Cheap spaceflight has ushered in an explosive growth era for Low Earth Orbit (LEO) satellites. While this has brought us LEO satellite megaconstellations for ubiquitious highspeed data, it has also enabled a proliferation of nanosatellites (e.g. CubeSats) launched by diverse organizations. An unfortunate side-effect is harmful interference to sensitive receivers like those of radio astronomy --- no place on Earth is safe. How can we enjoy the fruits of the satellite revolution without blinding ourselves to the secrets of the universe?

Automated spectrum analytics inform critical decisions in dynamic spectrum access networks such as (i) how to allocate network resources to clients, (ii) when to enforce penalties due to malicious or disruptive activity, and (iii) how to chart policies for future regulations. The insights gleaned from a spectrum trace, however, are as objective as the trace itself, and artifacts introduced by sensor imperfections or improper configuration will inevitably affect analysis outcomes. Yet, spectrum analytics have been largely developed in isolation from the underlying data collection and are oblivious to sensor-induced artifacts.To address this challenge, we develop VIA, a framework that attributes sensor properties and configuration to spectrum data fidelity, and models the relationship between spectrum analytics performance and data quality. VIA does not require expert input or intervention and can be used to profile the fidelity of unknown sensors. VIA takes as an input a spectrum trace and the sensor configuration, and benchmarks data quality along three dimensions: (i) Veracity, or how truthfully a scan captures spectrum activity, (ii) Intermittency, characterizing the temporal persistence of spectrum scans and (iii) Ambiguity quantifying the likelihood of false detection. We employ VIA to measure the data fidelity of five common sensor platforms. We then predict the outcome of several spectrum analysis tasks including occupancy and transmitter detection, and modulation recognition using both controlled and real-world measurements. We demonstrate high prediction performance with an average mean squared error of 0.0013 across all tasks using both regression and neural network models.

Mobile wireless networks revolutionize our lives and livelihoods. Yet, rural areas, characterized with sparse populations and rugged terrain, consistently lag behind in mobile connectivity compared to their urban counterparts. As a result, community-owned networks realized through fixed wireless tech-nologies, have become an increasingly viable Internet option for otherwise disconnected areas. Fixed wireless, however, is inherently designed for residential/stationary access and is not readily applicable for the use of mobile agents that might travel through a rural community. In this paper we explore the extension of fixed wireless networks for mobile access. A key factor for continuous mobile access is efficient rate adaptation. To that end, we develop WideRate- a reinforcement learning framework that employs signal strength measurements for optimal rate adaptation. We showcase WideRate in the context of wide-area Television White Space networks, whereby we design a vehicular mobile unit and carry out an extensive measurement campaign in a real community network. We use the collected traces to motivate the need for rate adaptation and implement a realistic network simulator that aids in our evaluation. We demonstrate that WideRate significantly outperforms counterparts from the literature including a reinforcement learning model.

Despite the substantial success of deep learning for Automatic Modulation Classification (AMC), models trained on a specific transmitter configuration and channel model often fail to generalize well to other scenarios with different transmitter configurations, wireless fading channels, or receiver impairments such as clock offset. This paper proposes Contrastive Learning with Self-Reconstruction called CLSR-AMC to learn good representations of signals resilient to channel changes. While contrastive loss focuses on the differences between individual modulations, the reconstruction loss captures representative features of the signal. Additionally, we develop three data augmentation operators to emulate the impact of channel and hardware impairments without exhaustive modeling of different channel profiles. We perform extensive experimentation with commonly used realistic datasets. We show that CLSR-AMC outperforms its counterpart based on contrastive learning for the same amount of labeled data by significant average accuracy gains of 24.29%, 17.01%, and 15.97% in the Additive White Gaussian Noise (AWGN), Rayleigh, and Rician channels, respectively.

