network conditions and system heterogeneity by incorporating deep reinforcement learning and split learning with FL. Experimental evaluation using real-world datasets demonstrates that DRFSL minimizes average training time by 49.45% and inference time by 24.43% and can achieve higher accuracy within the same timeframe compared to the existing FLASH framework.

Beamforming techniques use massive antenna arrays to formulate narrow Line-of-Sight signal sectors to address the increased signal attenuation in millimeter Wave (mmWave). However, traditional sector selection schemes involve extensive searches for the highest signal strength sector, introducing extra latency and communication overhead. This paper introduces a dynamic layer-wise and clustering-based federated learning (FL) algorithm for beam sector selection in autonomous vehicle networks called enhanced Dynamic Adaptive FL (eDAFL). The algorithm detects and selects the most important layers of a machine learning model for aggregation in FL process, significantly reducing network overhead and failure risks. eDAFL also consider an intra-cluster and inter-cluster approach to reduce overfitting and increase the abstraction level. We evaluate eDAFL on a real-world multi-modal dataset, demonstrating improved model accuracy by approximately 6.76% compared to existing methods, while reducing inference time by 84.04% and model size up to 52.20%.

Digital twins (DT) offer a low-overhead evaluation platform and the ability to generate rich datasets for training machine learning (ML) models before actual deployment. Specifically, for the scenario of ML-aided millimeter wave (mmWave) links between moving vehicles to roadside units, we show how DT can create an accurate replica of the real world for model training and testing. The contributions of this paper are twofold: First, we propose a framework to create a multimodal Digital Twin (DT), where synthetic images and LiDAR data for the deployment location are generated along with RF propagation measurements obtained via ray-tracing. Second, to ensure effective domain adaptation, we leveragemeta-learning, specificallyModel-Agnostic Meta-Learning(MAML), withtransfer learning(TL) serving as a baseline validation approach. The proposed framework is validated using a comprehensive dataset containing both real and synthetic LiDAR and image data for mmWave V2X beam selection. It also enables the investigation of how each sensor modality impacts domain adaptation, taking into account the unique requirements of mmWave beam selection. Experimental results show that models trained on synthetic data using transfer learning and meta-learning, followed by minimal fine-tuning with real-world data, achieve up to 4.09× and 14.04× improvements in accuracy, respectively. These findings highlight the potential of synthetic data and meta-learning to bridge the domain gap and adapt rapidly to real-world beamforming challenges.

In modern wireless network architectures, such as O-RAN, artificial intelligence (AI)-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control. The AI “apps” are selected on the basis of contextual information such as network conditions, topology, traffic statistics, and design goals. The mapping between context and AI model parameters is ideally done in a zero-shot fashion via an automatic model selection (AMS) mapping that leverages only contextual information without requiring any current data. This paper introduces a general methodology for the online optimization of AMS mappings. Optimizing an AMS mapping is challenging, as it requires exposure to data collected from many different contexts. Therefore, if carried out online, this initial optimization phase would be extremely time consuming. A possible solution is to leverage a digital twin of the physical system to generate synthetic data from multiple simulated contexts. However, given that the simulator at the digital twin is imperfect, a direct use of simulated data for the optimization of the AMS mapping would yield poor performance when tested in the real system. This paper proposes a novel method for the online optimization of AMS mapping that corrects for the bias of the simulator by means of limited real data collected from the physical system. Experimental results for a graph neural network-based power control app demonstrate the significant advantages of the proposed approach.

Adaptive receiver beamforming processors typically require expert design and can be limited by their convergence rate in data-starved applications. In this paper, we present a new type of machine learning beamformer using classification-based transfer learning (CBTL) to alleviate these limitations. The architecture consists of a pre-trained signal classifier, in our case a convolutional neural network, prepended by a beamforming layer. Narrowband beamforming weights are optimized by minimizing the classification loss, in turn nulling interference and amplifying a signal of interest (SOI). There are no requirements for calibration of the array, synchronization to the SOI, or training data modulated by the SOI. We describe the CBTL beamformer and demonstrate its effectiveness using several modulated signals. Simulated performance was compared to two well-established methods for blind source separation, and we achieved average signal-to-interference-plus-noise ratio gains of 3 to 9 dB when fewer than 100 samples were available from a 4-element array. The technique shows promise for applications where there is limited prior knowledge and few samples are available for beamformer estimation.

5G and beyond cellular networks promise remarkable advancements in bandwidth, latency, and connectivity. The emergence of Open Radio Access Network (O-RAN) represents a pivotal direction for the evolution of cellular networks, inherently supporting machine learning (ML) for network operation control. Within this framework, RAN Intelligence Controllers (RICs) from one provider can employ ML models developed by third-party vendors through the acquisition of key performance indicators (KPIs) from geographically distant base stations or user equipment (UE). Yet, the development of ML models hinges on the availability of realistic and robust datasets. In this study, we embark on a two-fold journey. First, we collect a comprehensive 5G dataset, harnessing real-world cell phones across diverse applications, locations, and mobility scenarios. Next, we replicate this traffic within a full-stack srsRAN-based O-RAN framework on Colosseum, the world's largest radio frequency (RF) emulator. This process yields a robust and O-RAN compliant KPI dataset mirroring real-world conditions. We illustrate how such a dataset can fuel the training of ML models and facilitate the deployment of xApps for traffic slice classification by introducing a CNN based classifier that achieves accuracy > 95% offline and 92% online. To accelerate research in this domain, we provide open-source access to our toolchain and supplementary utilities, empowering the broader research community to expedite the creation of realistic and O-RAN compliant datasets.

Open Radio Access Network (O-RAN) is positioned to play a pivotal role in shaping the future of telecommunications networks through open interfaces and virtualization, allowing interoperability between different vendors. As a key departure from single-operator managed RAN, a remote RAN intelligence controller (RIC) queries the gNB for the Key Performance Indicators (KPIs) that are required for making RAN control decisions, often leveraging advanced machine learning (ML) models. However, this repeated querying increases control traffic overhead on the so called E2 interface connecting the gNB to the RIC. To address this challenge, we utilize a method from Explainable Artificial Intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), which quantifies the contribution of each requested KPI to a model's prediction. Furthermore, we explore two different methods of choosing the most discriminative KPIs influencing model's performance, so that a smaller subset of KPIs may be queried, thus lowering the overhead on the E2 interface. Our analysis reveals that a model trained for the task of traffic classification using as input only the fraction of the top contributing KPIs identified by SHAP reduces control traffic overhead by up to 33% with only 7% reduction in ML classification accuracy.

Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this paradigm continues to spread, wireless systems must also evolve to identify active transmitters and unauthorized waveforms in real time under intentional distortion of preambles, extremely low signal-to-noise ratios and challenging channel conditions. We overcome limitations of correlation-based preamble matching methods in such conditions through the design of T-PRIME: a Transformer-based machine learning approach. T-PRIME learns the structural design of transmitted frames through its attention mechanism, looking at sequence patterns that go beyond the preamble alone. The paper makes three contributions: First, it compares Transformer models and demonstrates their superiority over traditional methods and state-of-the-art neural networks. Second, it rigorously analyzes T-PRIME’s real-time feasibility on DeepWave’s AIR-T platform. Third, it utilizes an extensive 66 GB dataset of over-the-air (OTA) WiFi transmissions for training, which is released along with the code for community use. Results reveal nearly perfect (i.e. > 98%) classification accuracy under simulated scenarios, showing 100% detection improvement over legacy methods in low SNR ranges, 97% classification accuracy for OTA single-protocol transmissions and up to 75% double-protocol classification accuracy in interference scenarios.

This paper presents COPILOT, a ML-based approach that allows vehicles requiring ubiquitous high bandwidth connectivity to identify the most suitable road side units (RSUs) through proactive handoffs. By cooperatively exchanging the data obtained from local 3D Lidar point clouds within adjacent vehicles and with coarse knowledge of their relative positions, COPILOT identifies transient blockages to all candidate RSUs along the path under study. Such cooperative perception is critical for choosing RSUs with highly directional links required for mmWave bands, which majorly degrade in the absence of LOS. COPILOT proposes three modules that operate in an inter-connected manner: (i) As an alternative to sending raw Lidar point clouds, it extracts and transmits low-dimensional intermediate features to lower the overhead of inter-vehicle messaging; (ii) It utilizes an attention-mechanism to place greater emphasis on data collected from specific vehicles, as opposed to nearest neighbor and distance-based selection schemes, and (iii) it experimentally validates the outcomes using an outdoor testbed composed of an autonomous car and Talon AD7200 60GHz routers emulating the RSUs, accompanied by the public release of the datasets. Results reveal COPILOT yields upto 69.8% and 20.42% improvement in latency and throughput compared to traditional reactive handoffs for mmWave networks, respectively.

While the open architecture, open interfaces, and integration of intelligence within Open Radio Access Network technology hold the promise of transforming 5G and 6G networks, they also introduce cybersecurity vulnerabilities that hinder its widespread adoption. In this paper, we conduct a thorough system-level investigation of cyber threats, with a specific focus on machine learning (ML) intelligence components known as xApps within the O-RAN's near-real-time RAN Intelligent Controller (near-RT RIC) platform. Our study begins by developing a malicious xApp designed to execute adversarial attacks on two types of test data - spectrograms and key performance metrics (KPMs), stored in the RIC database within the near-RT RIC. To mitigate these threats, we utilize a distillation technique that involves training a teacher model at a high softmax temperature and transferring its knowledge to a student model trained at a lower softmax temperature, which is deployed as the robust ML model within xApp. We prototype an over-the-air LTE/5G O-RAN testbed to assess the impact of these attacks and the effectiveness of the distillation defense technique by leveraging an ML-based Interference Classification (InterClass) xApp as an example. We examine two versions of InterClass xApp under distinct scenarios, one based on Convolutional Neural Networks (CNNs) and another based on Deep Neural Networks (DNNs) using spectrograms and KPMs as input data respectively. Our findings reveal up to 100% and 96.3% degradation in the accuracy of both the CNN and DNN models respectively resulting in a significant decline in network performance under considered adversarial attacks. Under the strict latency constraints of the near-RT RIC closed control loop, our analysis shows that the distillation technique outperforms classical adversarial training by achieving an accuracy of up to 98.3% for mitigating such attacks.

Open RAN (O-RAN) has the potential for revolutionizing not only cellular communication but also spectrum sensing by carefully controlling uplink/downlink traffic in shared spectrum bands. In this paper, we present the design ofSenseORAN, which detects the presence of radar pulses within the Citizens Broadband Radio Service (CBRS) band. SenseORAN is especially useful for scenarios where these pulses (highest priority) are fully overlapping with interfering LTE signals (secondary priority licensee), requiring immediate detection of such an occurrence. This design paradigm of re-using existing cellular infrastructure with ORAN-compliant sensing and communication slices can potentially eliminate the need for dedicated spectrum sensors along the coastline as well as severe restrictions on the transmit power for the LTE operators that are enforced today. Our approach involves a machine learning module deployed as aRadar Detection xAppat the near-Real-Time (near-RT) Radio Access Network (RAN) Intelligent Controller, i.e., near-RT RIC. The base station or gNB (i) uses the you-only-look-once (YOLO)-based machine learning framework that is modified to detect radar signals present within spectrograms generated from I/Q samples collected during the regular uplink cellular operation, and (ii) maintains a list of ‘occupied’ channels in the 3.5 GHz CBRS band that indicate radar presence. Our design is validated with (i) an over the air collected dataset composed of Type 1 radar and standard-compliant LTE waveforms, and (ii) an experimental testbed of SDRs running a complete Open RAN stack with a near-RT RIC implementation integrated with our YOLO-based xApp. We show radar detection accuracy of 100% under SINR conditions ≥ 12 dB after combining 7 spectrograms into a single decision. Furthermore, using testbed results, we demonstrate that the gNB can be reconfigured to avoid radar interference within 866 ms, which represents a reduction of 85.5% over the 60 s response time mandated for pausing cellular operation in detecting radar presence in the CBRS band today.

The next generation of cellular networks will be characterized by openness, intelligence, virtualization, and distributed computing. The Open Radio Access Network (Open RAN) framework represents a significant leap toward realizing these ideals, with prototype deployments taking place in both academic and industrial domains. While it holds the potential to disrupt the established vendor lock-ins, Open RAN's disaggregated nature raises critical security concerns. Safeguarding data and securing interfaces must be integral to Open RAN's design, demanding meticulous analysis of cost/benefit tradeoffs. In this paper, we embark on the first comprehensive investigation into the impact of encryption on two pivotal Open RAN interfaces: the E2 interface, connecting the base station with a near-real-time RAN Intelligent Controller, and the Open Fronthaul, connecting the Radio Unit to the Distributed Unit. Our study leverages a full-stack O-RAN ALLIANCE compliant implementation within the Colosseum network emulator and a production-ready Open RAN and 5G-compliant private cellular network. This research contributes quantitative insights into the latency introduced and throughput reduction stemming from using various encryption protocols. Furthermore, we present four fundamental principles for constructing security by design within Open RAN systems, offering a roadmap for navigating the intricate landscape of Open RAN security.

Robotic factory floors will revolutionize the future of manufacturing and the service industry by automating tasks. However, to fully supplement human effort, these robots will need low-latency, reliable connectivity throughout the work zone through links established by wireless access points (APs). This will allow the robot to assuredly respond to programming directives that rely on the real-time relaying of robot-generated sensor data to the Mobile Edge Computing (MEC) server. In this paper, we propose L-NORM, a multi-AP and multi-robot coordination framework, as a multi-tiered solution for such autonomous edge networks. First, multi-robot motion planning through reinforcement learning occurs at the MEC, using as input multi-modal robot sensor data. Second, multi-AP resource orchestration is performed using another reinforcement learning-based method that maps a subset of available APs to each robot toward meeting their sensor data delivery requirements. Furthermore, we suggest diversity combination of uplink channels with the 802.11ax scheduled access mode that will (i) support high reliability of multi-robot uplink sensor packets and (ii) enable multi-AP coordination, for optimized resource utilization. Through extensive simulation studies, we show that the probability of robot deviation to remain within 0.5 m from its optimal path, is 19% more in L-NORM compared to classical 802.11ax based edge network solution, considering$\sim$1 MB of sensor data per robot.

Fast sector-steering in the mmWave band for vehicular mobility scenarios is a challenge because standard-defined exhaustive search over predefined antenna sectors cannot be assuredly completed within short contact times. This paper proposes machine learning to speed up sector selection using data from multiple non-RF sensors, such as LiDAR, GPS, and camera images in the mmWave radios with large codebooks. The contributions in this paper are threefold: First, we propose a multimodal deep learning architecture that fuses the inputs from these data sources and locally predicts the sectors for best alignment at a vehicle. Second, we propose FLASH-and-Prune, which combines the knowledge from multiple vehicles by aggregating the local model parameters and exploits model pruning to optimize the model parameter exchange overhead. Third, we present a pruning strategy that takes into account the distributed nature of federated learning to adaptively prune or retrieve model weights. We validate the proposed architecture on a real-world multimodal dataset collected from an autonomous car. We observe that FLASH-and-Prune incurs 29.25% and 35.89% less overhead in the uplink and downlink, respectively, compared to standard federated learning.

