A machine learning based PM2.5 forecasting framework using internet of environmental things

Sachit Mahajan; Hao Min Liu; Ling Jyh Chen; Tzu Chieh Tsai

doi:10.1007/978-3-030-00410-1_20

A machine learning based PM2.5 forecasting framework using internet of environmental things

Sachit Mahajan^*
, Hao Min Liu
, Ling Jyh Chen
, Tzu Chieh Tsai

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Information and communication technologies have been widely used to achieve the objective of smart city development. A smart air quality sensing and forecasting system is an important part of a smart city. In this paper, we present an approach to accurately forecast hourly fine particulate matter (PM2.5). An Internet of Things (IoT) framework comprising of Airbox Devices for PM2.5 monitoring has been used to acquire the data. Our main focus is to achieve high forecasting accuracy with reduced computation time. We use a hybrid model to do the forecast and a grid based system to cluster the monitoring stations based on the geographical distance. The experimentation and evaluation is done using Airbox Devices data from 119 stations in Taichung area of Taiwan. We are able to demonstrate that a proper clustering based on geographical distance can reduce the forecasting error rate and also the computation time.

Original language	English
Title of host publication	IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings
Editors	Yi-Bing Lin, Ilsun You, Der-Jiunn Deng, Chun-Cheng Lin
Publisher	Springer Verlag
Pages	170-176
Number of pages	7
ISBN (Print)	9783030004095
DOIs	https://doi.org/10.1007/978-3-030-00410-1_20
Publication status	Published - 2018
Externally published	Yes
Event	3rd International Conference on IoT as a Service, IoTaaS 2017 - Taichun, Taiwan Duration: 2017 Sept 20 → 2017 Sept 22

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	246
ISSN (Print)	1867-8211

Other

Other	3rd International Conference on IoT as a Service, IoTaaS 2017
Country/Territory	Taiwan
City	Taichun
Period	2017/09/20 → 2017/09/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Air quality
Internet of Things (IoT)
Smart cities

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1007/978-3-030-00410-1_20

Cite this

Mahajan, S., Liu, H. M., Chen, L. J., & Tsai, T. C. (2018). A machine learning based PM2.5 forecasting framework using internet of environmental things. In Y.-B. Lin, I. You, D.-J. Deng, & C.-C. Lin (Eds.), IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings (pp. 170-176). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 246). Springer Verlag. https://doi.org/10.1007/978-3-030-00410-1_20

A machine learning based PM2.5 forecasting framework using internet of environmental things. / Mahajan, Sachit; Liu, Hao Min; Chen, Ling Jyh et al.
IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings. ed. / Yi-Bing Lin; Ilsun You; Der-Jiunn Deng; Chun-Cheng Lin. Springer Verlag, 2018. p. 170-176 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 246).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mahajan, S, Liu, HM, Chen, LJ & Tsai, TC 2018, A machine learning based PM2.5 forecasting framework using internet of environmental things. in Y-B Lin, I You, D-J Deng & C-C Lin (eds), IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 246, Springer Verlag, pp. 170-176, 3rd International Conference on IoT as a Service, IoTaaS 2017, Taichun, Taiwan, 2017/09/20. https://doi.org/10.1007/978-3-030-00410-1_20

Mahajan S, Liu HM, Chen LJ, Tsai TC. A machine learning based PM2.5 forecasting framework using internet of environmental things. In Lin YB, You I, Deng DJ, Lin CC, editors, IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings. Springer Verlag. 2018. p. 170-176. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-00410-1_20