Modulation recognition (modrec) seeks to identify the modulation of a transmitter from coresponding spectrum scans. It is an essential functional component of future spectrum sensing with critical applications in dynamic spectrum access and spectrum enforcement. While predominantly studied in single-input single-output (SISO) systems, practical modrec for multiple-input multiple-output (MIMO) communications requires more research attention. Existing MIMO modrec impose stringent requirements of fully- or over-determined sensing front-end, i.e. the number of sensor antennas should exceed that at the transmitter. This poses a prohibitive sensor cost even for simple 2x2 MIMO systems and will severely hamper progress in flexible spectrum access. We design a MIMO modrec framework that enables efficient and cost-effective modulation classification for under-determined settings involving fewer sensor antennas than those used for transmission. Our key idea is to exploit the inherent multi-scale self-similarity of MIMO modulation IQ constellations, which persists in under-determined settings. Our framework, called SYMMeTRy (Self-similaritY for MIMO ModulaTion Recognition), designs domain-aware classification features with high discriminative potential by summarizing regularities of symbol co-location in the MIMO constellation. To this end, we summarize the fractal geometry of observed samples to extract discriminative features for supervised MIMO modrec. We evaluate SYMMeTRy in a realistic simulation and in a small-scale MIMO testbed. We demonstrate that it maintains high and consistent performance across various noise regimes, channel fading conditions and with increasing MIMO transmitter complexity. Our efforts highlight SYMMeTRy's high potential to enable efficient and practical MIMO modrec in spectrum sensing infrastructures with mixed-complexity sensors.

The unique socio-economic structure of rural communities makes them particularly vulnerable to emergencies. However, rural emergency preparedness and response (EPR) significantly lag behind their urban counterparts. A key obstacle to timely dissemination of emergency information is limited broadband, which in turn limits agencies’ abilities to (i) disseminate preparedness and response information to residents and (ii) coordinate in the face of a disaster.

Automatic Modulation Classification (AMC) is significant for the practical support of a plethora of emerging spectrum applications, such as Dynamic Spectrum Access (DSA) in 5G and beyond, resource allocation, jammer identification, intruder detection, and in general, automated interference analysis. Although a well-known problem, most of the existing AMC work has been done under the assumption that the classifier has prior knowledge about the signal and channel parameters. This paper shows that unknown signal and channel parameters significantly degrade the performance of two of the most popular research streams in modulation classification: expert feature-based and data-driven. By understanding why and where those methods fail, in such unknown scenarios, we propose two possible directions to make AMC more robust to signal shape transformations introduced by unknown signal and channel parameters. We show that Spatial Transformer Networks (STN) and Transfer Learning (TL) embedded into a light ResNeXt-based classifier can improve average classification accuracy up to 10-30% for specific unseen scenarios with only 5% labeled data for a large dataset of 20 complex higher-order modulations.

Modulation recognition (modrec) is an essential transmitter fingerprinting task that enables future spectrum-sharing applications such as access management and enforcement. Traditional supervised modrec requires labeled training data for all target modulations, which cannot be readily met with the advent of new, customized and data-driven waveforms. Thus, a keystone question for the applicability of modrec is: Can we perform automatic recognition of previously unobserved modulations by adapting and reusing models that were trained on different but related modulations?To this end, we develop MODELESS (MODulation rEcognition with LimitEd SuperviSion) that exploits knowledge from observed modulations to classify samples from unobserved ones. Our solution is grounded in zero-shot transfer learning, which employs side information among observed and unobserved classes to transfer learned classifiers. In particular we quantify the similarity among the theoretical constellation diagrams of unobserved and observed modulations and employ them in a zero-shot transfer learning framework. Our framework is general, as it can produce predictions for arbitrary modulations as long as their theoretical constellations can be specified. We evaluate MODELESS on synthetic and real-world traces and in comparison with zero-shot counterparts from the literature. We demonstrate near-ideal classification accuracy in the majority of the testing cases and draw recommendations for future research into classification tasks with sub-par performance.

While mobile devices are ubiquitous, their supporting communication infrastructure is cost-effective only in densely populated urban areas and is often lacking in rural settings. This lack of connectivity leads to lost opportunities in applications such as rural emergency preparedness and response. Peer-to-peer exchange that uses predictable human mobility can enable delay-tolerant information access in rural settings. We propose, an adaptive distributed solution for device-to-device Connectivity Optimization via REinforcement Learning (CORE) in wireless adhoc networks. Our solution is designed for collaborative distributed agents with intermittent connectivity and limited battery power, but predictable mobility within short temporal horizons. We seek to maximize the utility of connection attempts while keeping the power expenditure within a predefined battery budget. Agents learn to adaptively make automated decisions for when to attempt connections and exchange information, based on a local RL model of their mobility and that of other agents they learn about from exchanges. Using both synthetic and real-world mobility traces, we demonstrate that agents are able to materialize 95% of the possible connections using 20% of their battery and successfully adapting to changes in the underlying mobility patterns within several days of learning.

