Mosaic: Towards City Scale Sensing with Mobile Sensor Networks

We introduce Mosaic, a mobile sensor network system for city scale sensing. Currently, we focus on accurate PM2.5 measurements. We design and implement low-cost smart sensors for this purpose. Those sensors are specifically designed for moving vehicles such as buses and taxies. The mobile sensing capability of our system enables a wide coverage of a city with a modest number of sensors. We incorporate a three-layer architecture in Mosaic. Mosaic faces many practical challenges which need to be properly addressed, e.g., reliable node hardware and software design, and accurate PM2.5 measurements. We have built three versions of Mosaic nodes. We present a novel data calibration approach combining traditional Artificial Neural Network (ANN) and Support Vector Machines (SVMs). We launch real-world deployments of Mosaic in two main cities in China -- Hangzhou and Ningbo. Our initial efforts show that Mosaic is a feasible approach for city scale sensing and our system can produce highly accurate PM2.5 measurements.