Mahajan, Sachit ; Liu, Hao Min ; Chen, Ling Jyh et al. / A machine learning based PM2.5 forecasting framework using internet of environmental things. IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings. editor / Yi-Bing Lin ; Ilsun You ; Der-Jiunn Deng ; Chun-Cheng Lin. Springer Verlag, 2018. pp. 170-176 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{c2fce730a6ea41febe6485f8f249fde7,

title = "A machine learning based PM2.5 forecasting framework using internet of environmental things",

abstract = "Information and communication technologies have been widely used to achieve the objective of smart city development. A smart air quality sensing and forecasting system is an important part of a smart city. In this paper, we present an approach to accurately forecast hourly fine particulate matter (PM2.5). An Internet of Things (IoT) framework comprising of Airbox Devices for PM2.5 monitoring has been used to acquire the data. Our main focus is to achieve high forecasting accuracy with reduced computation time. We use a hybrid model to do the forecast and a grid based system to cluster the monitoring stations based on the geographical distance. The experimentation and evaluation is done using Airbox Devices data from 119 stations in Taichung area of Taiwan. We are able to demonstrate that a proper clustering based on geographical distance can reduce the forecasting error rate and also the computation time.",

keywords = "Air quality, Internet of Things (IoT), Smart cities",

author = "Sachit Mahajan and Liu, \{Hao Min\} and Chen, \{Ling Jyh\} and Tsai, \{Tzu Chieh\}",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.; 3rd International Conference on IoT as a Service, IoTaaS 2017 ; Conference date: 20-09-2017 Through 22-09-2017",

year = "2018",

doi = "10.1007/978-3-030-00410-1\_20",

language = "English",

isbn = "9783030004095",

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

publisher = "Springer Verlag",

pages = "170--176",

editor = "Yi-Bing Lin and Ilsun You and Der-Jiunn Deng and Chun-Cheng Lin",

booktitle = "IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings",

}

TY - GEN

T1 - A machine learning based PM2.5 forecasting framework using internet of environmental things

AU - Mahajan, Sachit

AU - Liu, Hao Min

AU - Chen, Ling Jyh

AU - Tsai, Tzu Chieh

N1 - Publisher Copyright: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.

PY - 2018

Y1 - 2018

N2 - Information and communication technologies have been widely used to achieve the objective of smart city development. A smart air quality sensing and forecasting system is an important part of a smart city. In this paper, we present an approach to accurately forecast hourly fine particulate matter (PM2.5). An Internet of Things (IoT) framework comprising of Airbox Devices for PM2.5 monitoring has been used to acquire the data. Our main focus is to achieve high forecasting accuracy with reduced computation time. We use a hybrid model to do the forecast and a grid based system to cluster the monitoring stations based on the geographical distance. The experimentation and evaluation is done using Airbox Devices data from 119 stations in Taichung area of Taiwan. We are able to demonstrate that a proper clustering based on geographical distance can reduce the forecasting error rate and also the computation time.

AB - Information and communication technologies have been widely used to achieve the objective of smart city development. A smart air quality sensing and forecasting system is an important part of a smart city. In this paper, we present an approach to accurately forecast hourly fine particulate matter (PM2.5). An Internet of Things (IoT) framework comprising of Airbox Devices for PM2.5 monitoring has been used to acquire the data. Our main focus is to achieve high forecasting accuracy with reduced computation time. We use a hybrid model to do the forecast and a grid based system to cluster the monitoring stations based on the geographical distance. The experimentation and evaluation is done using Airbox Devices data from 119 stations in Taichung area of Taiwan. We are able to demonstrate that a proper clustering based on geographical distance can reduce the forecasting error rate and also the computation time.

KW - Air quality

KW - Internet of Things (IoT)

KW - Smart cities

UR - https://www.scopus.com/pages/publications/85055844406

UR - https://www.scopus.com/pages/publications/85055844406#tab=citedBy

U2 - 10.1007/978-3-030-00410-1_20

DO - 10.1007/978-3-030-00410-1_20

M3 - Conference contribution

AN - SCOPUS:85055844406

SN - 9783030004095

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 170

EP - 176

BT - IoT as a Service - Third International Conference, IoTaaS 2017, Proceedings

A2 - Lin, Yi-Bing

A2 - You, Ilsun

A2 - Deng, Der-Jiunn

A2 - Lin, Chun-Cheng

PB - Springer Verlag

T2 - 3rd International Conference on IoT as a Service, IoTaaS 2017

Y2 - 20 September 2017 through 22 September 2017

ER -

A machine learning based PM2.5 forecasting framework using internet of environmental things

Abstract

Publication series

Other

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this