Modulation recognition (modrec) is an essential functional component of future wireless networks with critical applications in dynamic spectrum access. While predominantly studied in single-input single-output (SISO) systems, practical modrec for multiple-input multiple-output (MIMO) communications requires more research attention. Existing MIMO modrec impose stringent requirements of fully- or over-determined sensing front-end, i.e. the number of sensor antennas should exceed that at the transmitter. This poses a prohibitive sensor cost even for simple 2x2 MIMO systems and will severely hamper progress in flexible spectrum access with advanced higher-order MIMO.We design a MIMO modrec framework that enables efficient and cost-effective modulation classification for under-determined settings characterized by fewer sensor antennas than those used for transmission. Our key idea is to exploit the inherent multi-scale self-similarity of MIMO modulation IQ constellations, which persists in under-determined settings. Our framework called SYMMeTRy (Self-similarit Y for MIMO ModulaTion Recognition) designs domain-aware classification features with high discriminative potential by summarizing regularities of symbol co-location in the MIMO constellation. To this end, we summarize the fractal geometry of observed samples to extract discriminative features for supervised MIMO modrec. We evaluate SYMMeTRy in a realistic simulation and in a small-scale MIMO testbed. We demonstrate that it maintains high and consistent performance across various noise regimes, channel fading conditions and with increasing MIMO transmitter complexity. Our efforts highlight SYMMeTRy's high potential to enable efficient and practical MIMO modrec.

With the advent of Dynamic Spectrum Access networks, practical modulation recognition (ModRec) has become an important problem with critical applications to spectrum enforcement and resource allocation. Existing ModRec frameworks hinge on exhaustive classifier training and require labeled observations for all modulations before recognition can be performed. As a result, a general ModRec system based on fully supervised classification quickly becomes intractable due to the emergence of new proprietary waveforms and the need to collect labeled training data for them and retrain the system. This underpins the need to perform modulation classification of previously unobserved modulations. Thus, the question emerges can learned classifiers be transferred to "unobserved" modulations? In this paper, we investigate the utility of zero-shot learning to address the above challenge in the context of ModRec. We design ModRec-0, which employs unseen modulations' constellation diagrams within a zero-shot framework to transfer learned classifiers from observed modulations. We propose several important properties to enable this transfer, such as the number of constellation points, phase and amplitude levels. Our system is flexible in that additional such properties as well as a variety of classification features can be incorporated. We evaluate our framework on synthetic and real over-the-air traces and investigate the necessary conditions such as SNR levels and observed training classes for successful transfer. We demonstrate that ModRec-0 achieves over 85% average accuracy across multiple modulation classes both in synthetic and real-world traces.

Access to mobile wireless networks has become critical for day-to-day life. However, it also inherently requires that a user's geographic location is continuously tracked by the service provider. It is challenging to maintain location privacy, especially from the provider itself. To do so, a user can switch through a series of identifiers, and even go offline between each one, though it sacrifices utility. This strategy can make it difficult for an adversary to perform location profiling and trajectory linking attacks that match observed behavior to a known user.

Modulation recognition plays a key role in emerging spectrum applications including spectrum enforcement, resource allocation, privacy and security. While critical for the practical progress of spectrum sharing, modulation recognition has so far been investigated under unrealistic assumptions: (i)a transmitter's bandwidth must be scanned alone and in full, (ii) prior knowledge of the technology must be available and (iii) a transmitter must be trustworthy. In reality these assumptions cannot be readily met, as a transmitter's bandwidth may only be scanned intermittently, partially, or alongside other transmitters, and modulation obfuscation may be introduced by short-lived scans or malicious activity.This paper bridges the gap between real-world spectrum sensing and the growing body of methods for modulation recognition designed under simplifying assumptions. We propose to use local features, besides global statistics, extracted from raw IQ data, which collectively enable a robust framework for modulation recognition that outperforms baselines from the state-of-the-art. Specifically, we exploit the discriminative power of local patterns from consecutive IQ samples extracted based on a Fisher Kernel framework that captures non-linearity in the underlying data. With these domain-informed features, we employ lightweight linear support vector machine classification for modulation detection. Our framework is robust to noise, partial transmitter scans and data biases without utilizing prior knowledge of the underlying transmitter technology. The recognition accuracy of our approach consistently outperforms baselines in both simulated and real-world traces. We demonstrate up to a 98% accuracy and a 30% improvement over several counterparts from the literature with partial scans in a USRP testbed.

