%0 Journal Article %1 Maag:2018:WEP:3200905.3191756 %A Maag, Balz %A Zhou, Zimu %A Thiele, Lothar %C New York, NY, USA %D 2018 %I ACM %J Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. %K calibration p2map %N 1 %P 24:1--24:25 %R 10.1145/3191756 %T W-Air: Enabling Personal Air Pollution Monitoring on Wearables %U http://doi.acm.org/10.1145/3191756 %V 2 %X Accurate, portable and personal air pollution sensing devices enable quantification of individual exposure to air pollution, personalized health advice and assistance applications. Wearables are promising (e.g., on wristbands, attached to belts or backpacks) to integrate commercial off-the-shelf gas sensors for personal air pollution sensing. Yet previous research lacks comprehensive investigations on the accuracies of air pollution sensing on wearables. In response, we proposed W-Air, an accurate personal multi-pollutant monitoring platform for wearables. We discovered that human emissions introduce non-linear interference when low-cost gas sensors are integrated into wearables, which is overlooked in existing studies. W-Air adopts a sensor-fusion calibration scheme to recover high-fidelity ambient pollutant concentrations from the human interference. It also leverages a neural network with shared hidden layers to boost calibration parameter training with fewer measurements and utilizes semi-supervised regression for calibration parameter updating with little user intervention. We prototyped W-Air on a wristband with low-cost gas sensors. Evaluations demonstrated that W-Air reports accurate measurements both with and without human interference and is able to automatically learn and adapt to new environments.

@article{Maag:2018:WEP:3200905.3191756, abstract = {Accurate, portable and personal air pollution sensing devices enable quantification of individual exposure to air pollution, personalized health advice and assistance applications. Wearables are promising (e.g., on wristbands, attached to belts or backpacks) to integrate commercial off-the-shelf gas sensors for personal air pollution sensing. Yet previous research lacks comprehensive investigations on the accuracies of air pollution sensing on wearables. In response, we proposed W-Air, an accurate personal multi-pollutant monitoring platform for wearables. We discovered that human emissions introduce non-linear interference when low-cost gas sensors are integrated into wearables, which is overlooked in existing studies. W-Air adopts a sensor-fusion calibration scheme to recover high-fidelity ambient pollutant concentrations from the human interference. It also leverages a neural network with shared hidden layers to boost calibration parameter training with fewer measurements and utilizes semi-supervised regression for calibration parameter updating with little user intervention. We prototyped W-Air on a wristband with low-cost gas sensors. Evaluations demonstrated that W-Air reports accurate measurements both with and without human interference and is able to automatically learn and adapt to new environments.}, acmid = {3191756}, added-at = {2018-10-31T17:03:57.000+0100}, address = {New York, NY, USA}, articleno = {24}, author = {Maag, Balz and Zhou, Zimu and Thiele, Lothar}, biburl = {https://www.bibsonomy.org/bibtex/2d1313a12a9c66cb793111d28f72cd2e9/lautenschlager}, description = {W-Air}, doi = {10.1145/3191756}, interhash = {de923852ae3c39dc2dec50a226d47f6f}, intrahash = {d1313a12a9c66cb793111d28f72cd2e9}, issn = {2474-9567}, issue_date = {March 2018}, journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.}, keywords = {calibration p2map}, month = mar, number = 1, numpages = {25}, pages = {24:1--24:25}, publisher = {ACM}, timestamp = {2018-10-31T17:03:57.000+0100}, title = {W-Air: Enabling Personal Air Pollution Monitoring on Wearables}, url = {http://doi.acm.org/10.1145/3191756}, volume = 2, year = 2018 }