Creating a digital world that closely mimics the real world with its many complex interactions and outcomes is possible today through advanced emulation software and ubiquitous computing power. Such a software-based emulation of an entity that exists in the real world is called a ‘digital twin’. In this paper, we consider a twin of a wireless millimeter-wave band radio that is mounted on a vehicle and show how it speeds up directional beam selection in mobile environments. To achieve this, we go beyond instantiating a single twin and propose the ‘$\MV$’ paradigm, with several possible digital twins attempting to capture the real world at different levels of fidelity. Towards this goal, this paper describes (i) a decision strategy at the vehicle that determines which twin must be used given the latency limitation, and (ii) a self-learning scheme that uses the$\MV$-guided beam outcomes to enhance DL-based decision-making in the real world over time. Our work is distinguished from prior works as follows: First, we use a publicly available RF dataset collected from an autonomous car for creating different twins. Second, we present a framework with continuous interaction between the real world and$\MV$of twins at the edge, as opposed to a one-time emulation that is completed prior to actual deployment. Results reveal that$\MV$offers up to$79.43\%$and$85.22\%$top-$10$beam selection accuracy for LOS and NLOS scenarios, respectively. Moreover, we observe$67.70-90.79\%$improvement in beam selection time compared to 802.11ad standard and 5G-NR standards.

Efficient routing of information between end-nodes is a key enabler for secure quantum networks and quantum secret key sharing, which rely on creating and sustaining entangled states over time. However, such pairwise entanglements degrade due to channel loss and the storage of the entangled photons at the network nodes. The state of entanglement in turn impacts fidelity, a metric which quantifies the degree of similarity between a pair of quantum states. In this paper, we propose a routing solution that satisfies threshold fidelity requirements imposed by a receiver on the quantum information received from multiple transmitter nodes. Our solution selects intermediate repeaters from a pool of such nodes within the network to maximize the sum-rate of quantum information transfer. To this extent, we first provide expressions for the fidelity loss between adjacent nodes as well as for the end-to-end quantum data rate. Then, we propose a novel two-stage routing solution that (i) identifies the k-shortest paths for each transmitter using fidelity as cost metric and (ii) (heuristically) assigns a path for each transmitter depending on whether the repeater nodes have a single or multiple available memory units. Simulation results demonstrate that our proposed fidelity-based routing solution satisfies a wide range of fidelity requirements [0.6-0.79] while maximizing the quantum information transfer rate, outperforming the existing distance- and hop-based routing approaches.

Open Radio Access Network (O-RAN) is considered as a major step in the evolution of next-generation cellular networks given its support for open interfaces and utilization of artificial intelligence (AI) into the deployment, operation, and maintenance of RAN. However, due to the openness of the O-RAN architecture, such AI models are inherently vulnerable to various adversarial machine learning (ML) attacks, i.e., adversarial attacks which correspond to slight manipulation of the input to the ML model. In this work, we showcase the vulnerability of an example ML model used in O-RAN, and experimentally deploy it in the near-real time (near-RT) RAN intelligent controller (RIC). Our ML-based interference classifier xAp$p$(extensible application in near-RT RIC) tries to classify the type of interference to mitigate the interference effect on the O-RAN system. We demonstrate the first-ever scenario of how such an xApp can be impacted through an adversarial attack by manipulating the data stored in a shared database inside the near-RT RIC. Through a rigorous performance analysis deployed on a laboratory O-RAN testbed, we evaluate the performance in terms of capacity and the prediction accuracy of the interference classifier xApp using both clean and perturbed data. We show that even small adversarial attacks can significantly decrease the accuracy of ML application in near-RT RIC, which can directly impact the performance of the entire O-RAN deployment.

The use of alternate modalities, like images, for fast beamforming in the millimeter wave (mmWave)-band is being proposed to ensure high bandwidth connectivity in vehicular scenarios typically seen in the context of autonomous cars. Considering the dynamic deployment conditions, a car may encounter new environments which were not explicitly included in an apriori training dataset. In this paper, we propose to use the Model-Agnostic Meta-Learning (MAML) framework on the image data of the mmWave vehicle-to-infrastructure beam selection FLASH dataset, to overcome the generalization issues of a pre-trained model in unseen non-line-of-sight (NLOS) connectivity environments. MAML has additional advantages over traditional deep-learning techniques: (i) it uses a fraction of the data which, in turn, simplifies data collection and storage, and (ii) it results in equal or higher accuracy in optimal beam selection compared to the case when the new environment dataset is fully available during initial training. We show that our MAML implementation improves test accuracy of beam selection by up to 86% with fine-tuning when encountering an unseen NLOS environment compared to conventional supervised learning.

Massive MIMO (mMIMO) technology is considered as a key enabler for 5G and beyond cellular networks, which allows formation of highly directional radiation beams in the millimeter-wave (mmWave) band. Specifically, considering the 5G new radio (NR) standard, a codebook-based approach is used that allows setting the antenna weights, so that both transmission and reception can be achieved in the desired angle. However, when a fixed codebook is used, these angular directions may not be exactly aligned along the optimal path that maximizes the SINR between the transmitter-receiver pair, depending on the granularity of the beam and the codebook size. To address these issues, we propose selection of the analog parameters of the transceiver chain through Deep Reinforcement Learning (DRL). Simulation results show that our approach allows fine-grained beam refinement to the coarse initial estimates of Angle-of-Arrival and Angle-of-Departures in mmWave Frequency Range 2 (FR2) for the 5G NR standard obtained during the a reduced initial beam establishment procedure (P-1). We observe our approach consistently improves the Reference Signal Received Power (RSRP) perceived at the UE side up to 15% while allowing a reduction in the number of Synchronization Signal Blocks (SSBs) up to a factor of$\times 64$compared to the equivalent number used in P-1 to obtain comparable steering accuracy. Finally, once the trained DRL agent is implemented, it eliminates 100% of control signals needed for the beam refinement procedures, namely P-2 for transmitter beam refinement and P-3 for receiver.

Finding a path with the least overall noise from quantum memories, fibers, and gate operations in a quantum network involves the challenge of acquiring knowledge of these noises, their sources, and the time of occurrences. In this paper, we propose a reinforcement learning-based route selection approach that uses a multi-arm bandit algorithm to find the least noisy path from a transmitter (Tx) to a receiver (Rx), without considering any information on qubit decoherence due to probabilistic noises inherent in quantum memories and imperfect gate operations. It only uses network deployment knowledge to find a set of feasible paths from Tx to Rx. We provide a key finding from a network design perspective which says that performing entanglement swapping on nodes within a path in a non-synchronized and parallel manner not always reduces the decoherence experienced in achieving the end-to-end entanglement on that path. Further, we design and open-source a new simulator for simulating probabilistic noises encountered during entanglement distribution between Tx-Rx on a path, which has supporting callable functions for connecting the unknown network environment required for interaction with the multi-arm bandit agent. The simulation results demonstrate that our proposed route selection approach provides a path up to ~ 33% better fidelity (less noise) compared to conventional, distance-based route selection approach for the considered quantum network.

A promising vision for the emerging next generation of cellular networks is one that embraces openness, intelligence, virtualization, and distributed computing. The Open Radio Access Network (O-RAN) framework is making significant strides toward these goals and is already seeing prototype deployments in academia and industry. While there is general consensus that this technology may disrupt the status quo by eliminating vendor lock-ins, there are serious questions about the security implications in such dis-aggregated networks. Indeed, securing data and controlling interfaces must be a core consideration in the design of O-RAN and cost/benefit tradeoffs need to be rigorously analyzed, given the short time-scales of wireless operation. In this paper, we undertake the first systematic study on the impact of encryption on a critical O-RAN interface (called ‘E2’) connecting the base station to a near-real time radio intelligence controller using an implementation on the Colosseum radio frequency (RF) emulator. The contributions of this paper include quantitative measurements of added latency and CPU utilization due to encryption on the E2 interface that could impact data acquisition and machine learning models. In our experiments we found encryption adds$\leq 50\mu s$of delay and CPU utilization limits throughput to approximately 500 Mbps. We also include a theoretical model to extend this study to other O-RAN implementations beyond the emulation environments of the Colosseum.

The use of non-RF data can potentially speed up millimeter wave-band sector-steering in vehicular mobility scenarios by gaining contextual knowledge of the environment. While several works have demonstrated the benefits of this approach, especially applying machine learning models on inputs from LiDAR and image sensors, adapting such models in ‘unseen’ environments remains an open problem. State-of-the-art techniques generally use a single, pretrained model for all different scenarios, which assumes that the network has ‘seen’ representative examples of all future scenarios. In this paper, we propose the TUNE framework, which solves this problem by: ($a$) transfer learning (TL) for better performance with similar convergence times in comparison to non-TL-generated model testing, (b) utilizing statistical properties to select the best-suited starting ‘seen’ scenario (and by extension the model trained for it), and (c) a refinement of the transfer learning framework by dynamically selecting the most pertinent layers for retaining, thus reducing the overhead compared to fully retraining a model. We validate TUNE on publicly available synthetic and real-world datasets for mmWave beam selection for V2X communication, revealing that TUNE generally outperforms non-TL methods in a variety of tasks where a different number of beams is available between the training and testing environments.

Quantum links are inherently noisy and quantum information bits (qubits) suffer upto 13% degradation in their entangled states within time-scale of 0.5 ms. Thus, mitigating errors becomes essential for reliable end-to-end data communication in a multi-hop quantum network. Compared to the typical operations performed within the contained environment of a single quantum computer, removal of both bit- and phase-flip errors in a distributed network of such computers is challenging due to the stochastic variations in the noise at each intermediate link. This paper describes a scheme that determines both the bit-and phase-flip errors (abbreviated as ‘BiP’) and mitigates them for distributed and networked quantum systems. To achieve this, we model the environment noise using general error models and obtain error calibration matrices in different computational bases for bit-phase-flip errors. Results reveal that BiP improves the fidelity beyond 95% for the received qubits compared to the state-of-the-art error mitigation method by correcting the elevation θ and azimuthal angles φin the Bloch sphere representation.

The RF environment in a secure space can be compromised by intentional transmissions of hard-to-detect underlay signals that overlap with a high-power baseline transmission. Specifically, we consider the case where a direct sequence spread spectrum (DSSS) signal is the underlay signal hiding within a baseline 4G Long-Term Evolution (LTE) signal. As compared to overt actions like jamming, the DSSS signal allows the LTE signal to be decodable, which makes it hard to detect. ICARUS presents a machine learning based framework that offers choices at the physical layer for inference with inputs of (i) in-phase and quadrature (IQ) samples only, (ii) cycle-frequency features obtained via cyclostationary signal processing (CSP), and (iii) fusion of both, to detect the underlay DSSS signal and its modulation type within LTE frames. ICARUS chooses the best inference method considering both the expected accuracy and the computational overhead. ICARUS is rigorously validated on multiple real-world datasets that include signals captured in cellular bands in the wild and the NSF POWDER testbed for advanced wireless research (PAWR). Results reveal that ICARUS can detect DSSS anomalies and its modulation scheme with 98-100% and 67 − 99% accuracy, respectively, while completing inference within 3 − 40 milliseconds on an NVIDIA A100 GPU platform.

Small form-factor single antenna devices, typically deployed within wireless sensor networks, lack many benefits of multi-antenna receivers like leveraging spatial diversity to enhance signal reception reliability. In this paper, we introduce the theory of achieving spatial diversity in such single-antenna systems by using reconfigurable intelligent surfaces (RIS). Our approach, called ‘RIS-STAR’, proposes a method of proactively perturbing the wireless propagation environment multiple times within the symbol time (that is less than the channel coherence time) through reconfiguring an RIS. By leveraging the stationarity of the channel, RIS-STAR ensures that the only source of perturbation is due to the chosen and controllable RIS configuration. We first formulate the problem to find the set of RIS configurations that maximizes channel hardening, which is a measure of link reliability. Our solution is independent of the transceiver’s relative location with respect to the RIS and does not require channel estimation, alleviating two key implementation concerns. We then evaluate the performance of RIS-STAR using a custom-simulator and an experimental testbed composed of PCB-fabricated RIS. Specifically, we demonstrate how a SISO link can be enhanced to perform similar to a SIMO link attaining an 84.6% channel hardening improvement in presence of strong multipath and non-line-of-sight conditions.

This paper proposes and experimentally validates a new paradigm for computing with wireless signals over-the-air (OTA). It demonstrates the first fully connected (FC) neural network (NN) constructed entirely using channel propagation and signal interference principles. Our design is based on architecting the desired linear operation of an FC layer through the superposition of signals emitted from multiple transmitters and received at a single receiver, similar to multiple input single output (MISO) systems. Our design takes into account several practical considerations, such as the impact of multiple subcarriers, the number of transmit antennas, and the changing wireless channel. The key outcome of our work is developing a principled methodology that transforms a given trained digital FC NN into its OTA equivalent. This novel computational paradigm, which we call AirFC, allows us to run NN tasks without compute-specific hardware during tests. We validate our design using 9 time-synchronized software-defined radios (SDRs) available on the ORBIT testbed, emulating a 16 antenna array. We use the MNIST dataset as input to our wireless FC NN and demonstrate classification with 92.61% accuracy, which proves that our NN with OTA FC layers performs similar to the conventional, all-digital version with an accuracy decrease of only 0.73%.

Wireless communication between an unmanned aerial vehicle (UAV) and the ground base station is susceptible to adversarial jamming. In such situations, it is important for the UAV to indicate a new channel to the BS. This paper describes a method of creating spatial codes that map the chosen channel to the location of the UAVs in space, wherein the latter physically traverses the space from a given so called ”constellation points” to another. These points create patterns in the sky, analogous to modulation constellations in classical wireless communications, and are detected at the BS through a millimeter-wave radar sensor. A constellation point represents a distinct n-bit field mapped to a specific channel, allowing simultaneous frequency switching at both ends without any RF transmissions. The main contributions of this paper are: (i) We conduct experimental studies to demonstrate how such constellations may be formed using COTS UAVs and mmWave sensors, (ii) We develop a theoretical framework that maps a desired constellation design to error and band switching time, including multi-user scenario-specific challenges, (iii) We compare our approach against current FHSS technology and (iv) We experimentally demonstrate jamming resilient communications and validate system goodput for links formed by UAV-mounted software defined radios.

With the recent surge in autonomous driving vehicles, the need for accurate vehicle detection and tracking is critical now more than ever. Detecting vehicles from visual sensors fails in non-line-of-sight (NLOS) settings. This can be compensated by the inclusion of other modalities in a multi-domain sensing environment. We propose several deep learning based frameworks for fusing different modalities (image, radar, acoustic, seismic) through the exploitation of complementary latent embeddings, incorporating multiple state-of-the-art fusion strategies. Our proposed fusion frameworks considerably outperform unimodal detection. Moreover, fusion between image and non-image modalities improves vehicle tracking and detection under NLOS conditions. We validate our models on the real-world multimodal ESCAPE dataset, showing 33.16% improvement in vehicle detection by fusion (over visual inference alone) over test scenarios with 30-42% NLOS conditions. To demonstrate how well our framework generalizes, we also validate our models on the multimodal NuScene dataset, showing$\sim$22% improvement over competing methods.

Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind convolution that uses over-the-air computation and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call ’AirNN’. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating convolutions with over-the-air computation. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.

In IEEE 802.11 WiFi-based waveforms, the receiver performs coarse time and frequency synchronization using the first field of the preamble known as the legacy short training field (L-STF). The L-STF occupies upto 40% of the preamble length and takes upto$32 \mu \text{s}$of airtime. With the goal of reducing communication overhead, we propose a modified waveform, where the preamble length is reduced by eliminating the L-STF. To decode this modified waveform, we propose a neural network (NN)-based scheme called PRONTO that performs coarse time and frequency estimations using other preamble fields, specifically the legacy long training field (L-LTF). Our contributions are threefold: (i) We present PRONTO featuring customized convolutional neural networks (CNNs) for packet detection and coarse carrier frequency offset (CFO) estimation, along with data augmentation steps for robust training. (ii) We propose a generalized decision flow that makes PRONTO compatible with legacy waveforms that include the standard L-STF. (iii) We validate the outcomes on an over-the-air WiFi dataset from a testbed of software defined radios (SDRs). Our evaluations show that PRONTO can perform packet detection with 100% accuracy, and coarse CFO estimation with errors as small as 3%. We demonstrate that PRONTO provides upto 40% preamble length reduction with no bit error rate (BER) degradation. We further show that PRONTO is able to achieve the same performance in new environments without the need to re-train the CNNs. Finally, we experimentally show the speedup achieved by PRONTO through GPU parallelization over the corresponding CPU-only implementations.