Large-scale emergencies, both natural and man-made, are increasingly incurring devastating losses in terms of infrastructure and human lives. Rural areas are particularly vulnerable to such losses. Emergency preparedness and response services, in rural areas, severely lag behind that of their urban counterparts. One of the key limiting factors is the lack of adequate broadband connectivity, which limits agencies' capabilities to (i) disseminate emergency preparedness and response information to residents and (ii) efficiently coordinate in the face of a disaster. In this demo, we present the EApp; a smartphone application that strives to improve the information access regarding emergencies for rural residents and first responders.

While cellular networks connect over 3.7 billion people worldwide, their availability and quality is not uniform across regions. Under-provisioned and overloaded networks, as are common in rural or post-disaster areas, lead to poor network performance and a poor-quality user experience. To address this problem, we propose HybridCell: a system that leverages locally-owned small-scale cellular networks to augment the operation of overloaded commercial networks. HybridCell is the first system to allow a user with their existing SIM card and mobile phone to seamlessly switch between commercial and local networks in order to maintain continuous connectivity. HybridCell accomplishes this by identifying poorly-performing networks and taking action to provide seamless cellular connectivity to end users. Using traces from commercial cellular networks collected during our visit to the Za'atari refugee camp in Jordan, we demonstrate HybridCell's capability to detect and act upon commercial network overload, offering an alternate communication channel during times of congestion. We show that even in scenarios where provider networks deny calls due to overload, HybridCell is able to accommodate users and facilitate local calling.

The current paradigm of exclusive spectrum assignment and allocation is creating artificial spectrum scarcity that has a dramatic impact on network performance and user experience. Thus, governments, industry and academia have endeavored to create novel spectrum management mechanisms that allow multi-tiered access. A key component of such an approach is deep understanding of spectrum utilization in time, frequency and space. To address this challenge, we propose AirVIEW, a one-pass, unsupervised spectrum characterization approach for rapid transmitter detection with high tolerance to noise. AirVIEW autonomously learns its parameters and employs wavelet decomposition in order to amplify and reliably detect transmissions at a given time instant. We show that AirVIEW can robustly identify transmitters even when their power is only 5dBm above the noise floor. Furthermore, we demonstrate AirVIEW's ability to inform next-generation Dynamic Spectrum Access by characterizing essential transmitter properties in wideband spectrum measurements from 50MHz to 4.4GHz.

Knowledge about active radio transmitters is critical for multiple applications: spectrum regulators can use this information to assign spectrum, licensees can identify spectrum usage patterns and provision their future needs, and dynamic spectrum access applications can efficiently pick operating frequency. To achieve these goals, we need a system that continuously senses and characterizes the radio spectrum. Current measurement systems, however, do not scale over time, frequency and space and cannot perform transmitter detection. We address these challenges with theSpectrum Observatory, an end-to-end system for spectrum measurement and characterization. This paper details the design and integration of the Spectrum Observatory, and describes and evaluates the first unsupervised method for detailed characterization of arbitrary transmitters calledTxMiner. We evaluate TxMiner on real-world spectrum measurements collected by the Spectrum Observatory between 30 MHz and 6 GHz and show that it identifies transmitters robustly. Furthermore, we demonstrate the Spectrum Observatory’s capabilities to map the number of active transmitters and their frequency and temporal characteristics, to detect rogue transmitters, and identify opportunities for dynamic spectrum access.

Camera snapshot images are widely used in IoT applications. However, when the applications are deployed in rural areas or poorly-performing networks, the images offloading usually exhausts the limited network resources. While we can certainly revamp the network links, we can also optimize the payload at the same time. In this paper, we propose a middlebox system design that exploits the patterns of similarity between consecutive camera snapshots to alleviate the network load. Our preliminary results show that despite of small errors introduced in the images, the amount of reduced payloads could be a valuable choice to alleviate poorly performing networks.

