When Sharing Economy Meets IoT

Abstract

Air pollution is a serious global issue impacting public health and social economy. In particular, exposure to small particulate matter of 2.5 microns or less in diameter (PM2.5) can cause cardiovascular and respiratory diseases, and cancer. Fine-grained urban air quality monitoring is crucial yet difficult to achieve. In this paper, we present the design, implementation, and evaluation of an ambient environment aware system, namely UbiAir, which can support fine-grained urban air quality monitoring through mobile crowdsensing on a bike-sharing system. We have built specific IoT box configured with multiple pollutant sensors and attached on shared bikes to sample micro-scale air quality data in the monitoring space that is split by a scalable grid structure. Both hardware and software data calibration methods are exploited in UbiAir to make the sampled data reliable. Then, we use Bayesian compressive sensing (BCS) as an inference model that leverages the calibrated samples to recover data points without direct measurements and reconstruct an accurate air quality map covering the entire monitoring space. In addition, red envelope based incentive schemes and differential rewarding strategies have been designed in UbiAir, and an adaptive BCS algorithm is proposed to deploy the red envelopes at the most informative positions to facilitate data sampling and inference. We have tested our system on campus with over 100k data measurements collected by 36 students through 18 days. Our real-world experiments show that UbiAir is a light-weight, low-cost, accurate and scalable system for fine-grained air quality monitoring, as compared with other solutions.