Generating custom modulation patterns as well as dynamically varying the mapping of the constellation points to their corresponding bit representations are some existing methods for mitigating eavesdropping attacks. In such cases, the custom symbol to bit mapping needs to be conveyed to the receiver through a secure and reliable channel. Instead of sending the representations of the modified symbols in regular information fields, we propose a machine learning-based approach, in which the modified symbols are encoded in the parameters of a light-weight neural network (NN). This NN is trained at the transmitter-side, sent as a secret key to the receiver, where it serves as a demapping block to recover the received symbols correctly. In addition, this paper explores the role of data augmentation during the training stage to increase the robustness of the NN with respect to the noise in the channel, as well as architecture compression to reduce transmission overhead. We validate the robustness of the proposed NN-based custom-modulation demapping approach by comparing it with demapping of a standard scheme (e.g., 16QAM), which reveals no appreciable loss in performance. We further quantitatively analyze the impact of channel and noise impairments on the demapping performance.

We are being increasingly surrounded by electronic devices that need reliable authentication before they can be accessed. While typed passwords, face and fingerprint-based authentication are popular today, we explore the possibility of using additional bio-origin signals, especially electrocardiogram (ECG) signals that can be collected without an active engagement and attention of the human user. Our proposed approach, abbreviated as FERST, uses a two-stage deep learning framework for signal processing and classification. The acquired and pre-equalized ECG signal is transferred from a wearable device through arm-wrist-palm galvanic coupled channel. The first part of the reception framework consists of a denoising autoencoder (DAE) that filters this noisy ECG signal. Then, the second stage includes a convolutional neural network (CNN) to classify and authenticate the denoised ECG signal as present/absent in a prior database used for training. The overall design goal of our approach is to achieve acceptable authentication performance with simple hardware, which further decreases network complexity and enables miniaturization of the end-to-end system. Results reveal that the FERST provides (i) 82% improvement in inference time relative to state-of-the-art adaptive filtration methods, (ii) outperforms the state-of-the-art with 99.7% classification accuracy on a standardized ECG library dataset and (iii) a relatively high classification accuracy of 99.2% for different arm-wrist-palm channel dimensions.

Millimeter-Wave (mmWave) has great potential to provide high data dates given its large available bandwidth, but its severe path loss and high propagation sensitivity to different environmental conditions make deployment planning particularly challenging. Traditional slope-intercept models fall short in capturing large site-specific variations due to urban clutter, terrain tilt or foliage, and ray-tracing faces challenges in characterizing mmWave propagation accurately with reasonable complexity. In this work, we apply machine learning (ML) techniques to predict mmWave path loss on a link-to-link basis over an extensive set of 28 GHz field measurements collected in a major city of USA, with over 120,000 links from both urban and suburban scenarios, with over 40 dB variation for links at similar distances. Either raw environmental profile (terrain+clutter) of each link or 8 selected expert features are used to either directly predict path loss via regression-based approaches or predict the best performing option out of a pool of theoretical/empirical propagation models. Our evaluation shows that Lasso regression provides the best path loss prediction with a performance (RMSE 8.1 dB) comparable to the per-site slope-intercept fit (RMSE 8.0 dB), whereas model selection method achieves 8.6 dB RMSE, both are significantly better than the best a posteriori 3GPP model (UMa-NLOS, 10.0 dB).

Opening the Citizen Broadband Radio Service (CBRS) band in the US to secondary users offers unprecedented opportunities to LTE and 5G networks, as long as incumbent radar signals are protected from interference. Towards this aim, the US Federal Communications Commission (FCC) requires Environmental Sensing Capabilities (ESCs) to be installed along the coastal regions. Furthermore, FCC mandates that the secondary users transmit with low power levels, such that the aggregated interference and noise power in the vicinity of ESC sensors remains below −109 dBm/MHz. At this interference level, the ESC must detect 99 % of radar pulses with peak power of at least −89 dBm/MHz. In this paper, we design an enhanced ESC sensor, called ESC+, that leverages the deep learning framework called 'you only look once’ (YOLO) for signal detection using spectrograms. We propose a two-stage spectrogram-based coarse and fine signal analysis method for: (i) detecting, and characterizing radar pulses in environments where the aggregated noise and interference level goes beyond FCC restrictions, and (ii) detecting and characterizing other signal types (e.g., 5G and LTE) in the CBRS band, with a goal of determining unauthorized users. We generate a realistic spectrogram dataset in MATLAB consisting of three signal types of radar, 5G, and LTE where the aggregated interference and noise power occurring concurrently with the radar pulse is varied upto −104 dBm/MHz. We show 100% radar pulse detection in interference and noise levels of up to 3 dB higher than what is required today.

Fast sector-steering in the mmWave band for vehicular mobility scenarios remains an open challenge. This is because standard-defined exhaustive search over predefined antenna sectors cannot be assuredly completed within short contact times. This paper proposes machine learning to speed up sector selection using data from multiple non-RF sensors, such as LiDAR, GPS, and camera images. The contributions in this paper are threefold: First, a multimodal deep learning architecture is proposed that fuses the inputs from these data sources and locally predicts the sectors for best alignment at a vehicle. Second, it studies the impact of missing data (e.g., missing LiDAR/images) during inference, which is possible due to unreliable control channels or hardware malfunction. Third, it describes the first-of-its-kind multimodal federated learning framework that combines model weights from multiple vehicles and then disseminates the final fusion architecture back to them, thus incorporating private sharing of information and reducing their individual training times. We validate the proposed architectures on a live dataset collected from an autonomous car equipped with multiple sensors (GPS, LiDAR, and camera) and roof-mounted Talon AD7200 60GHz mmWave radios. We observe 52.75% decrease in sector selection time than 802.11ad standard while maintaining 89.32% throughput with the globally optimal solution.

Deep learning methods have been very successful at radio frequency fingerprinting tasks, predicting the identity of transmitting devices with high accuracy. We study radio frequency fingerprinting deployments at resource-constrained edge devices. We use structured pruning to jointly train and sparsify neural networks tailored to edge hardware implementations. We compress convolutional layers by a$27.2\times$factor while incurring a negligible prediction accuracy decrease (less than 1 percent). We demonstrate the efficacy of our approach over multiple edge hardware platforms, including a Samsung Gallaxy S10 phone and a Xilinx-ZCU104 FPGA. Our method yields significant inference speedups,$11.5\times$on the FPGA and$3\times$on the smartphone, as well as high efficiency: the FPGA processing time is$17\times$smaller than in a V100 GPU. To the best of our knowledge, we are the first to explore the possibility of compressing networks for radio frequency fingerprinting; as such, our experiments can be seen as a means of characterizing the informational capacity associated with this specific learning task.

This paper adopts a systems approach to study how millimeter wave (mmWave) radio transmitters on UAVs provide high throughput links under typical hovering conditions. With Terragraph channel sounder units, we experimentally study the impact of signal fluctuations and sub-optimal beam selection on a testbed involving DJI M600 UAVs. From the hovering-related insights and the measured antenna radiation patterns, we develop and validate the first stochastic UAV-to-Ground mmWave channel model with UAVs as transmitters. Our UAV-centric analytical model complements the classical fading with additional losses expected in the mmWave channel during hovering, considering 3-D antenna configuration and beamforming training parameters. We specifically consider lateral displacement, roll, pitch, and yaw, whose magnitude vary depending on the availability of specialized hardware such as real-time kinematic GPS. We then leverage this model to mitigate the hovering impact on the UAV-to-Ground link by selecting a near-to-optimum pair of beams. Importantly, our work does not change the wireless standard nor require any cross-layer information, making it compatible with current mmWave devices. Results demonstrate that our channel model drops estimation error to$\approx$0.2 percent, i.e., 18x lower, and improves the average PHY bit-rate by$\approx$10 percent when compared to existing state-of-the-art channel models and beamforming methods for UAVs.

We propose a novel distributed beamforming framework for UAVs, called SABRE, wherein airborne transmitters synchronize their operations for data communication with target receivers. SABRE chooses the best-suited subset of transmitters that maximizes user-defined QoS, considering relative distances from receivers, traffic characteristics, cumulative SNR desired at the receiver, and individual SNR estimated for each link. This paper makes three main contributions: (i) It shows how to achieve distributed beamforming in challenging, aerial hovering conditions by accurately synchronizing start-times and eliminating relative clock offsets. (ii) It proposes an algorithm with polynomial complexity that groups transmitters and chooses the receiver, maximizing the number of satisfied receivers in each round. (iii) It experimentally validates the concept of aerial beamforming in a testbed composed of four DJI-M100 UAVs in realistic outdoor environments. We follow this up with at-scale emulation involving beamforming with multiple candidate UAV transmitters in Colosseum, the world’s largest RF emulator. SABRE keeps the overall network frame error rate below 10% with a probability of 0.95 and manifests a 40% improvement in meeting user QoS thresholds over classical resource allocation methods. From a community viewpoint, the beamforming code, UAV interfacing designs, and the Colosseum container will be released publicly, allowing further independent investigations.

Emerging applications like distributed coordinated beamforming (DCB), intelligent reflector arrays, and networked robotic devices will transform wireless applications. However, for systems-centric work on these topics, the research community must first overcome the hurdle of implementing fine-grained, over-the-air timing synchronization, which is critical for any coordinated operation. To address this gap, this paper presents an open-source design and implementation of 'RFClock' that provides timing, frequency and phase synchronization for software defined radios (SDRs). It shows how RFClock can be used for a practical, 5-node DCB application without modifying existing physical/link layer protocols. By utilizing a leader-follower architecture, RFClock-leader allows follower clocks to synchronize with mean offset under 0.107Hz, and then corrects the time/phase alignment to be within a 5ns deviation. RFClock is designed to operate in generalized environments: as standalone unit, it generates a 10MHz/1PPS signal reference suitable for most commercial-off-the-shelf (COTS) SDRs today; it does not require custom protocol-specific headers or messaging; and it is robust to interference through a frequency-agile operation. Using RFClock for DCB, we verify significant increase in channel gain and low BER in a range of [0 -- 10--3] for different modulation schemes. We also demonstrate performance that is similar to a popular wired solution and significant improvement over a GPS-based solution, while delivering this functionality at a fractional price/power point.

Practical experimentation and prototyping are core steps in the development of any wireless technology. Often times, however, this crucial step is confined to small laboratory setups that do not capture the scale of commercial deployments and do not ensure result reproducibility and replicability, or it is skipped altogether for lack of suitable hardware and testing facilities. Recent years have seen the development of publicly-available testing platforms for wireless experimentation at scale. Examples include the testbeds of the PAWR program and Colosseum, the world's largest wireless network emulator. With its 256 software-defined radios, 24 racks of powerful compute servers and first-of-its-kind channel emulator, Colosseum allows users to prototype wireless solutions at scale, and guarantees reproducibility and replicability of results. This tutorial provides an overview of the Colosseum platform. We describe the architecture and components of the testbed as a whole, and we then showcase how to run practical experiments in diverse scenarios with heterogeneous wireless technologies (e.g., Wi-Fi and cellular). We also emphasize how Colosseum experiments can be ported to different testing platforms, facilitating full-cycle experimental wireless research: design, experiments and tests at scale in a fully controlled and observable environment and testing in the field. The tutorial concludes with considerations on the flexible future of Colosseum, focusing on its planned extension to emulate larger scenarios and channels at higher frequency bands (mmWave).

Accurate beam alignment in the millimeter-wave (mmWave) band introduces considerable overheads involving brute-force exploration of multiple beam-pair combinations and beam retraining due to mobility. This cost becomes often intractable under high mobility scenarios, where fast beamforming algorithms that can quickly adapt the beam configurations are still under development for 5G and beyond. Besides, blockage prediction is a key capability in order to establish mmWave reliable links. In this paper, we propose a data fusion approach that takes inputs from visual edge devices and localization sensors to (i) reduce the beam selection overhead by narrowing down the search to a small set containing the best possible beam-pairs and (ii) detect blockage conditions between transmitters and receivers. We evaluate our approach through joint simulation of multi-modal data from vision and localization sensors and RF data. Additionally, we show how deep learning based fusion of images and Global Positioning System (GPS) data can play a key role in configuring vehicle-to-infrastructure (V2I) mmWave links. We show a 90% top-10 beam selection accuracy and a 92.86% blockage prediction accuracy. Furthermore, the proposed approach achieves a 99.7% reduction on the beam selection time while keeping a 94.86% of the maximum achievable throughput.

Object sensing and tracking using electric and magnetic fields allow intelligent interaction, automation, and adaptation in cyber-physical systems. Our approach, called iSense, uses a software-defined collaborative sensing technique for the detection of the type of object when placed on a large surface and tracking its mobility. iSense is cost effective, low power, and scalable, which allows its use over large surfaces. First, we introduce a dual-coil magnetic resonant sensing architecture based on nested coils, i.e., passive (outer) and active (inner) coils, for low-power contactless sensing. Second, a data-driven support vector machine-based approach helps to classify different types of objects using the voltage readings obtained at the passive coil. iSense combines sensed voltage information from multiple different coils spread over the surface with a group-based interference mitigation mechanism between coils for collaborative sensing. We validate our system with real-time prototype and experimental evaluations. We demonstrate the detection of seven different types of objects over three different materials, and real-time detection and tracking of mobile objects including a robot car. Experimental results show that each sensing coil only consumes few milliwatts, i.e., 18× less than inductive sensing and 15× less than classical magnetic resonance sensing, extend sensing depth to 3 cm, and enable tracking on the large surface sensing with more than 90% accuracy for velocity estimation.

Unmanned aerial vehicle (UAV) mounted millimeter-wave (mmWave) base stations as well as aerial backhaul links will enable on-demand deployment of network resources. However, prior work has shown aerial links are prone to the frequent disruption caused by: 1) constant hovering due to GPS inaccuracies that impact narrow beamwidths; 2) blockages in the direct line of sight; and 3) suboptimal beam selection, especially if reduced angular sectors are searched in a highly dynamic environment. This article characterizes the impact of each of these phenomena for aerial mmWave links and proposes methods to distinctly identify when they occur in isolation or in combination during deployment. Furthermore, it also proposes corrective actions at the UAV, appropriate for the specific type(s) of impacting events: physical displacement from its earlier location, angular rotation around its vertical axis, or beamwidth adjustment. Our approach relies on exploiting the information contained in the angular domain of a large data set of experimentally collected beam-selection outcomes, under the above practical scenarios. We incorporate GPS accuracy models and antenna radiation patterns to create a robust model of potential outages. We then propose device-agnostic algorithms that jointly optimize UAVs' physical movement and the beamforming procedure. The experimental results obtained by mounting a pair of 60-GHz channel sounders on M600 DJI UAVs reveal loss reduction of up to 74.7%, translated into 260% physical layer bit-rate improvement compared to the classical 802.11ad standards-defined approach.

Wireless RF energy transfer for indoor sensors is an emerging paradigm ensuring continuous operation without battery limitations. However, high power radiation within ISM band interferes with packet reception for existing WiFi devices. The paper proposes the first effort in merging RF energy transfer within a standards compliant 802.11 protocol, realizing practical and WiFi-friendly Energy Delivery with Mobile Transmitters (WiFED Mobile). WiFED Mobile architecture is composed of a centralized controller coordinating the actions of multiple energy transmitters (ETs), and deployed sensors that periodically requires charging. The paper first describes 802.11 supported protocol features that can be exploited by sensors to request energy and for ETs to participate in energy transfer. Second, it devises a controller-driven bipartite matching algorithm, assigning appropriate number of ETs to sensors for efficient energy delivery. Thirdly, it detects outlier sensors (OS), which have limited power reception from static ETs and utilizes mobile ETs (METs) to satisfy their charging cycles. The proposed in-band and protocol supported coexistence in WiFED Mobile is validated via simulations and partly in a software defined radio testbed, showing that METs reduce latency by 42% and improve throughput by 83% in scenarios where using only static ETs fails to satisfy charging cycles of OS.

