MegaSense: 5G and AI for Air Quality Monitoring

Sasu Tarkoma; Xiaoli Liu; Andrew Rebeiro-Hargrave; Samu Varjonen

doi:10.1007/978-3-030-51005-3_2

MegaSense: 5G and AI for Air Quality Monitoring

Sasu Tarkoma, Xiaoli Liu, Andrew Rebeiro-Hargrave, Samu Varjonen

Research output: Contribution to journal › Conference article › Scientific › peer-review

Abstract

Air pollution has become a global challenge during the growth of megacities, which drives the deployment of air quality monitoring in order to understand and mitigate district level air pollution. Currently, air pollution monitoring mainly relies on high-end accurate reference stations, which are usually stationary and expensive. Thus, the air quality monitoring deployments are typically coarse grained with only a very small number of stations in a city. We propose scalable air quality monitoring by leveraging low-cost air pollution sensors, artificial intelligence methods, and versatile connectivity provided by 4G/5G. We describe pilot deployments for testing the developed sensing technologies in three different locations in Helsinki, Finland.

Original language	English
Journal	Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Volume	323
Pages (from-to)	13-19
Number of pages	7
ISSN	1867-8211
DOIs	https://doi.org/10.1007/978-3-030-51005-3_2
Publication status	Published - 2020
MoE publication type	A4 Article in conference proceedings
Event	International Conference, SmartCity360° - Virtual event Duration: 2 Dec 2020 → 4 Dec 2020 Conference number: 6

Fields of Science

113 Computer and information sciences

Access to Document

10.1007/978-3-030-51005-3_2

2020_Megasense_ChapterAccepted author manuscript, 3.94 MBLicence: Unspecified

Cite this

@article{03abc2c8fa5d43dcb06666cb1cfde065,

title = "MegaSense: 5G and AI for Air Quality Monitoring",

abstract = "Air pollution has become a global challenge during the growth of megacities, which drives the deployment of air quality monitoring in order to understand and mitigate district level air pollution. Currently, air pollution monitoring mainly relies on high-end accurate reference stations, which are usually stationary and expensive. Thus, the air quality monitoring deployments are typically coarse grained with only a very small number of stations in a city. We propose scalable air quality monitoring by leveraging low-cost air pollution sensors, artificial intelligence methods, and versatile connectivity provided by 4G/5G. We describe pilot deployments for testing the developed sensing technologies in three different locations in Helsinki, Finland.",

keywords = "113 Computer and information sciences",

author = "Sasu Tarkoma and Xiaoli Liu and Andrew Rebeiro-Hargrave and Samu Varjonen",

year = "2020",

doi = "10.1007/978-3-030-51005-3_2",

language = "English",

volume = "323",

pages = "13--19",

journal = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",

issn = "1867-8211",

publisher = "Springer Science and Business Media Deutschland GmbH",

note = "International Conference, SmartCity360° ; Conference date: 02-12-2020 Through 04-12-2020",

}

TY - JOUR

T1 - MegaSense: 5G and AI for Air Quality Monitoring

AU - Tarkoma, Sasu

AU - Liu, Xiaoli

AU - Rebeiro-Hargrave, Andrew

AU - Varjonen, Samu

N1 - Conference code: 6

PY - 2020

Y1 - 2020

N2 - Air pollution has become a global challenge during the growth of megacities, which drives the deployment of air quality monitoring in order to understand and mitigate district level air pollution. Currently, air pollution monitoring mainly relies on high-end accurate reference stations, which are usually stationary and expensive. Thus, the air quality monitoring deployments are typically coarse grained with only a very small number of stations in a city. We propose scalable air quality monitoring by leveraging low-cost air pollution sensors, artificial intelligence methods, and versatile connectivity provided by 4G/5G. We describe pilot deployments for testing the developed sensing technologies in three different locations in Helsinki, Finland.

AB - Air pollution has become a global challenge during the growth of megacities, which drives the deployment of air quality monitoring in order to understand and mitigate district level air pollution. Currently, air pollution monitoring mainly relies on high-end accurate reference stations, which are usually stationary and expensive. Thus, the air quality monitoring deployments are typically coarse grained with only a very small number of stations in a city. We propose scalable air quality monitoring by leveraging low-cost air pollution sensors, artificial intelligence methods, and versatile connectivity provided by 4G/5G. We describe pilot deployments for testing the developed sensing technologies in three different locations in Helsinki, Finland.

KW - 113 Computer and information sciences

U2 - 10.1007/978-3-030-51005-3_2

DO - 10.1007/978-3-030-51005-3_2

M3 - Conference article

SN - 1867-8211

VL - 323

SP - 13

EP - 19

JO - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

JF - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

T2 - International Conference, SmartCity360°

Y2 - 2 December 2020 through 4 December 2020

ER -