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.

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.

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.

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.

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.