We propose a framework called AirID that identifies friendly/authorized UAVs using RF signals emitted by radios mounted on them through a technique called as RF fingerprinting. Our main contribution is a method of intentionally inserting `signatures' in the transmitted I/Q samples from each UAV, which are detected through a deep convolutional neural network (CNN) at the physical layer, without affecting the ongoing UAV data communication process. Specifically, AirID addresses the challenge of how to overcome the channel-induced perturbations in the transmitted signal that lowers identification accuracy. AirID is implemented using Ettus B200mini Software Defined Radios (SDRs) that serve as both static ground UAV identifiers, as well as mounted on DJI Matrice M100 UAVs to perform the identification collaboratively as an aerial swarm. AirID tackles the well-known problem of low RF fingerprinting accuracy in `train on one day test on another day' conditions as the aerial environment is constantly changing. Results reveal 98% identification accuracy for authorized UAVs, while maintaining a stable communication BER of 10-4for the evaluated cases.

5G and open radio access networks (Open RANs) will result in vendor-neutral hardware deployment that will require additional diligence towards managing security risks. This new paradigm will allow the same network infrastructure to support virtual network slices for transmit different waveforms, such as 5G New Radio, LTE, WiFi, at different times. In this multivendor, multi-protocol/waveform setting, we propose an additional physical layer authentication method that detects a specific emitter through a technique called as RF fingerprinting. Our deep learning approach uses convolutional neural networks augmented with triplet loss, where examples of similar/dissimilar signal samples are shown to the classifier over the training duration. We demonstrate the feasibility of RF fingerprinting base stations over the large-scale over-the-air experimental POWDER platform in Salt Lake City, Utah, USA. Using real world datasets, we show how our approach overcomes the challenges posed by changing channel conditions and protocol choices with 99.86% detection accuracy for different training and testing days.

In lifelong learning, we wish to maintain and update a model (e.g., a neural network classifier) in the presence of new classification tasks that arrive sequentially. In this paper, we propose a learn-prune-share (LPS) algorithm which addresses the challenges of catastrophic forgetting, parsimony, and knowledge reuse simultaneously. LPS splits the network into task-specific partitions via an ADMM-based pruning strategy. This leads to no forgetting, while maintaining parsimony. Moreover, LPS integrates a novel selective knowledge sharing scheme into this ADMM optimization framework. This enables adaptive knowledge sharing in an end-to-end fashion. Comprehensive experimental results on two lifelong learning benchmark datasets and a challenging real world radio frequency fingerprinting dataset are provided to demonstrate the effectiveness of our approach. Our experiments show that LPS consistently outperforms multiple state-of-the-art competitors.

We study an Open-World Class Discovery problem in which, given labeled training samples from old classes, we need to discover new classes from unlabeled test samples. There are two critical challenges to addressing this paradigm: (a) transferring knowledge from old to new classes, and (b) incorporating knowledge learned from new classes back to the original model. We propose Class Discovery Kernel Network with Expansion (CD-KNet-Exp), a deep learning framework, which utilizes the Hilbert Schmidt Independence Criterion to bridge supervised and unsupervised information together in a systematic way, such that the learned knowledge from old classes is distilled appropriately for discovering new classes. Compared to competing methods, CD-KNet-Exp shows superior performance on three publicly available benchmark datasets and a challenging real-world radio frequency fingerprinting dataset.

Network densification through the deployment of WiFi access points (APs) is a promising solution towards achieving high connectivity rates required for emerging applications. A critical first step is to discover an AP before an active association between the client and the AP can be established. Legacy AP discovery procedures initiated by the client result in high latency in the order of a few 100 ms and waste spectrum, especially when clients need to frequently switch between multiple APs. We propose CSIscan that exploits the broadcast nature of WiFi channels by embedding discovery related information within an AP's ongoing regular transmissions. The AP does this by intelligently distorting the transmitted OFDM frame by inducing perturbations in the preamble, and these injected `bits' of information are detected via changes in the perceived channel state information (CSI). A deep learning framework allocates the optimal level of distortion on a per-subcarrier basis that keeps the resulting packet error rate to less than 1%. Existing clients perceive no changes in their ongoing communication, while potential new clients quickly obtain discovery information at the same time. We experimentally demonstrate that CSIscan reduces the overall WiFi latency from 150 ms to 10 ms and improves spectrum utilization with ~72% reduction in the probe traffic. We show that CSIscan delivers up to 40 discovery information bits in the outgoing WiFi packet in an indoor environment.

Radio fingerprinting uniquely identifies wireless devices by leveraging tiny hardware-level imperfections inevitably present in off-the-shelf radio circuitry. This way, devices can be directly identified at the physical layer by analyzing the unprocessed received waveform - thus avoiding energy-expensive upper-layer cryptography that resource-challenged embedded devices may not be able to afford. Recent advances have proven that convolutional neural networks (CNNs) - thanks to their multidimensional mappings - can achieve fingerprinting accuracy levels impossible to achieve by traditional low-dimensional algorithms. The same research, however, has also suggested that the wireless channel may negatively impact the accuracy of CNN-based radio fingerprinting algorithms by making device-unique hardware imperfections much harder to recognize.In spite of the growing interest in radio fingerprinting research by academia and DARPA, the wireless research community still lacks (i) a large-scale open dataset for radio fingerprinting collected in diverse environments and rich, diverse, channel conditions; and (ii) a full-fledged, systematic, quantitative investigation of the impact of the wireless channel on the accuracy of CNN-based radio fingerprinting algorithms. The key contribution of this paper is to bridge this gap by (i) collecting and sharing with the community more than 7TB of wireless data obtained from 20 wireless devices with identical RF circuitry (and thus, worst-case scenario for fingerprinting) over the course of several days in (a) an anechoic chamber, (b) in-the-wild testbed, and (c) with cable connections; and (ii) providing a first-of-its-kind evaluation of the impact of the wireless channel on CNN-based fingerprinting algorithms through (a) the 7TB experimental dataset and (b) a 400GB dataset provided by DARPA containing hundreds of thousands of transmissions from thousands of WiFi and ADS-B devices with different SNR conditions. Experimental results conclude that (i) the wireless channel impacts the classification accuracy significantly, i.e., from 85% to 9% and from 30% to 17% in the experimental and DARPA dataset, respectively; and that (ii) equalizing I/Q data can increase the accuracy to a significant extent (i.e., by up to 23%) when the number of devices increases significantly.

This paper proposes MAGIC: magnetic resonant (MR) coupling for intra-body communication between implants and wearables. MAGIC includes not only the hardware-software design of the coupled coils and methods of manipulating the magnetic field for relaying information, but also the ability to raise immediate emergency-related alerts with guaranteed delivery time. MR coupling makes the design of the transmission link robust to channel-related parameters, as the magnetic permeability of skin and muscle is close to that of air. Thus, changes in tissue moisture content and thickness does not impact the design, which is a persistent problem in other approaches for implant communications like RF, ultrasound and galvanic coupling (GC). The paper makes three main contributions: It develops the theory leading to the design of the information relaying coils in MAGIC. It proposes a systems-level design of a communication link that extends up to 50cm with a low expected BER of 10-4. Finally, the paper includes an experimental setup demonstrating how MAGIC operates in air and muscle tissue, as well as a comparison with alternative implant communication technologies, such as classical radio frequency and GC. Results reveal that MAGIC offers instantaneous alerts with up to 5 times lower power consumption compared to other forms of communication.

Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector combinations to identify the beam pair with the highest SNR. In this paper, we propose a machine learning (ML) approach with two sequential convolutional neural networks (CNN) that uses out-of-band information, in the form of camera images, to (i) rapidly identify the locations of the transmitter and receiver nodes, and then (ii) return the optimal beam pair. We experimentally validate this intriguing concept for indoor settings using the NI 60GHz mmwave transceiver. Our results reveal that our ML approach reduces beamforming related exploration time by 93% under different ambient lighting conditions, with an error of less than 1% compared to the time-intensive deterministic method defined by the current standards.

Retailers are aiming to enhance customer experience by automating the checkout process. The key impediment here is the effort to manually align the product barcode with the scanner, requiring sequential handling of items without blocking the line-of-sight of the laser beam. While recent systems such as Amazon Go eliminate human involvement using an extensive array of cameras, we propose a privacy-preserving alternative, RFGo, that identifies products using passive RFID tags. Foregoing continuous monitoring of customers throughout the store, RFGo scans the products in a dedicated checkout area that is large enough for customers to simply walk in and stand until the scan is complete (in two seconds). Achieving such low-latency checkout is not possible with traditional RFID readers, which decode tags using one antenna at a time. To overcome this, RFGo includes a custom-built RFID reader that simultaneously decodes a tag's response from multiple carrier-level synchronized antennas enabling a large set of tag observations in a very short time. RFGo then feeds these observations to a neural network that accurately distinguishes the products within the checkout area from those that are outside. We build a prototype of RFGo and evaluate its performance in challenging scenarios. Our experiments show that RFGo is extremely accurate, fast and well-suited for practical deployment in apparel stores.

Unmanned aerial systems (UASs) allow easy deployment, three-dimensional maneuverability and high reconfigurability, as they sustain communication network in the absence of pre-installed infrastructure. The proposed FOg Computing in UAS Software-defined mesh network (FOCUS) paradigm aims to realize an implementable network design that considers practical issues of aerial connectivity and computation. It allocates UASs to the tasks of data forwarding and in-network fog computing while maximizing number of ground-users in UAS coverage. FOCUS improves efficient utilization of network resources by introducing on-board computation and innovates on top of software-defined networking stack by integrating the capabilities of network and ground controllers to enable simultaneous orchestration of both UASs and communication flows. There are three main contributions of the paper: First, a SDN-based architecture is designed enabling autonomous configuration of computation and communication as well as managing multi-hop aerial links. Second, a global optimization problem to achieve optimal forwarding and computational allocation is formulated using Open Jackson Network model and solved via a heuristic approach with well defined complexity. Third, FOCUS framework is implemented on a small-scale testbed of Intel®Aero UASs performing image analysis with a full software stack. Experiments reveal at least 32% latency improvement in computation service time compared to traditional centralized computation at the end-server or greedy task allocation schemes within the network.

Object sensing and tracking using electric and magnetic fields allow intelligent interaction, automation, and adaptation in cyber-physical systems. Our approach, called Softsense, uses a software-defined collaborative sensing technique for detection of the type of object and where it is placed on a large surface. Unlike RF based sensing approaches that are generally dependent on channel conditions, capacitive sensing that detects only low conductive objects, and Qi-based inductive sensing that is effective at few mm in range, Softsense is designed to operate without the above limitations. Softsense is cost effective, low power and scalable, which allows extension over large surfaces. First, we introduce a dual-coil inductive sensing architecture based on nested coils, i.e., passive (outer) and active (inner) coils, for low-power contact-less sensing. A data driven support vector machine-based approach helps to classify different materials using the voltage readings obtained at the passive coil. SoftSense combines sensed voltage information from multiple different coils spread over the surface for collaborative sensing. We validate our design on a real sensing prototype with customized coils, fabricated sensing circuit, and a network software controller. Experimental results show that each sensing coil only consumes few milliwatts, i.e., 18x less than the inductive sensing and 15x less than classical magnetic resonance sensing, extends sensing depth to 3 cm, and enables coverage of large surface sensing.

Wireless communication between an unmanned aerial vehicle (UAV) and the ground base station (BS) is susceptible to adversarial jamming. In such situations, it is important for the UAV to indicate a new channel to the BS. This paper describes a method of creating spatial codes that map the chosen channel to the motion and location of the UAVs in space, wherein the latter physically traverses the space from a given so called ''constellation point'' to another. These points create patterns in the sky, analogous to modulation constellations in classical wireless communications, and are detected at the BS through a millimeter-wave (mmWave) radar sensor. A constellation point represents a distinct n-bit field mapped to a specific channel, allowing simultaneous frequency switching at both ends without any RF transmissions. The main contributions of this paper are: (i) We conduct experimental studies to demonstrate how such constellations may be formed using COTS UAVs and mmWave sensors, given realistic sensing errors and hovering vibrations, (ii) We develop a theoretical framework that maps a desired constellation design to error and band switching time, considering again practical UAV movement limitations, and (iii) We experimentally demonstrate jamming resilient communications and validate system goodput for links formed by UAV-mounted software defined radios.

This paper describes the architecture and performance of ORACLE, an approach for detecting a unique radio from a large pool of bit-similar devices (same hardware, protocol, physical address, MAC ID) using only IQ samples at the physical layer. ORACLE trains a convolutional neural network (CNN) that balances computational time and accuracy, showing 99% classification accuracy for a 16-node USRP X310 SDR testbed and an external database of >100 COTS WiFi devices. Our work makes the following contributions: (i) it studies the hardware-centric features within the transmitter chain that causes IQ sample variations; (ii) for an idealized static channel environment, it proposes a CNN architecture requiring only raw IQ samples accessible at the front-end, without channel estimation or prior knowledge of the communication protocol; (iii) for dynamic channels, it demonstrates a principled method of feedback-driven transmitter-side modifications that uses channel estimation at the receiver to increase differentiability for the CNN classifier. The key innovation here is to intentionally introduce controlled imperfections on the transmitter side through software directives, while minimizing the change in bit error rate. Unlike previous work that imposes constant environmental conditions, ORACLE adopts the `train once deploy anywhere' paradigm with near-perfect device classification accuracy.

Increasing threats of malicious eavesdropping raise concerns in confidential data reporting by body-worn sensors. We propose a secure, body-guided transmission channel through the use of galvanic coupling (GC). This method involves injecting weak electrical current into the body, which propagates primarily through the skin. The proposed approach makes the transmission of biometric data impervious to sniffing attacks, enabling the body to serve as a waveguide. This paper makes the following contributions: (i) An analytical channel model using a tissue equivalent circuit of the human arm-wrist-palm GC-propagation path is formulated and empirically verified. (ii) A simulation study is conducted for a comparative analysis of various modulation schemes, leveraging the validated GC-channel behavior. (iii) A GC-transceiver with optimized communication parameters (modulation, frequency, power) is designed and implemented using a dielectrically equivalent tissue phantom, and (iv) through experimental trials, resilience to over-the-air susceptibility (i.e., likelihood of adversarial eavesdropping) of the GC-signal and similar body communication techniques are demonstrated. Performance results of the GC-transceiver prototype yield a bit error rate of 10-6with a transmit power of -2dBm, in addition to over 7x reduction of signal radiation outside the body compared to capacitive coupling.

We propose AirBeam, the first complete algorithmic framework and systems implementation of distributed air-to-ground beamforming on a fleet of UAVs. AirBeam synchronizes software defined radios (SDRs) mounted on each UAV and assigns beamforming weights to ensure high levels of directivity. We show through an exhaustive set of the experimental studies on UAVs why this problem is difficult given the continuous hovering-related fluctuations, the need to ensure timely feedback from the ground receiver due to the channel coherence time, and the size, weight, power and cost (SWaP-C) constraints for UAVs. AirBeam addresses these challenges through: (i) a channel state estimation method using Gold sequences that is used for setting the suitable beamforming weights, (ii) adaptively starting transmission to synchronize the action of the distributed radios, (iii) a channel state feedback process that exploits statistical knowledge of hovering characteristics. Finally, AirBeam provides insights from a systems integration viewpoint, with reconfigurable B210 SDRs mounted on a fleet of DJI M100 UAVs, using GnuRadio running on an embedded computing host.

