Urban sound mapping at the edge

In this paper, we report on Citygram [1]-[5] and IBM's partnership in sound-mapping with a focus on capturing urban noise pollution via "edge compute" paradigms. Our noise sensor network is built on plug-And-sense principles that maximize citizen-scientist participation. We report on both standalone hardware and pure software prototype technologies. The pure software solutions operate entirely on standard web-browsers and is fully compatible with popular operating systems including OS X, Windows, Android, and various Linux operating systems (OS). Due to Citygram's pure JavaScript codebase, not only is it OS versatile, it is also hardware versatile as it runs on standard web-browsers, headless browsers, and node.js. In turn, Citygram software runs on a vast array of commonly used devices including smartphones, phablets, tablets, single board computers, notebooks, and desktop computers. On the other hand, standalone hardware solutions have been designed to run continuously as dedicated remote sensing stations (RSS) and are currently being developed on inexpensive, configurable single-board Raspberry Pis (RPi) that are applicable to various environmental sensing situations. RPi forms the most fundamental computational base for IBM Blue Horizon edge compute services. Together, Citygram and Horizon sensor network enables efficient workload expansion, autonomous operation, remote updates, and edge-based analytics. Both hardware and software node solutions capture, process, and analyze data at the "edge" and have been developed to address issues associated with traditional sensor network designs: (1) ease of deployment, (2) network density and scaling, (3) reliability, (4) cost, and (5) dynamicity.