Sammanfattning

This demo presents MegaSense, an air pollution monitoring system for realizing low-cost, near real-time and high resolution spatio-temporal air pollution maps of urban areas. MegaSense involves a novel hierarchy of multi-vendor distributed air quality sensors, in which accurate sensors calibrate lower cost sensors. Current low-cost air quality sensors suffer from measurement drift and they have low accuracy. We address this significant open problem for dense urban areas by developing a calibration scheme that detects and automatically corrects drift. MegaSense integrates with the 5G cellular network and leverages mobile edge computing for sensor management and distributed pollution map creation. We demonstrate MegaSense with two sensor types, a state of the art air quality monitoring station and a low-cost sensor array, with calibration between the two to improve the accuracy of the low-cost device. Participants can interact with the sensors and see air quality changes in real-time, and observe the mechanism to mitigate sensor drift. Our re-calibration method minimizes the error for NO2 and O3 81% of the time (vs single calibration) and reduces the mean relative error by 25%-45%.
Originalspråkengelska
Titel på gästpublikationMobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking
Antal sidor3
UtgivningsortNew York, NY
FörlagACM
Utgivningsdatum2018
Sidor843-845
ISBN (tryckt)978-1-4503-5903-0
DOI
StatusPublicerad - 2018
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangAnnual International Conference on Mobile Computing and Networking - New Delhi, Indien
Varaktighet: 29 okt 20182 nov 2018
Konferensnummer: 24
https://sigmobile.org/mobicom/2018/

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här

Lagerspetz, E., Varjonen, S. K. L., Concas, F., Mineraud, J. V., & Tarkoma, S. A. O. (2018). Demo: MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge. I MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (s. 843-845). New York, NY: ACM. https://doi.org/10.1145/3241539.3267724
Lagerspetz, Eemil ; Varjonen, Samu Karel Luca ; Concas, Francesco ; Mineraud, Julien Vincent ; Tarkoma, Sasu Arimo Olavi. / Demo : MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge. MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. New York, NY : ACM, 2018. s. 843-845
@inproceedings{641fd559ab3f4c07b4711e0ceb011b4d,
title = "Demo: MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge",
abstract = "This demo presents MegaSense, an air pollution monitoring system for realizing low-cost, near real-time and high resolution spatio-temporal air pollution maps of urban areas. MegaSense involves a novel hierarchy of multi-vendor distributed air quality sensors, in which accurate sensors calibrate lower cost sensors. Current low-cost air quality sensors suffer from measurement drift and they have low accuracy. We address this significant open problem for dense urban areas by developing a calibration scheme that detects and automatically corrects drift. MegaSense integrates with the 5G cellular network and leverages mobile edge computing for sensor management and distributed pollution map creation. We demonstrate MegaSense with two sensor types, a state of the art air quality monitoring station and a low-cost sensor array, with calibration between the two to improve the accuracy of the low-cost device. Participants can interact with the sensors and see air quality changes in real-time, and observe the mechanism to mitigate sensor drift. Our re-calibration method minimizes the error for NO2 and O3 81{\%} of the time (vs single calibration) and reduces the mean relative error by 25{\%}-45{\%}.",
keywords = "113 Computer and information sciences, Air quality, Edge, Cloud computing, Calibration, articifial intelligence",
author = "Eemil Lagerspetz and Varjonen, {Samu Karel Luca} and Francesco Concas and Mineraud, {Julien Vincent} and Tarkoma, {Sasu Arimo Olavi}",
year = "2018",
doi = "10.1145/3241539.3267724",
language = "English",
isbn = "978-1-4503-5903-0",
pages = "843--845",
booktitle = "MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking",
publisher = "ACM",
address = "International",

}

Lagerspetz, E, Varjonen, SKL, Concas, F, Mineraud, JV & Tarkoma, SAO 2018, Demo: MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge. i MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. ACM, New York, NY, s. 843-845, Annual International Conference on Mobile Computing and Networking, New Delhi, Indien, 29/10/2018. https://doi.org/10.1145/3241539.3267724

Demo : MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge. / Lagerspetz, Eemil; Varjonen, Samu Karel Luca; Concas, Francesco; Mineraud, Julien Vincent; Tarkoma, Sasu Arimo Olavi.

MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. New York, NY : ACM, 2018. s. 843-845.

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

TY - GEN

T1 - Demo

T2 - MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge

AU - Lagerspetz, Eemil

AU - Varjonen, Samu Karel Luca

AU - Concas, Francesco

AU - Mineraud, Julien Vincent

AU - Tarkoma, Sasu Arimo Olavi

PY - 2018

Y1 - 2018

N2 - This demo presents MegaSense, an air pollution monitoring system for realizing low-cost, near real-time and high resolution spatio-temporal air pollution maps of urban areas. MegaSense involves a novel hierarchy of multi-vendor distributed air quality sensors, in which accurate sensors calibrate lower cost sensors. Current low-cost air quality sensors suffer from measurement drift and they have low accuracy. We address this significant open problem for dense urban areas by developing a calibration scheme that detects and automatically corrects drift. MegaSense integrates with the 5G cellular network and leverages mobile edge computing for sensor management and distributed pollution map creation. We demonstrate MegaSense with two sensor types, a state of the art air quality monitoring station and a low-cost sensor array, with calibration between the two to improve the accuracy of the low-cost device. Participants can interact with the sensors and see air quality changes in real-time, and observe the mechanism to mitigate sensor drift. Our re-calibration method minimizes the error for NO2 and O3 81% of the time (vs single calibration) and reduces the mean relative error by 25%-45%.

AB - This demo presents MegaSense, an air pollution monitoring system for realizing low-cost, near real-time and high resolution spatio-temporal air pollution maps of urban areas. MegaSense involves a novel hierarchy of multi-vendor distributed air quality sensors, in which accurate sensors calibrate lower cost sensors. Current low-cost air quality sensors suffer from measurement drift and they have low accuracy. We address this significant open problem for dense urban areas by developing a calibration scheme that detects and automatically corrects drift. MegaSense integrates with the 5G cellular network and leverages mobile edge computing for sensor management and distributed pollution map creation. We demonstrate MegaSense with two sensor types, a state of the art air quality monitoring station and a low-cost sensor array, with calibration between the two to improve the accuracy of the low-cost device. Participants can interact with the sensors and see air quality changes in real-time, and observe the mechanism to mitigate sensor drift. Our re-calibration method minimizes the error for NO2 and O3 81% of the time (vs single calibration) and reduces the mean relative error by 25%-45%.

KW - 113 Computer and information sciences

KW - Air quality

KW - Edge

KW - Cloud computing

KW - Calibration

KW - articifial intelligence

U2 - 10.1145/3241539.3267724

DO - 10.1145/3241539.3267724

M3 - Conference contribution

SN - 978-1-4503-5903-0

SP - 843

EP - 845

BT - MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking

PB - ACM

CY - New York, NY

ER -

Lagerspetz E, Varjonen SKL, Concas F, Mineraud JV, Tarkoma SAO. Demo: MegaSense: Megacity-scale Accurate Air Quality Sensing with the Edge. I MobiCom '18 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. New York, NY: ACM. 2018. s. 843-845 https://doi.org/10.1145/3241539.3267724