Radio fingerprinting provides a reliable and energy-efficient IoT authentication strategy by leveraging the unique hardware-level imperfections imposed on the received wireless signal by the transmitter's radio circuitry. Most of existing approaches utilize hand-tailored protocol-specific feature extraction techniques, which can identify devices operating under a pre-defined wireless protocol only. Conversely, by mapping inputs onto a very large feature space, deep learning algorithms can be trained to fingerprint large populations of devices operating under any wireless standard.

The growing spectrum crunch has motivated exploratory efforts in the use of LTE in the 5 GHz bands for downlink traffic. However, this paradigm raises concerns of fair sharing of the spectrum and the adverse impact of scheduled LTE frames on Wi-Fi Packet Success Rates (PSR). To address this issue, we propose E-Fi, an interference-evasion mechanism that allows Wi-Fi devices to survive LTE transmissions without any cooperation between these two different standards. Different from existing approaches, we argue that the simple use of Almost Blank Subframes (ABS) within the LTE standard offering short channel access windows overestimates opportunities for Wi-Fi. The pilots embedded in the ABS not only interfere with Wi-Fi but also adversely impact the carrier sensing function. E-Fi mitigates this problem through a two-fold approach. It uses a combination of (i) Wi-Fi Direct with packet relaying and (ii) classical distributed coordination function to reach distant nodes. Second, it ensures load balancing for both Wi-Fi uplink and downlink traffic with high PSR by creating node-groups based with dedicated contention-based medium access intervals. Our approach is validated by comprehensive simulation and experimental results that indicate significantly higher throughput in E-Fi compared to classical Wi-Fi.

As the dominant protocol on the Internet, TCP has attracted significant attention and has been implemented in various ways, each of which optimizes for a single objective such as high throughput or low delay. However, in today's mobile networks that carry traffic from diverse types of flows, this approach may lead to misconfiguration of TCP congestion control algorithms and further degrade performance for many applications. In this paper, we propose Janus, a new transport-layer framework that automatically selects among existing congestion control variants to optimize traffic in accordance with application demands. Janus is easy to deploy because it reuses existing, well-tested congestion control implementations, and does not require any in-network or client-side changes. To explore the potential for this approach, we implement Janus in the Linux kernel and extensively evaluate its performance with both emulated and real Internet traffic. We show Janus outperforms alternative protocols by offering fast convergence times in response to changing network conditions, achieving 5-10X lower delay with comparable or higher throughput. Our approach also significantly improves user-perceived performance according to QoE metrics, with up to 5X fewer interruptions for video streaming applications and 2X faster page loading for web-browsing applications.

In a world dominated by the wearable IoT devices, malicious security threats have become a common concern in system design. Guided by this notion, we propose a secure transmission system through body-guided channels using Galvanic Coupling (GC). The GC-method injects weak electrical current into human tissue, primarily propagating through the skin. The proposed design provides impermeability to malicious attacks, (e.g. side-channel sniffing) when sending biometric data, as the body behaves as a natural waveguide. The following contributions are: 1) the analytical formulation and empirical verification of a 3D tissue equivalent circuit model for GC-signal propagation of the human arm-wrist-palm channel; 2) the simulation study of numerous modulation schemes, drawn from the validated results of the GC-channel model; 3) the design and implementation of a transceiver prototype using optimal communication parameters (modulation, frequency, power) for transmission on a dielectrically equivalent tissue phantom; and 4) through the experimental trials, we demonstrate the eavesdropping susceptibility of the GCsignals, and similar body communication techniques, over-the-air and while in direct contact with the medium. The performance results of the GC-transceiver prototype yield a bit error rate of 10-6with a transmit power of -2 dBm, in addition to over 7x reduction of signal radiation outside the body compared to capacitive coupling.

Smart health (s-health) is a vital topic and an essential research field today, supporting the real-time monitoring of user’s data by using sensors, either in direct or indirect contact with the human body. Real-time monitoring promotes changes in healthcare from a reactive to a proactive paradigm, contributing to early detection, prevention, and long-term management of health conditions. Under these new conditions, continuous user authentication plays a key role in protecting data and access control, once it focuses on keeping track of a user’s identity throughout the system operation. Traditional user authentication systems cannot fulfill the security requirements of s-health, because they are limited, prone to security breaches, and require the user to frequently authenticate by, e.g., a password or fingerprint. This interrupts the normal use of the system, being highly inconvenient and not user friendly. Also, data transmission in current authentication systems relies on wireless technologies, which are susceptible to eavesdropping during the pairing stage. Biological signals, e.g., electrocardiogram (ECG) and electroencephalogram (EEG), can offer continuous and seamless authentication bolstered by exclusive characteristics from each individual. However, it is necessary to redesign current authentication systems to encompass biometric traits and new communication technologies that can jointly protect data and provide continuous authentication. Hence, this article presents a novel biosignal authentication system, in which the photoplethysmogram (PPG) biosignal and a galvanic coupling (GC) channel lead to continuous, seamless, and secure user authentication. Furthermore, this article contributes to a clear organization of the state of the art on biosignal-based continuous user authentication systems, assisting research studies in this field. The evaluation of the system feasibility presents accuracy in keeping data integrity and up to 98.66% accuracy in the authentication process.

Wireless RF energy transfer for indoor sensors is an emerging paradigm that ensures continuous operation without battery limitations. However, high power radiation within the ISM band interferes with the packet reception for existing WiFi devices. The paper proposes the first effort in merging the RF energy transfer functions within a standards compliant 802.11 protocol to realize practical and WiFi-friendly Energy Delivery (WiFED). The WiFED architecture is composed of a centralized controller that coordinates the actions of multiple distributed energy transmitters (ETs), and a number of deployed sensors that periodically request energy from the ETs. The paper first describes the specific 802.11 supported protocol features that can be exploited by sensors to request energy and for the ETs to participate in the energy delivery process. Second, it devises a controller-driven bipartite matching-based algorithmic solution that assigns the appropriate number of ETs to energy requesting sensors for an efficient energy transfer process. The proposed in-band and protocol supported coexistence in WiFED is validated via simulations and partly in a software defined radio testbed, showing 15% improvement in network lifetime and 31% reduction in the charging delay compared to the classical nearest distance-based charging schemes that do not anticipate future energy needs of the sensors and are not designed to co-exist with WiFi systems.

This paper presents FreeIoT, a control plane paradigm that allows fine grained signaling for city-scale IoT deployments without installing any additional infrastructure. FreeIoT overlays control/wake-up information for sensors over existing standards compliant LTE through the following contributions: First, we develop a novel encoding scheme that changes the spatial positioning of Almost Blank Subframes (ABS) within a standard LTE frame to convey control information. ABS was originally defined in the standard to allow coexistence between the macro-cell eNB and nearby small cells, which FreeIoT leverages as a side channel for IoT signaling. Our approach works with any number of ABS settings chosen by the LTE eNB, and accordingly adjusts the encoding of control messages at maximum possible transmission rates. Second, a session management protocol is introduced to maintain contextual information of the control signaling. This allows FreeIoT to handle situations where the control message may span multiple frames, or when the LTE operator temporarily reduces the number of ABS. FreeIoT also incorporates an error detection and correction mechanism to counter channel and fading errors. Finally, we implement a proof of concept testbed to validate the operation of FreeIoT using a software defined LTE eNB and custom-designed RF energy harvesting circuit interfaced with off-the-shelf sensors.

This paper proposes a network architecture and supporting optimization framework that allows Unmanned Aerial Vehicles (UAVs) to perform city-scale video monitoring of a set of Points of Interest (PoI). Our approach is systems-driven, relying on experimental studies to identify the permissible number of hops for multi-UAV video relaying in a noisy 3-D environment. Our architecture itself is innovative in the sense that it defines a mathematical framework for selecting the UAVs for periodic re-charging by landing on public transportation buses, and then `riding' the bus to the successive chosen Pol. Specifically, we show that our UAV scheduler can be modeled as an instance of multicommodity flow problems, and mathematically solved through Mixed Integer Linear Programming (MILP) techniques. Thus, our centralized formulation identifies the UAV, the next bus, and the next PoI, given the information about energy thresholds, the bus routes in the city and their next arrival times, to ensure persistent and reliable video coverage of all PoIs in the city. Finally, our work is validated via emulation of a city environment with live traffic updates from a real bus transportation network.

Emerging network architectures in 60GHz millimeter wave bands will likely use dense deployment of access points (APs) given the high attenuation and frequent line-of-sight related outages. We show in this paper that naively connecting to any available AP, or even multiple APs, may not fully realize the promise of efficiently utilizing the extremely large bandwidths available in this band. This paper holistically addresses these problems through the Multi-AP Association Protocol (MAP) that: (i) indicates ideal durations for beam-searching at the physical/link layers of the protocol stack that will result in minimal interruptions to user-traffic, (ii) devises a Multi-AP association framework based on multipath TCP, which increases the network robustness by allowing immediate redirection of traffic to alternative APs whenever an existing connection is interrupted, and (iii) designs an exploration-exploitation aware flow scheduling algorithm that dynamically activates the sub-flows to optimize transport layer performance. MAP is a lightweight, client side system that needs zero modifications to existing protocol stack, though it interacts with the latter to opportunistically trigger standards-defined functions. The paper also presents convergence analysis of throughput, experimental validation on a 60GHz network testbed, and trace-driven simulation studies that shows MAP achieving 5-7x reduction in re-buffering rate in HD video streaming, rapid convergence to the best possible AP, and fair allocation of resources among clients.

We present CapBand, a battery-free hand gesture recognition wearable in the form of a wristband. The key challenges in creating such a system are (1) to sense useful hand gestures at ultra-low power so that the device can be powered by the limited energy harvestable from the surrounding environment and (2) to make the system work reliably without requiring training every time a user puts on the wristband. We present successive capacitance sensing, an ultra-low power sensing technique, to capture small skin deformations due to muscle and tendon movements on the user's wrist, which corresponds to specific groups of wrist muscles representing the gestures being performed. We build a wrist muscles-to-gesture model, based on which we develop a hand gesture classification method using both motion and static features. To eliminate the need for per-usage training, we propose a kernel-based on-wrist localization technique to detect the CapBand's position on the user's wrist. We prototype CapBand with a custom-designed capacitance sensor array on two flexible circuits driven by a custom-built electronic board, a heterogeneous material-made, deformable silicone band, and a custom-built energy harvesting and management module. Evaluations on 20 subjects show 95.0% accuracy of gesture recognition when recognizing 15 different hand gestures and 95.3% accuracy of on-wrist localization.

Ambient radio frequency (RF) energy harvesting (RF-EH) allows powering low-power electronic devices without wires, batteries, and dedicated energy sources. Current RF-EH circuit designs for ambient RF harvesting are optimized and fabricated for a predetermined frequency band. Thus, a single circuit is tuned for a given band with simple extensions to multiple circuits operating individually in distinct bands. Our approach is different in the sense that it designs and implements a common circuit design that can operate on multiple different RF cellular and ISM bands. This paper makes two contributions. First, it presents a study of ambient RF signal strength distribution conducted in Boston, MA, USA, indicating locations and associated RF bands that can point toward the practicality of ambient RF-EH. Second, it demonstrates an adjustable circuit for harvesting from LTE 700-MHz, GSM 850MHz, and ISM 900-MHz bands with one single circuit. Our circuit design is fabricated on printed circuit board with comprehensive evaluations at each associated frequency to test the power conversion efficiency (PCE). In addition, we characterize the charging performance, and feasibility of powering sensors outdoors such as TI eZ430-RF2500. Results reveal more than 45% PCE for our prototype.

This paper proposes deployment strategies for consumer unmanned aerial vehicles (UAVs) to maximize the stationary coverage of a target area and to guarantee the continuity of the service through energy replenishment operations at ground charging stations. The three main contributions of our work are as follows. 1) A centralized optimal solution is proposed for the joint problem of UAV positioning for a target coverage ratio and scheduling the charging operations of the UAVs that involves travel to the ground station. 2) A distributed game-theory-based scheduling strategy is proposed using normal-form games with rigorous analysis on performance bounds. Furthermore, a bio-inspired scheme using attractive/repulsive spring actions are used for distributed positioning of the UAVs. 3) The cost-benefit tradeoffs of different levels of cooperation among the UAVs for the distributed charging operations is analyzed. This paper demonstrates that the distributed deployment using only 1-hop messaging achieves approximation of the centrally computed optimum, in terms of coverage and lifetime.

In an increasingly interconnected world, the rising number of wireless devices in the Internet of Things has caused heavy congestion on particular bandwidths (BWs). Due to spectrum scarcity, the need has arisen for these devices to operate on the same BWs. However, existing wireless devices are inflexible and have no capabilities to coexist with devices using other protocols. In this work, we propose new FPGA-based design techniques to receive multiple protocols on the same computing platform. Our methods incorporate tunable parameters, such as FIR filter length and number of bits per fixed-point word, to explore design tradeoffs regarding clock cycle, resource utilization, power consumption, and detection accuracy. We separate the physical (PHY) layer receive chains into a set of building blocks, including rate transition, pattern detection, and OFDM demodulation. We investigate implementation of the LTE physical downlink shared channel (PDSCH) and 802.11a protocols to test our techniques. LTE is the standard for high-speed wireless communication for mobile phones and data terminals; Wi-Fi uses variants of IEEE 802.11a. To ease the system development process, we develop our models using MathWorks Simulink, which supports auto-generation of HDL code for the non-critical sections and incorporation of hand-tuned HDL code as part of its black box interface. Our building blocks can be used by the wireless system modeling community to meet the needs of modern evolving wireless standards. In the future, our framework will allow researchers to achieve high-performance transceiver implementations on FPGA fabric for multiple cutting edge protocols.

Cognitive radio (CR) is an enabling technology that allows opportunistic use of under-utilized licensed spectrum allocated to primary users (PUs). However, the frequent channel sensing and switching interferes with the transport layer functions, leading to slow flow convergence during active transmissions by the CR. In this paper, we propose TCP C2, a method that greatly improves the flow responsiveness to abrupt variation of underlying layer spectrum availability in cellular CR architectures. The key idea of C2is to allow the sender to estimate the current bottleneck link bandwidth and network load by observing variance in the throughput and round trip time. Following this, fast congestion window scaling allows the flow to converge quickly to the optimal sending rate. Analytic derivations and packet-based simulation results show the increased resiliency of our approach over classical end-to-end TCP protocols in the presence of intermittent spectrum sensing and disruptions caused by PU arrival. Additionally, we show that C2enforces fairness among flows, and also coexists well with classical TCP flavors.

Several applications involving the utilization of Small Unmanned Aerial Vehicles (SUAVs) require stationary and long-term coverage of a target area. Unfortunately, this goal is hard to achieve due the need for coordination and the limited flight autonomy of the SUAVs. In this paper, we investigate how to guarantee persistent coverage of a target area through SUAVs by exploiting characteristics of fixed terrestrial infrastructure and inherent energy limitations. This paper makes three main contributions. First, the problem of SUAV activity scheduling is formulated for pre-existing fixed placements, and centrally solved to maximize the network lifetime given a target coverage ratio. Second, a distributed, bio-inspired algorithm is devised using local (1-hop) communication only, i.e., the scheme takes into account both positioning and charging issues allowing the SUAVs to self-organize into a maximum-coverage connected swarm, and coordinate the charging operations. Third, the performance of the distributed scheme is compared to the optimal solution, and the impact of the system parameters like the placement height and the discharging rate on the coverage metrics is discussed.