Ubiquitous cellular coverage is often taken for granted, yet numerous people live outside, or at the fringes, of commercial cellular coverage. Further, natural disasters and human rights violations cause the displacement of millions of people annually worldwide, with many of these people relocating to shelters and camps in areas at or just beyond the margins of existing cellular infrastructure. In this work we design PhoneHome, a system prototype that extends existing cellular coverage to areas with no or damaged cellular infrastructure, or infrastructure that is otherwise poorly performing. We explore the feasibility of PhoneHome and address current limitations and future directions for independently operated, user-extensible cellular infrastructure.

While cellular networks connect over 3.7 billion people worldwide, their availability and quality is not uniform across regions. Under-provisioned and overloaded networks lead to poor network performance and an aggravated user experience. To address this problem we propose HybridCell: a system that leverages locally-owned small-scale cellular networks to augment the operation of overloaded commercial networks. HybridCell is the first system to allow a user with their existing SIM card and mobile phone to seamlessly switch between commercial and local networks in order to maintain continuous connectivity. Hybrid-Cell accomplishes this by identifying poorly-performing networks and taking action to provide seamless cellular connectivity to end users. Using traces collected from observing the cellular infrastructure during our visit to the Za'atari refugee camp in Jordan, we demonstrate HybridCell's capability to detect and act upon commercial network overload, offering an alternate communication channel during times of congestion. We show that even in scenarios where provider networks deny calls due to overload, HybridCell is able to accommodate users and facilitate local calling.

Cellular networks are often the first telecommunications infrastructure in developing regions. By studying cellular net- work traffic, researchers gain insight into how technologies can be used to access services critical to further development. In this work, we approach a cellular traffic dataset provided by Orange in Cote d'Ivoire with the goal of identifying distinctions between urban and rural use of cellular infrastructure. We report on a number of interesting differences between urban and rural usage of cellular infrastructure. For instance, 70% of calls that originate in rural areas occur within the vicinity of the same antenna, whereas the same is true for only 23% of calls with urban origin. We are compelled to conclude that development efforts for rural areas might be implemented differently from development efforts in urban areas based on divergent use of current cellular infrastructure.

Studies of user behavior in cellular networks have served as a knowledge base for development of critical applications and services catered to specific user needs. In this paper we examine community persistence in egocentric social graphs extracted from cellular network traces in the Cote d'Ivoire provided by Orange. The goal of our study is to inform mechanisms for improved dissemination of information by identifying subscribers or groups that can serve as information relays. We find that communities that persist in an egocentric network are independent of one another. Thus, multiple information relays can be selected from each independent community, to increase the probability that information will flow to the ego.

Cellular networks have revolutionized the way people communicate in rural areas. At the same time, deployment of commercial-grade cellular networks in areas with low population density, such as in rural sub-Saharan Africa, is prohibitively expensive relative to the return of investment. As a result, 48% of the rural population in Africa remains disconnected. To address this problem, we design a local cellular network architecture, Kwiizya, that provides basic voice and text messaging services in rural areas. We deployed an instance of Kwiizya in the rural village of Macha in Zambia. In this video we present interviews with people from the Macha community talking about their use of cellphones. We also present footage from the installation of Kwiizya in Macha.

Cellular networks have revolutionized the way people communicate in rural areas. At the same time, deployment of commercial-grade cellular networks in areas with low population density, such as in rural sub-Saharan Africa, is prohibitively expensive relative to the return of investment. As a result, 48\% of the rural population in Africa remains disconnected. To address this problem, we design a local cellular network architecture, Kwiizya, that provides basic voice and text messaging services in rural areas. Our system features an interface for development of text message based applications that can be leveraged for improved health care, education and support of local businesses. We deployed an instance of Kwiizya in the rural village of Macha in Zambia. Our deployment utilizes the existing long distance Wi-Fi network in the village for inter-base station communication to provide high quality services with minimal infrastructure requirements. In this paper we evaluate Kwiizya in-situ in Macha and show that the network maintains low delay and jitter (20ms and 3ms, respectively) for voice call traffic, while providing high call Mean Opinion Score of 3.46, which is the theoretical maximum supported by our system.