Karyn Doke, Andrew Okoro, Mariya Zheleva


we present VIA, a framework that attributes sensor properties and configuration to spectrum data fidelity, and models the relationship between data fidelity and the performance of spectrum analytics. 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 predict the outcome of several spectrum analytic tasks in controlled and real-world measurements and demonstrate high prediction accuracy using both regression-based and a neural network predictors.