Implants are poised to revolutionize personalized healthcare by monitoring and actuating physiological functions. Such implants operate under challenging constraints of limited battery energy, heterogeneous tissue-dependent channel conditions and human-safety regulations. To address these issues, we propose a new cross-layer protocol for galvanic coupled implants wherein weak electrical currents are used in place of classical radio frequency (RF) links. As the first step, we devise a method that allows multiple implants to communicate individual sensed data to each other through CDMA code assignments, but delegates the computational burden of decoding only to the on-body surface relays. Then, we devise a distributed beamforming approach that allows coordinated transmissions from the implants to the relays by considering the specific tissue path chosen and tissue heating-related safety constraints. Our contributions are two fold: First, we devise a collision-free protocol that prevents undue interference at neighboring implants, especially for multiple deployments. Second, this is the first application of near-field distributed beamforming in human tissue. Results reveal significant improvement in the network lifetime for implants of up to 79% compared to the galvanic coupled links without beamforming.

Unmanned Aerial Vehicular (UAV) networks extend wireless access for devices without infrastructure coverage, and also help establish a connectivity backbone during military reconnaissance and disaster events. This paper focuses on the design of a resilient end-to-end connectivity paradigm under unique architectural and scenario assumptions. First, the UAVs themselves are equipped with multiple interfaces that use standardized protocols, with associated variation in data throughout, range, and bit error rates. Second, there may be adversarial agents seeking to disrupt connectivity through targeted jamming in 3D spaces. Third, we assume an overlay software defined control plane, where the UAVs function as software switches, able to execute forwarding commands and determine preferred routes under controller directives. Our proposed approach devises metrics that influence the choice of the wireless interface and weights edges formed between UAV pairs. Further, it also uses a multi-layer graph model and creates maximally separated paths in 3D space to ensure resiliency to jamming. Simulation results conducted for urban scenarios reveal 34% improvement in enhanced resiliency for end-to-end outages by trading off 12% increase in latency over competing approaches.

Advances in wireless technology have resulted in pervasive deployment of devices of a high variability in form factors, memory and computational ability. The need for maintaining continuous connections that deliver data with high reliability necessitate re-thinking of conventional design of the transport layer protocol. This paper investigates the use of Q-learning in TCP cwnd adaptation during the congestion avoidance state, wherein the classical alternation of the window is replaced, thereby allowing the protocol to immediately respond to previously seen network conditions. Furthermore, it demonstrates how memory plays a critical role in building the exploration space, and proposes ways to reduce this overhead through function approximation. The superior performance of the learning-based approach over TCP New Reno is demonstrated through a comprehensive simulation study, revealing 33.8% and 12.1% improvement in throughput and delay, respectively, for the evaluated topologies. We also show how function approximation can be used to dramatically reduce the memory requirements of a learning-based protocol while maintaining the same throughput and delay.

Software defined radio (SDR) allows unprecedented levels of flexibility by transitioning the radio communication system from a rigid hardware platform to a more user-controlled software paradigm. However, it can still be time consuming to design and implement such SDRs as they typically require thorough knowledge of the operating environment and a careful tuning of the program. In this work, we describe a systems contribution and outline strategies on how to create a state-action based design in implementing the CSMA/CA/ACK MAC layer in MATLAB®that runs on the USRP®platform, a commonly used SDR. Our design allows optimal selection of the parameters so that all operations remain functionally compliant with the IEEE 802.11b standard (1Mbps specification). The code base of the system is enabled through the Communications System ToolboxTMand incorporates channel sensing and exponential random back-off for contention resolution. The current work provides a testbed to experiment with and enables creation of new MAC protocols starting from the fundamental IEEE 802.11b compliant standard. Our system design approach guarantees the consistent performance of the bi-directional link and we include the experimental results for the three node system to demonstrate the robustness of the MAC layer in mitigating packet collisions and enforcing fairness among nodes.

Software-defined radios have introduced new platforms for dynamically modifying wireless system designs, and heterogeneous computing has opened up implementing such designs on different computing elements. Our goal is to develop a hardware-software modeling environment that captures reusability of various processing blocks at the physical layer for several modern protocols, and makes decisions regarding whether each processing block should be part of reconfigurable hardware or embedded processor software based on timing constraints and power budgets for the overlying applications. Our approach creates several different MathWorks Simulink model variants for both the transmitter and the receiver, each with a different boundary between hardware and software components. Using the 802.11a standard as an example, we use these models to generate a bitstream for the FPGA and executable code for the ARM processor on a Xilinx Zynq system-on-chip. Our results collect such metrics as data path delay, resource utilization, and power usage and demonstrate how to enhance the SDR design.

Galvanic coupling is the enabler of closed-loop communication between implanted sensors and embedded actuating devices (such as drug injectors) by providing energy-efficient and reliable non-RF transmission through links formed within tissue. For safe deployment, it is critical to verify that the amount of heat generated within tissues during signal propagation stays within permissible bound. In this paper, we analyze the thermal distribution within tissues, for galvanic coupling-based communication for varying transmission power levels, number of collocated transmitters, and blood perfusion conditions using finite element based numerical simulation and skin-phantom based experiments. Our results confirm that tissue heating remains well below safe limit of 1 °C. Using the temperature dissipation profile, we derive the suitable transmission duty cycles, separation distances and number of concurrent sources that may co-exist without raising the tissue temperature. The proposed strategies provide upto four fold increase in bandwidth efficiency through concurrent transmissions, ensuring sufficient bandwidth for implant communications.

Wireless RF power transmission from dedicated Energy Transmitters (ETs) is emerging as a promising approach to enable battery-less wireless networked sensor systems. However, when data communication and RF energy recharging occur in-band, sharing the RF medium and devoting separate access times for both operations raises architectural and protocol level challenges. This paper proposes a novel method of concurrent transmission of data and energy to solve this problem, allowing ETs to transmit energy and sensors to transmit data in the same band synchronously. Our key idea concerns devising a physical layer modulation scheme that allows the data transmitting node to introduce variations in the envelope of the energy signal at the intended recipient. We implemented a proof-of-concept receiver, modeled and validated through extensive experimentation. We then propose a new physical layer mechanism for guaranteed successful delivery of information in a point-to-point link. Quantitative results demonstrate the feasibility of joint energy-data transfer, along with its associated benefits and tradeoffs.

Implanted sensors and actuators in the human body promise in-situ health monitoring and rapid advancements in personalized medicine. We propose a new paradigm where such implants may communicate wirelessly through a technique called as galvanic coupling, which uses weak electrical signals and the conduction properties of body tissues. While galvanic coupling overcomes the problem of massive absorption of RF waves in the body, the unique intra-body channel raises several questions on the topology of the implants and the external (i.e., on skin) data collection nodes. This paper makes the first contributions towards (i) building an energy-efficient topology through optimal placement of data collection points/relays using measurement-driven tissue channel models, and (ii) balancing the energy consumption over the entire implant network so that the application needs are met. We achieve this via a two-phase iterative clustering algorithm for the implants and formulate an optimization problem that decides the position of external data-gathering points. Our theoretical results are validated via simulations and experimental studies on real tissues, with demonstrated increase in the network lifetime.

Simultaneous Wireless Information and Power Transmission (SWIPT) has been proposed as a feasible solution to enable joint power and data transfer for the nodes of a battery-less wireless networked sensor system. Different from existing approaches, where the incident energy is split between decoding and harvesting blocks at the receiver chain, this paper describes the design and implementation of an all-digital receiver circuit. We leverage the internal control signals of the circuit, targeting ultra-low power consumption, low bit-rate applications in SWIPT. A proof-of-concept receiver is modeled, implemented using off-the-shelf hardware, and validated through extensive experiments. Quantitative results demonstrate the benefits of this joint energy-data reception approach through a single receiver chain, offering bit-rates of 400 bps.

Smart homes will compose of multiple sensors that will sense, compute and transmit information to a central cloud, all of which are energy consuming tasks. We propose to demonstrate a software-defined solution for wirelessly charging these sensors using RF energy, thereby extending their lifetimes. In our demo, the actions of more than one energy transmitter (ET) are synchronized in phase and frequency in real time using periodic feedback from the target sensor, but without any common clock reference. The controller selects the optimal subset of ETs to satisfy the energy request from a given sensor, which cooperatively beamform RF energy towards that sensor. Our software-defined framework, implemented in Python, allows the central controller to automatically discover the installed sensors, obtain energy needs, and schedule charging tasks in an asynchronous and non-blocking manner that allows the network to scale. The demonstration includes advancements in design and fabrication of RF energy harvesting circuits that interface with the TI EZ430 sensors, implementation of a software-defined control and data plane, as well as a real-time distributed beamforming algorithm on USRP radios that results in a battery-free network of sensors.

This paper proposes the design and implementation of low-- energy tokens for smart interaction with capacitive touch-- enabled devices by associating the token's identity with its contact, or touch. The proposed token's design features two key novel technical components: (1) a through--touch--sensor low--energy communication method for token identification and (2) a touch--sensor energy harvesting technique. The communication mechanism involves the token transmitting its identity (ID) directly through the touch--sensor by artificially modifying the effective capacitance between the touch-- sensor and token surfaces. This approach consumes significantly lower energy compared to traditional electrical signal modulation approaches. By enabling the token to harvest energy from touch--screen sensors or touch--surfaces the token is rendered battery--free. Through experimental evaluations using a prototype implementation, the proposed design is shown to achieve at least 95% identification accuracy. It is also shown to consume less energy than competitive techniques (NFC P2P and Bluetooth Low--Energy) for communicating a short ID sequence. The adoption of this technology among users is evaluated through a user study on 12 subjects.

Full duplex communication promises a paradigm shift in wireless networks by allowing simultaneous packet transmission and reception within the same channel. While recent prototypes indicate the feasibility of this concept, there is a lack of rigorous theoretical development on how full duplex impacts medium access control (MAC) protocols in practical wireless networks. In this paper, we formulate the first analytical model of a CSMA/CA based full duplex MAC protocol for a wireless LAN network composed of an access point serving mobile clients. There are two major contributions of our work: First, our Markov chain-based approach results in closed form expressions of throughput for both the access point and the clients for this new class of networks. Second, our study provides quantitative insights on how much of the classical hidden terminal problem can be mitigated through full duplex. We specifically demonstrate that the improvement in the network throughput is up to 35-40 percent over the half duplex case. Our analytical models are verified through packet level simulations in ns-2. Our results also reveal the benefit of full duplex under varying network configuration parameters, such as number of hidden terminals, client density, and contention window size.

The recent surge of implantable and wearable medical devices have paved the way for realizing intra-body networks (IBNs). Traditional RF-based techniques fall short in wirelessly connecting such devices owing to absorption within body tissues. A different approach is known as galvanic coupling, which employs weak electrical current within naturally conducting tissues to enable intra-body communication. This work is focused on channel characterization of the human body tissues considering the propagation of such electrical signals through it that carry data. Experiments were conducted using porcine tissue (in lieu of actual human tissue) with skin, fat and muscle layers in the frequency range of 100 kHz to 1 MHz. By utilizing single-carrier BPSK modulated Pseudorandom Noise Sequences, a correlative channel sounding system was implemented, leading to the following contributions: (1) measurements of the channel impulse and frequency response, (2) a noise analysis and capacity estimation, and (3) the comparison of results with existing models.

Wireless RF power transmission promises battery-less, resilient, and perpetual wireless sensor networks. Through the action of controllable Energy Transmitters (ETs) that operate at-a- distance, the sensors can be re-charged by harvesting the radiated RF energy. However, both the charging rate and effective charging range of the ETs are limited, and thus multiple ETs are required to cover large areas. While this action increases the amount of wireless energy injected into the network, there are certain areas where the RF energy combines destructively. To address this problem, we propose a duty-cycled random- phase multiple access (DRAMA). Non-intuitively, our approach relies on deliberately generating random interferences, both destructive and constructive, at the destination nodes. We demonstrate that DRAMA optimizes the power conversion efficiency, and the total amount of energy harvested. Through real-testbed experiments, we prove that our proposed scheme provides significant advantages over the current state of the art in our considered scenario, as it requires up to 70% less input RF power to recharge the energy buffer of the sensor in the same time.

This paper formulates the location-dependent power harvesting rates in generalized 2D and 3D placement of multiple Radio Frequency (RF) Energy Transmitters (ETs) for recharging the nodes of a wireless sensor network (WSN). In particular, we study the distributions of total available and harvested power over the entire WSN. We provide closed matrix forms of harvestable power at any given point in space due to the action of concurrent energy transfer from multiple ETs, explicitly considering constructive and destructive interference of the transmitted energy signals. We also analyze the performance of energy transfer in the WSN through power outage probability, interference, and harvested voltage as a function of the wireless power received from the ETs. Our results reveal that the network wide received power and interference power from concurrent energy transfers exhibit Log-Normal distributions, and the harvested voltage over the network follows a Rayleigh distribution.

Implanted medical sensors and actuators within the human body will enable remote data gathering, diagnosis, and the ability to directly control drug delivery actuators. To establish the communication links through the body tissues, we adopt galvanic coupling that uses low frequency electrical signals of weak amplitude. In this paper, we propose a topology management strategy using Weiszfeld algorithm that attempts to minimize the transmission power of the body nodes by reducing the distance from the source nodes to pick-up points or relays that gather and forward the received information. It takes into account the unique propagation model of the electrical signals within the body at various tissue layers, which is completely different from over the air RF. Our algorithm considers separately the constraints of on-skin nodes and the implanted nodes, especially in terms of minimizing the energy for the latter, which cannot be easily retrieved and re-charged. It also considers the difference in specific bandwidth requirements for the applications running within the nodes, by moving relays closer towards the high data rate demanding regions. We show that by optimizing the position of the relay node, the energy consumption can be significantly improved to extend the lifetime of the intra-body network up to several years.

A wireless sensor network that employs passive radio wake-up of the sensor nodes can reduce the energy cost for unnecessary idle listening and communication overhead, extending the network lifetime. A passive wake-up radio is powered by the electromagnetic waves transmitted by a wake-up transmitter rather than a battery on the sensor node. However, this method of powering the wake-up radio results in a short wake-up range, which limits the performance of a passive wake-up radio sensor network. In this article, we describe our design of a passive wake-up radio sensor node—REACH 2 -Mote—using a high-efficiency, energy-harvesting module and a very low power wake-up circuit to achieve an extended wake-up range. We implemented REACH 2 -Mote in hardware and performed field tests to characterize its performance. The experimental results show that REACH 2 -Mote can achieve a wake-up range of 44 feet. We also modeled REACH 2 -Mote and evaluated its performance through simulations, comparing its performance to that of another passive wake-up radio approach, an active wake-up radio approach, and a conventional duty cycling approach. The simulation results show that REACH 2 -Mote can significantly extend the network lifetime while achieving high packet delivery rate and low latency.

Both Xilinx and Altera have released SoCs that tightly couple programmable logic with a dual core Cortex A9 ARM processor. These SoCs show promise in accelerating applications that exploit both the FPGA's parallel processing architecture and the CPU's sequential processing. For example, before accessing a wireless channel, a cognitive radio does spectrum sensing to detect channel occupancy and then makes a decision based on spectrum policies. Spectrum sensing maps well to FPGA fabric, while spectrum decision can be implemented with a CPU. Both algorithms are highly sensitive to latency as a faster decision improves spectrum utilization. This paper introduces CRASH: Cognitive Radio Accelerated with Software and Hardware - a new software and programmable logic framework for Xilinx's Zynq SoC targeting cognitive radio. We implement spectrum sensing and the spectrum decision in three configurations: both algorithms in the FPGA, both in software only, and spectrum sensing on the FPGA and spectrum decision on the CPU. We measure the end-to-end latency to detect and acquire unoccupied spectrum for these configurations. Results show that CRASH can successfully partition algorithms between FPGA and CPU and reduce processing latency.

