Project QuAiL: Quick (and Dirty) Aggregate Queries on Low-Power WANs

Getting a quick rough understanding from large number of spatially distributed sensors can enable various real world solutions such as forest fire detection, flood sensing and machine learning inference from the data. Our work, QuAiL enables this quick spatial aggregation showing high efficacy in detecting forest fires faster and more accurately. Our solution leverages the property of wireless powers adding up over the air to get weighted linear combination from sensors. We show high fidelity low latency aggregation for various machine learning, statistical and spatial applications with a focused case-study on forest fire detection.


  • Quick (and Dirty) Aggregate Queries on Low-Power WANs, Akshay Gadre, Fan Yi, Anthony Rowe, Bob Iannucci and Swarun Kumar, IPSN 2020 (Best Paper Award) [PAPER]