Wireless transfer of energy through directed radio frequency waves has the potential to realize perennially operating sensor nodes by replenishing the energy contained in the limited on-board battery. However, the high power energy transfer from energy transmitters (ETs) interferes with data communication, limiting the coexistence of these functions. This paper provides the first experimental study to quantify the rate of charging, packet loss due to interference, and suitable ranges for charging and data communication of the ETs. It also explores how the placement and relative distances of multiple ETs affect the charging process, demonstrating constructive and destructive energy aggregation at the sensor nodes. Finally, we investigate the impact of the separation in frequency between data and energy transmissions, as well as among multiple concurrent energy transmissions. Our results aim at providing insights on radio frequency-based energy harvesting wireless sensor networks for enhanced protocol design and network planning.

Cognitive radio (CR) vehicular networks are poised to opportunistically use the licensed spectrum for high bandwidth inter-vehicular messaging, driver-assist functions, and passenger entertainment services. Recent rulings that mandate the use of spectrum databases introduce additional challenges in this highly mobile environment, where the CR enabled vehicles must update their spectrum data frequently and complete the data transfers with roadside base stations. As the rules allow local spectrum sensing only under the assurance of high accuracy, there is an associated tradeoff in obtaining assuredly correct spectrum updates from the database at a finite cost, compared to locally obtained sensing results that may have a finite error probability. This paper aims to answer the question of when to undertake local spectrum sensing and when to rely on database updates through a novel method of exploiting the correlation between 2G spectrum bands and TV whitespace. We describe experimental studies that validate our approach and quantify the cost savings made possible by intermittent database queries.

Vehicular networks that require additional spectrum for communication may leverage cognitive radio technology. Towards this aim, the vehicle must select one among several candidate channels for data transmission, with the possibility that other surrounding vehicles may also identify the same spectrum for their use. Such networks are distinguished from their classical, stationary counterparts by high mobility, time-varying and heterogeneous environment leading to dynamic channel availability. Owing to this changing environment, the history of spectrum usage information may be unavailable to the vehicles at all points on their journey, necessitating blind decision-making. In this paper, we propose a method of spectrum selection without a priori channel information. The main contributions of our work are: (i) we provide a framework to determine, through a Hidden Markov Model, whether a channel is occupied by a licensed user, another cognitive radio enabled vehicle, or if the observed signal fluctuations are due to noise; and (ii) we devise a prediction algorithm to determine which channels are likely to be available within the shortest amount of time. Our approach is verified through a simulation study, and we demonstrate equivalent performance to schemes that use prior history of the channel usage at specific vehicle locations.

Guaranteeing network connectivity in post-disaster scenarios is challenging yet crucial to save human lives and to coordinate the operations of first responders. In this paper, we investigate the utilization of low-altitude aerial mesh networks composed by Small Unmanned Aerial Vehicles (SUAVs) in order to re-enstablish connectivity among isolated end-user (EU) devices located on the ground. Aerial ad-hoc networks provide the advantage to be deployable also on critical scenarios where terrestrial mobile devices might not operate, however their implementation is challenging from the point of view of mobility management and of coverage lifetime. In this paper, we address both these issues with three novel research contributions. First, we propose a distributed mobility algorithm, based on the virtual spring model, through which the SUAV-based mesh node-called also Repairing Units (RUs) in this study- can self-organize into a mesh structure by guaranteeing Quality of Service (QoS) over the aerial link, and connecting the maximum number of EU devices. Second, we evaluate our scheme on a realistic 3D environment with buildings, and we demonstrate the effectiveness of the aerial deployment compared to a terrestrial one, in terms of coverage and wireless link reliability. Third, we address the problem of energy lifetime, and we propose a distributed charging scheduling scheme, through which a persistent coverage of RUs can be guaranteed over the emergency scenario.

Harvesting energy from radio frequency (RF) waves brings us closer to achieving the goal for perpetual operation of a wireless sensor network (WSN) by replenishing the batteries of the sensor nodes. However, due to restrictions on the maximum transmitted power, path loss, and receiver sensitivity, only a small amount of energy can be harvested. While a dedicated RF source alleviates the problem to some extent, novel techniques are required to boost the energy transfer efficiency of the source. In this paper, we provide the first experimental demonstration of multi-path energy routing (MPER) for the case of a sparsely distributed WSNs and show its improved performance over direct energy transfer (DET). In addition, we extend this concept to the case of densely distributed WSNs and experimentally demonstrate and compare the gains obtained by 2- and 3-path energy routing over DET. Our experimental results show that significant energy gains can be achieved in a dense network deployment even when the node to be charged is partially blocked by the neighboring nodes.

Cognitive radio (CR) networks will enable dynamic spectrum re-use and thereby accelerate the adoption of high bandwidth services in available licensed frequencies with better channel characteristics. However, the possibility of the licensed user reclaiming the channel raises additional concerns on how best to reserve resources for secondary users (SUs) that are likely to have different qualities of service (QoSs) depending on their application requirements. This paper addresses the problem of spectrum resource management for co-located SUs with both streaming and intermittent data by efficiently identifying the number of backup channels that will ensure seamless end to end service. The contributions of this paper are threefold: First, a comprehensive analytical framework based on queueing theory is devised to calculate the theoretical delay in accessing the spectrum depending on the required QoS, with guidelines on how to optimize the set of back-up channels for possible future use; second, a method of spectrum allocation for SUs with these different QoS demands is formulated, especially as they co-exist and affect the performance of each other; third, a case study of applying these techniques in a novel application area of wireless medical telemetry is presented. Results reveal that the simulated spectral efficiency of the channel allocation using our approach matches closely with our theoretical predictions, within a 5% bound.

Wireless charging through directed radio frequency (RF) waves is an emerging technology that can be used to replenish the battery of a sensor node, albeit at the cost of data communication in the network. This tradeoff between energy transfer and communication functions requires a fresh perspective on medium access control (MAC) protocol design for appropriately sharing the channel. Through an experimental study, we demonstrate how the placement, the chosen frequency, and number of the RF energy transmitters impact the sensor charging time. These studies are then used to design a MAC protocol called RF-MAC that optimizes energy delivery to sensor nodes, while minimizing disruption to data communication. In the course of the protocol design, we describe mechanisms for (i) setting the maximum energy charging threshold, (ii) selecting specific transmitters based on the collective impact on charging time, (iii) requesting and granting energy transfer requests, and (iv) evaluating the respective priorities of data communication and energy transfer. To the best of our knowledge, this is the first distributed MAC protocol for RF energy harvesting sensors, and through a combination of experimentation and simulation studies, we observe 300% maximum network throughput improvement over the classical modified unslotted CSMA MAC protocol.

Use of a passive wake-up radio can drastically increase the network lifetime in a sensor network by reducing or even completely eliminating unnecessary idle listening. A sensor node with a wake-up radio receiver (WuRx) can operate in an extremely low power sleep mode until it receives a trigger signal sent by a wake-up radio transmitter (WuTx). After receiving the trigger signal, the attached WuRx wakes up the sensor node to start the data communication. In this paper, we implement and compare the performance of three passive wake-up radio-based sensor nodes: 1) WISP-Mote, which is a sensor mote that employs an Intel WISP passive RFID tag as the WuRx; 2) EH-WISP-Mote, which combines a novel energy harvester with the WISP-Mote; and 3) REACH-Mote, which uses the energy harvester circuit combined with an ultra-low-power pulse generator to trigger the wake-up of the mote. Experimental results show that the wake-up range and wake-up delay for the EH-WISP-Mote are improved compared with the WISP-Mote, while providing the ability to perform both broadcast-based and ID-based wake-ups. On the other hand, the REACH-Mote, which can only provide broadcast-based wake-up, can achieve a much longer wake-up range than any known passive wake-up radio to date, achieving feasible wake-up at a range of up to 37 ft.

Wireless transfer of energy will help realize perennially operating sensors, where dedicated transmitters replenish the residual node battery level through directed radio frequency (RF) waves. However, as this radiative transfer is in-band, it directly impacts data communication in the network, requiring a fresh perspective on medium access control (MAC) protocol design for appropriately sharing the channel for these two critical functions. Through an experimental study, we first demonstrate how the placement, the chosen frequency, and number of the RF energy transmitters affect the sensor charging time. These studies are then used to design a MAC protocol called RFMAC that optimizes energy delivery to desirous sensor nodes on request. To the best of our knowledge, this is the first distributed MAC protocol for RF energy harvesting sensors, and through a combination of experimentation and simulation studies, we demonstrate 112% average network throughput improvement over the modified unslotted CSMA MAC protocol.

Batteries of field nodes in a wireless sensor network pose an upper limit on the network lifetime. Energy harvesting and harvesting aware medium access control protocols have the potential to provide uninterrupted network operation, as they aim to replenish the lost energy so that energy neutral operation of the energy harvesting nodes can be achieved. To further improve the energy harvesting process, there is a need for novel schemes so that maximum energy is harvested in a minimum possible time. Multi-hop radio frequency (RF) energy transfer is one such solution that addresses these needs. With the optimal placement of energy relay nodes, multi-hop RF energy transfer can save energy of the source as well as time for the harvesting process. In this work we experimentally demonstrate multi-hop RF energy transfer, wherein two-hop energy transfer is shown to achieve significant energy and time savings with respect to the single-hop case. It is also shown that the gain obtained can be translated to energy transfer range extension.

While great strides have been made in spectrum sensing techniques in cognitive radio networks, these approaches are susceptible to unconventional attacks that may result in catastrophic performance degradation of the spectrum usage efficiency. For example, primary user emulation, intelligent jamming and denial of service for spectrum usage may impact the performance of classical spectrum sensing approaches. To address these challenges, this paper proposes a multi-dimensional cooperative sensing framework that can flexibly incorporate a variety of physical layer features to identify cases related to malicious behavior and genuine node failures. Though our approach is distributed, it is resilient in the sense that it does not simply rely on majority voting by a collection of nearby nodes. The key contributions of this paper are as follows: (i) A multiple criteria analysis technique and a non-parametric Bayesian inference method are formulated for identifying the spectrum holes that are least susceptible to malicious activity and failures, and (ii) Using real traces from the CRAWDAD data repository, we test our framework in a variety of practical settings, to prove the performance benefit of our approach.

It is our great pleasure to welcome you to the Second IEEE International Workshop on Emerging COgnitive Radio Applications and aLgorithms (CORAL 2013), held in Madrid on June 4, 2013, in conjunction with the IEEE WoWMoM 2013 Conference.

Cognitive Radio (CR) networks allow users to opportunistically transmit in the licensed spectrum bands, as long as the performance of the Primary Users (PUs) of the band is not degraded. Consequently, variation in spectrum availability with time and periodic spectrum sensing undertaken by the CR users have a pronounced effect on the higher layer protocol performance, such as at the transport layer. This paper investigates the limitations of classical TCP newReno in a CR ad hoc network environment, and proposes TCP CRAHN, a window-based TCP-friendly protocol. Our approach incorporates spectrum awareness by a combination of explicit feedback from the intermediate nodes and the destination. This is achieved by adapting the classical TCP rate control algorithm running at the source to closely interact with the physical layer channel information, the link layer functions of spectrum sensing and buffer management, and a predictive mobility framework that is developed at the network layer. An analysis of the expected throughput in TCP CRAHN is provided, and simulation results reveal significant improvements by using our approach. To the best of our knowledge, our approach takes the first steps toward the design of a transport layer for CR ad hoc networks.

Cognitive radio (CR) allows a pair of wireless communicating devices to intelligently adapt their transmission parameters based on the characteristics of the radio frequency (RF) environment, possibly using vacant portions of licensed frequency bands. A key step in this process is spectrum sensing, where the presence of primary users of the spectrum is detected by sending raw samples from the front-end to the host computer, a process that incurs significant processing delay. In this paper we introduce the Cognitive Radio Universal Software Hardware (CRUSH) platform that revisits the classical software defined radio (SDR) architecture by including a Xilinx ML605 FPGA board, thereby flexibly sharing the processing load with the host computer. CRUSH shifts the spectrum sensing overhead closer to the front-end. Our design results in orders of magnitude speedup and can flexibly connect up to three SDRs together, resulting in a powerful platform suitable for time-sensitive CR functions.

The FPGA is an integral component of a software defined radio (SDR) that provides the needed reconfigurability for dynamically adapting its transceiver and data processing functions. Because of the desire to process data faster and with less latency, researchers are looking at FPGA-based SDR. Our architecture, called CRUSH, is composed of a Xilinx ML605 connected to an Ettus USRP through a a custom interface board allowing flexible data transfer between them. In addition, we provide a framework that supports ease of use, independent programming on both devices, and integration with software running on the host. To demonstrate our platform we implemented spectrum sensing, a key step in determining channel availability before transmission in dynamic spectrum access networks. Spectrum sensing is implemented on CRUSH using FFTs for a 100× speedup; the complete sensing cycle is 10× faster than the same design without CRUSH. By reducing the load of transferring raw samples to the host and allowing a powerful FPGA extension for off-the-shelf devices, CRUSH enables advances in both protocol design and reconfigurable hardware targeting radio applications.

This paper presents SAVE, for Stochastic Analysis and aVailability of Energy, an analytical framework providing closed form expressions for residual energy and lifetime prediction of wireless sensor nodes. SAVE models a wide umbrella of input factors, including channel characteristics, different energy sources and harvesting policies, link layer parameters (e.g., error control and duty cycling) and various data traffic generation models. Our framework uses stochastic semi-Markov models to derive the residual energy distribution for each harvesting node accounting for practically observed temporal variations. We validate the analytical expressions derived by SAVE by means of simulations, and show that SAVE predictions provide a remarkably close match to the simulation results.

Wireless Medical Telemetry Systems (WMTS) currently operate on FCC designated bands for transmitting critical patient health information to distant receivers within hospitals. However, the current devices experience intermittent interference from digital TV transmissions in neighboring channels; are prohibited from transmitting multimedia data; and must operate with a secondary access priority in portions of the WMTS band, also shared with utility metering. We propose a fundamentally new communication paradigm for medical telemetry through dynamic spectrum access technology that adheres to the access rules in the WMTS band, and yet addresses the above concerns. The contributions of the paper are as follows: (i) we undertake a spectrum measurement study at hospital locations in the Boston area to model spectrum usage and activities in the medical band, (ii) we formulate the channel and power allocation task as an optimization problem under constrains of permissible electromagnetic interference to sensitive medical equipment, and latency, bandwidth thresholds of the medical data. Simulation results reveal the potential benefit of the use of dynamic spectrum access to improve medical telemetry and promises long-term improvement in the healthcare domain.

It is our great pleasure in welcoming you to the First IEEE International Workshop on Emerging COgnitive Radio Applications and aLgorithms (CORAL), held in conduction with the IEEE WoWMoM conference. We have a great technical program lined up on this fast emerging and potentially disruptive field of Cognitive Radio, bringing together researchers, practitioners, and students from both industry and academia. We are excited to have a forum facilitating the cross-pollination of ideas from both theoretical and practical perspective, and look forward to your participation.

Distributed spectrum allocation in Cognitive Radio (CR) systems requires each Secondary User (SU) to learn the optimal spectrum policy which maximizes the network performance while minimizing the impact to the Primary Users (PUs). To this aim, each SU must rely on local sensing information which however can be biased by interference and fading effects on the received signal. Thus, if each SU works in isolation, the convergence to the system-wide optimal policy can not be guaranteed. In this paper, we formulate the spectrum allocation problem as a cooperative learning task in which each SU can learn the spectrum availability of each channel and share such knowledge with the other SUs. We propose a correlation model through which different SUs can leverage the experience of other nodes, and we integrate it into a distributed channel allocation scheme. At the same time, we investigate mechanisms to bound the cooperation overhead based on the performance of the distributed learning process. Simulation results confirm the ability of the cooperative learning scheme in providing higher sensing accuracy and convergence time when compared with noncooperative spectrum allocation schemes for CR networks.

Cognitive Radio (CR) technology constitutes a promising approach to increase the capacity of Wireless Mesh Networks (WMNs). Using this technology, Mesh Routers (MRs) and the attached Mesh Clients (MCs) are allowed to opportunis- tically transmit on the licensed band, but under the constraint not to interfere with the Primary Users (PUs) of the spectrum. Thus, the effective deployment of CR- WMNs require that each MR must be able to: sense the current spectrum, select an available PU-free channel and perform the spectrum handoff to a new channel in case of PU arrival on the current one. How to coordinate these actions in the optimal way which maximizes the performance of the CR-WMNs while minimizing the interference to the PUs constitutes an open research issue in CR systems. In this paper, we propose an adaptive spectrum scheduling and allocation scheme which allows a MR to identify the best schedule of (i) when to sense the current channel, (ii) when to transmit, (iii) when to perform a spectrum handoff. Due the large number of parameters involved, we propose Reinforcement Learning (RL) techniques to allow a MR to learn by itself the optimal balance between spectrum sensing-exploitation- exploration actions based on network feedbacks coming from the MCs. We perform extensive simulations which confirm the adaptivity and efficiency of our approach in terms of increased throughput when compared with non-learning based schemes for CR-WMNs.

The emerging paradigm of wearable and implantable medical sensors has enabled continuous and unobtrusive monitoring for patients and human subjects, allowing them to continue their normal activities, and yet be assured of immediate response in case of a detected health emergency. Energy harvesting has been proposed as a viable scheme for powering such sensors as periodic retrievals for battery replacements may not be feasible. The current state of the art in energy harvesting allows tapping into several physical and naturally existing sources, such as solar, wind, vibration, RF scavenging, among others. However, there is a lack of theoretical models that can predict future consumption and residual availability of energy in a sensor node equipped with multiple boards that can simultaneously operate on different types of sources. In this paper, we propose MAKERS, a Markov model based method to capture the energy states of such sensors. MAKERS allows detailed prediction of the probability of a node failing to detect an event owing to lack of energy, which is a key design consideration for body sensor sensors.

Spectrum sharing is envisaged to allow multiple cognitive radio (CR) nodes to jointly use the vacant spectrum resource for opportunistic transmission. Most previous work on the spectrum sharing did not take into account the spectrum heterogeneity, such as different transmission ranges, error rates, etc. In this paper, a spectrum sharing algorithm is presented that accommodates spectrum heterogeneity for centralized CR networks, meanwhile the individual users are free to be mobile. Each node is uniquely assigned a channel while considering its channel occupancy time, the location of the node, and the fairness of channel access opportunity. Each of these metrics contributes in part to a larger optimization problem and the final objective is to maximize the total utility of system. Simulations results reveal significant improvement in reducing spectrum handoffs.

Cognitive radio (CR) ad hoc networks are composed of wireless nodes that may opportunistically transmit in licensed frequency bands without affecting the primary users of that band. In such distributed networks, gathering the spectrum information is challenging as the nodes have a partial view of the spectrum environment based on the local sensing range. Moreover, individual measurements are also affected by channel uncertainties and location-specific fluctuations in signal strength. To facilitate the distributed operation, this paper makes the following contributions: (i) First, an experimental study is undertaken to measure the signal characteristics for indoor and outdoor locations for the TV channels 21 – 51, and these results are used to identify the conditions under which nodes may share information. (ii) Second, a Cooperative reinforcement LearnIng scheme for Cognitive radio networKs (CLICK) is designed for combining the spectrum usage information observed by a node and its neighbors. (iii) Finally, CLICK is integrated within a MAC protocol for testing the benefits and overhead of our approach on a higher layer protocol performance. The proposed learning framework and the protocol design are extensively evaluated through a thorough simulation study in ns-2 using experimental traces of channel measurements.

Cognitive radio (CR) technology enables the opportunistic use of the vacant licensed frequency bands, thereby improving the spectrum utilization. However, the CR operation must not interfere with the transmissions of the licensed or primary users (PUs), and this is generally achieved by incurring a trade-off in the CR network performance. In order to evaluate this trade-off, a distributed CR routing protocol for ad hoc networks (CRP) is proposed that makes the following contributions: (i) explicit protection for PU receivers that are generally not detected during spectrum sensing, (ii) allowing multiple classes of routes based on service differentiation in CR networks, and (iii) scalable, joint route-spectrum selection. A key novelty of CRP is the mapping of spectrum selection metrics, and local PU interference observations to a packet forwarding delay over the control channel. This allows the route formation undertaken over a control channel to capture the environmental and spectrum information for all the intermediate nodes, thereby reducing the computational overhead at the destination. Results reveal the importance of formulating the routing problem from the viewpoint of safeguarding the PU communication, which is a unique feature in CR networks.

Cognitive radio (CR) technology allows devices to opportunistically use the vacant portions of the licensed wireless spectrum. However, the available spectrum changes dynamically with the primary user (PU) activity, necessitating frequent PU sensing coordination and exchanging network topology information in a multihop CR ad hoc network. To facilitate these tasks, an always-on, out-of-band common control channel (CCC) design is proposed that uses noncontiguous OFDM subcarriers placed within the guard bands separating the channels of the licensed spectrum. First, the task of choosing the OFDM-specific parameters, including the number, power, and bandwidth of the subcarriers is formulated as a feasibility problem to ensure that the CCC does not adversely interfere with the PU operation. Second, for unicast messaging between a given pair of users, a subset of the guard bands may be chosen, which allows an additional measure of protection for the adjacent PU spectrum. For this, the multiarm bandit algorithm is used that allows the guard band selection to evolve over time based on the observed interference from the PU. Results reveal that our proposed CCC ensures connectivity and improved PU protection with a limited trade-off in data rate when compared to frequency-hopping and cluster-based CCC schemes.

Spectrum sensing allows the cognitive radio (CR) devices to determine the presence of licensed users in the chosen spectrum band. Though several sensing methods based on energy detection and cyclostationary feature extraction have been proposed, they fail to account for the location-specific results, and provide no incentive for the node to perform sensing at the cost of its own data throughput. In this work, a node admission policy called CORAL is proposed for CR wireless mesh networks that ranks candidate joining mesh clients (MCs) based on their distinct contributions towards the spectrum sensing coverage area. Moreover, CORAL incorporates different traffic classes, and attempts to keep the higher ranked MCs affiliated to the mesh cluster for longer durations of time. Simulation results reveal improved throughput and enhanced PU protection in the area, in which the licensed and CR users co-exist.

Wireless sensor networks are equipped with batteries with limited charge, and are often deployed in conditions that make their retrieval and replacement infeasible. Thus, energy conservation has been a primary consideration for protocol design for such networks. Recent advancements in the transfer of energy wirelessly over large distances, such as through radio frequency electromagnetic (EM) waves and magnetic coupling, may give rise to a new class of networks that allow the sensors to be charged on the field, thereby prolonging the network lifetime. Moreover, wireless charging though EM waves may be undertaken in the same unlicensed band as that used for communication, leading to several unique protocol design challenges for such a network. The contribution of this paper is threefold: First, a set of experiments is undertaken to investigate the effect of distance and location on the energy transfer through EM waves. Second, a new routing metric based on the charging ability of the sensor nodes is proposed. Finally, an optimization framework is developed to determine the optimal charging and transmission cycle for the sensor network, resulting in enhanced lifetime of the network under user-specified end-to-end constraints of throughput and latency.

Wireless sensor networks (WSNs) are being increasingly deployed in office blocks or residential areas for commercial applications, such as home automation, meter reading, surveillance, among others. At these locations, the WSNs experience interference in the 2.4 GHz unlicensed band due to wireless LANs (WLANs) and commercial microwave devices, leading up to 92% packet losses. In this paper, an algorithmic framework is proposed, that allows the sensor nodes to identify the type of the interferer and its operational channel, so that the former may adapt their own transmission to reduce packet losses in the network. Our proposed interference classification approach comprises of an (i) offline measurement of the spectral characteristics of the WLAN and microwave devices to obtain a reference spectrum shape, and (ii) matching the observed spectral pattern during network operation with the stored reference shape The knowledge of the interferer characteristics is then leveraged by the sensor nodes to decide their transmission channel, packet scheduling times and sleep-awake cycles. Results reveal that our approach incurs up to 50 - 70% energy savings in the WSN, by reducing interference related packet losses.

Existing research in transport protocols for wireless ad-hoc networks has focused on reliable end-to-end packet delivery under uncertain channel conditions, route failures due to node mobility and link congestion. In a cognitive radio (CR) environment, there are several key challenges that must be addressed apart from the above concerns. The intermittent spectrum sensing undertaken by the CR users, the activity of the licensed users of the spectrum, large-scale bandwidth variation based on spectrum availability, and the channel switching process need to be considered in the transport protocol design. In this paper, a window-based transport protocol for CR ad-hoc networks, TP-CRAHN, is proposed that distinguishes each of these events by a combination of explicit feedback from the intermediate nodes and the destination. This is achieved by adapting the classical TCP rate control algorithm running at the source to closely interact with the physical layer channel information, the link layer functions of spectrum sensing and buffer management, and a predictive mobility framework that is developed at the network layer. To the best of our knowledge, this is the first work on the transport layer to specifically address the concerns of the CR ad-hoc networks and our approach is thoroughly validated by simulation experiments.

Cognitive Radio (CR) technology constitutes a new paradigm to provide additional spectrum utilization opportunities in wireless ad hoc networks. Recent research in this field has mainly focused on devising spectrum sensing and sharing algorithms, to allow an opportunistic usage of licensed portions of the spectrum by Cognitive Radio Users (CRUs). However, it is also important to consider the impact of such schemes on the higher layers of the protocol stack, in order to provide efficient end-to-end data delivery. Since TCP is the de facto transport protocol standard on Internet, it is crucial to estimate its ability in providing stable end-to-end communication over Cognitive Radio Ad Hoc Networks (CRAHNs). The contributions of this paper are twofold. First, we propose an extension of the NS-2 simulator to support realistic simulation of CRAHNs. Our extension allows to model the activities of Primary Users (PUs), and the opportunistic spectrum management by CRUs in the licensed band. Second, we provide an accurate simulation analysis of the TCP performance over CRAHNs, by considering the impact of three factors: (i) spectrum sensing cycle, (ii) interference from PUs and (iii) channel heterogeneity. The simulation results show that the sensing interval and the PU activity play a critical role in deciding the optimal end-to-end performance, and reveals the inadequacy of classical TCP to adapt to variable spectrum conditions.

Wireless Mesh Networks (WMNs) are envisaged to extend Internet access and other networking services in personal, local, campus, and metropolitan areas. Mesh routers (MR) form the connectivity backbone while performing the dual tasks of packet forwarding as well as providing network access to the mesh clients. However, the performance of such networks is limited by traffic congestion, as only limited bandwidth is available for supporting the large number of nodes in close proximity. This problem can be alleviated by the cognitive radio paradigm that aims at devising spectrum sensing and management techniques, thereby allowing radios to intelligently locate and use frequencies other than those in the 2.4 GHz ISM band. These promising technologies are integrated in our proposed Cognitive Mesh NETwork (COMNET) algorithmic framework, thus realizing an intelligent frequency-shifting self-managed mesh network. The contribution of this paper is threefold: (1) A new approach for spectrum sensing is devised without any change to the working of existing de facto mesh protocols. (2) An analytical model is proposed that allows MRs to estimate the power in a given channel and location due to neighboring wireless LAN traffic, thus creating a virtual map in space and frequency domains. (3) These models are used to formulate the task of channel assignment within the mesh network as an optimization problem, which is solved in a decentralized manner. Our analytical models are validated through simulation study, and results reveal the benefits of load sharing by adopting unused frequencies for WMN traffic.

The availability of low-cost hardware is enabling the development of wireless multimedia sensor networks (WMSNs), i.e., networks of resource-constrained wireless devices that can retrieve multimedia content such as video and audio streams, still images, and scalar sensor data from the environment. In this paper, ongoing research onprototypesofmultimediasensorsand their integration intotestbedsforexperimentalevaluationof algorithms and protocols for WMSNs are described. Furthermore, open research issues and future research directions, both at the device level and at the testbed level, are discussed. This paper is intended to be a resource for researchers interested in advancing the state-of-the-art in experimental research on wireless multimedia sensor networks.

Tins paper presents CMAC, a fully desynchronized MAC protocol that is designed to exploit the existing multi-channel support in sensor nodes. The hardware requirements of our protocol are minimal, requiring a single half-duplex transceiver and a low-power wake-up radio. CMAC takes into account the fundamental energy constraint in sensor nodes by placing them in a default sleep mode and waking them up only when necessary. As a contrast to other dual radio wake-up schemes, our protocol focuses on how communication and its preceding control message exchange mechanism can be undertaken in a multi-channel scenario without assuming a separate control channel. CMAC enables spatial channel re-use, nearly collision free communication, and addresses the deafness problem without incurring a tradeoff in fairness or latency. When compared with a recent MAC protocol SMAC, results show that CMAC obtains nearly 200% reduction in energy consumption, significantly improved throughput, and end-to-end delay values that are 50-150% better than SMAC for our simulated topologies

Over the past few years, wireless local area networks (WLANs) have gained an increased attention and a large number of WLANs are being deployed in universities, companies, airports etc. Majority of the IEEE 802.11 based WLANs employ distributed coordination function (DCF) in wireless access points (AP) to arbitrate the wireless channel among Wireless Stations (STAs). However, DCF poses serious unfairness problem between uplink and downlink flows. To overcome this unfairness problem, we propose a simple enhancement to the IEEE 802.11 DCF which provides priority to the AP and thus enables it to acquire a larger share of the channel when required. We have demonstrated the unfairness problem through systematic measurements in an experimental test bed of WLAN using the legacy 802.11 DCF. We also developed analytical models to calculate the throughput of AP and the STAs and verify these results through thorough simulations in ns-2. We observe that our simulation results find in good agreement with our analytical models. Results show that our proposed enhancement achieves a fair distribution of bandwidth and improves the throughput (by nearly 300%) for the downlink flows as compared to the DCF, without severely affecting the performance of uplink flows

In this paper we propose a method for data compression and its subsequent regeneration using a polynomial regression technique. We approximate data received over the considered area by fitting it to a function and communicate this by passing only the coefficients that describe the function. In this paper, we extend our previous algorithm TREG to consider non-complete aggregation trees. The proposed algorithm DUMMYREG is run at each parent node and uses information present in the existing child to construct a complete binary tree. In addition to obtaining values in regions devoid of sensor nodes and reducing communication overhead, this new approach further reduces the error when the readings are regenerated at the sink. Results reveal that for a network density of 0.0025 and a complete binary tree of depth 4, the absolute error is 6%. For a non-complete binary tree, TREG returns an error of 18% while this is reduced to 12% when DUMMYREG is used

Wireless sensor networks have enabled information gathering from a large geographical region and present unprecedented opportunities for a broad spectrum of monitoring applications. In this paper, we propose a data-centric storage scheme to determine a distribution of attributes over a large-scale sensor network such that the cost of retrieving data is minimized. We analytically determine the conditions under which the proposed architecture is beneficial and present simulation results to demonstrate the same. To the best of our knowledge, this is the first attempt to determine an allocation of attributes over a sensor network based on the correlations between attributes

This paper introduces a distributed channel assignment scheme (DCA) for wireless sensor networks. Recent developments in sensor technology, as seen in Berkeley's Mica2 Mote, Rockwell's WINS nodes and the IEEE 802.15.4 Zigbee, have enabled support for single-transceiver, multi-channel communication. DCA exploits this capability by assigning optimally minimum channels in a distributed manner in order to make subsequent communication free from both primary and secondary interference. The main contribution of this paper is solving the channel assignment problem, also named as the 2-hop coloring problem, in which repetition of colors occurs only if the nodes are separated by more than 2 hops. Our work achieves legal coloring under energy constrained conditions for sensor networks and significant performance improvements are shown when compared with similar existing schemes. Finally, we validate our approach through extensive analysis and simulation results.