Data-driven modeling techniques for indoor CO2 estimation

Bob Vergauwen; Oscar Mauricio Agudelo; Raj Thilak Rajan; Frank Pasveer; Bart De Moor

doi:10.1109/ICSENS.2017.8234156

Data-driven modeling techniques for indoor CO₂ estimation

Bob Vergauwen, Oscar Mauricio Agudelo, Raj Thilak Rajan, Frank Pasveer, Bart De Moor

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

Abstract

This paper presents the results of using the Least-Squares Support Vector Machines (LS-SVMs) framework for estimating CO₂ levels at the Holst Center building in the Netherlands. Within the IoT framework, a Wireless Sensor Network (WSN) consisting of seven sensors is currently deployed at the third floor of the building. Each sensor node provides measures of temperature, relative humidity and CO₂ levels, and transmits the readings to a consumer accessible cloud. Given that CO₂ has a big impact on people comfort and productivity, its monitoring and control has become a common practice in recent years. In this work we provide a way to estimate the CO₂ concentration when a CO₂ sensor is not trustworthy (e.g., due to maintenance or a malfunction), by using nonlinear models built from historical sensor data. Results showed that the model structures proposed in this work provided better CO₂ estimates than those given by conventional linear autoregressive (AR) and autoregressive exogenous (ARX) models.

Original language	English
Title of host publication	IEEE SENSORS 2017 - Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-3
Number of pages	3
ISBN (Electronic)	9781509010127
DOIs	https://doi.org/10.1109/ICSENS.2017.8234156
Publication status	Published - 2017
Externally published	Yes
Event	16th IEEE SENSORS Conference, ICSENS 2017 - Glasgow, United Kingdom Duration: 30 Oct 2017 → 1 Nov 2017

Publication series

Name	Proceedings of IEEE Sensors
Volume	2017-December
ISSN (Print)	1930-0395
ISSN (Electronic)	2168-9229

Conference

Conference	16th IEEE SENSORS Conference, ICSENS 2017
Country/Territory	United Kingdom
City	Glasgow
Period	30/10/17 → 1/11/17

Keywords

air quality
CO-estimation
LS-SVM
non-linear modeling
wireless sensor network (WSN)
Sensor Network

Access to Document

10.1109/ICSENS.2017.8234156

Cite this

@inproceedings{7796c78235144ddc828a9ab3c95e7997,

title = "Data-driven modeling techniques for indoor CO2 estimation",

abstract = "This paper presents the results of using the Least-Squares Support Vector Machines (LS-SVMs) framework for estimating CO2 levels at the Holst Center building in the Netherlands. Within the IoT framework, a Wireless Sensor Network (WSN) consisting of seven sensors is currently deployed at the third floor of the building. Each sensor node provides measures of temperature, relative humidity and CO2 levels, and transmits the readings to a consumer accessible cloud. Given that CO2 has a big impact on people comfort and productivity, its monitoring and control has become a common practice in recent years. In this work we provide a way to estimate the CO2 concentration when a CO2 sensor is not trustworthy (e.g., due to maintenance or a malfunction), by using nonlinear models built from historical sensor data. Results showed that the model structures proposed in this work provided better CO2 estimates than those given by conventional linear autoregressive (AR) and autoregressive exogenous (ARX) models.",

keywords = "air quality, CO-estimation, LS-SVM, non-linear modeling, wireless sensor network (WSN), Sensor Network",

author = "Bob Vergauwen and Agudelo, {Oscar Mauricio} and Rajan, {Raj Thilak} and Frank Pasveer and {De Moor}, Bart",

year = "2017",

doi = "10.1109/ICSENS.2017.8234156",

language = "English",

series = "Proceedings of IEEE Sensors",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1--3",

booktitle = "IEEE SENSORS 2017 - Conference Proceedings",

address = "United States",

note = "16th IEEE SENSORS Conference, ICSENS 2017 ; Conference date: 30-10-2017 Through 01-11-2017",

}

Vergauwen, B, Agudelo, OM, Rajan, RT, Pasveer, F & De Moor, B 2017, Data-driven modeling techniques for indoor CO₂ estimation. in IEEE SENSORS 2017 - Conference Proceedings. Proceedings of IEEE Sensors, vol. 2017-December, Institute of Electrical and Electronics Engineers (IEEE), pp. 1-3, 16th IEEE SENSORS Conference, ICSENS 2017, Glasgow, United Kingdom, 30/10/17. https://doi.org/10.1109/ICSENS.2017.8234156

Data-driven modeling techniques for indoor CO₂ estimation. / Vergauwen, Bob; Agudelo, Oscar Mauricio; Rajan, Raj Thilak et al.
IEEE SENSORS 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 1-3 (Proceedings of IEEE Sensors; Vol. 2017-December).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Data-driven modeling techniques for indoor CO2 estimation

AU - Vergauwen, Bob

AU - Agudelo, Oscar Mauricio

AU - Rajan, Raj Thilak

AU - Pasveer, Frank

AU - De Moor, Bart

PY - 2017

Y1 - 2017

N2 - This paper presents the results of using the Least-Squares Support Vector Machines (LS-SVMs) framework for estimating CO2 levels at the Holst Center building in the Netherlands. Within the IoT framework, a Wireless Sensor Network (WSN) consisting of seven sensors is currently deployed at the third floor of the building. Each sensor node provides measures of temperature, relative humidity and CO2 levels, and transmits the readings to a consumer accessible cloud. Given that CO2 has a big impact on people comfort and productivity, its monitoring and control has become a common practice in recent years. In this work we provide a way to estimate the CO2 concentration when a CO2 sensor is not trustworthy (e.g., due to maintenance or a malfunction), by using nonlinear models built from historical sensor data. Results showed that the model structures proposed in this work provided better CO2 estimates than those given by conventional linear autoregressive (AR) and autoregressive exogenous (ARX) models.

AB - This paper presents the results of using the Least-Squares Support Vector Machines (LS-SVMs) framework for estimating CO2 levels at the Holst Center building in the Netherlands. Within the IoT framework, a Wireless Sensor Network (WSN) consisting of seven sensors is currently deployed at the third floor of the building. Each sensor node provides measures of temperature, relative humidity and CO2 levels, and transmits the readings to a consumer accessible cloud. Given that CO2 has a big impact on people comfort and productivity, its monitoring and control has become a common practice in recent years. In this work we provide a way to estimate the CO2 concentration when a CO2 sensor is not trustworthy (e.g., due to maintenance or a malfunction), by using nonlinear models built from historical sensor data. Results showed that the model structures proposed in this work provided better CO2 estimates than those given by conventional linear autoregressive (AR) and autoregressive exogenous (ARX) models.

KW - air quality

KW - CO-estimation

KW - LS-SVM

KW - non-linear modeling

KW - wireless sensor network (WSN)

KW - Sensor Network

UR - http://www.scopus.com/inward/record.url?scp=85044295931&partnerID=8YFLogxK

U2 - 10.1109/ICSENS.2017.8234156

DO - 10.1109/ICSENS.2017.8234156

M3 - Conference contribution

AN - SCOPUS:85044295931

T3 - Proceedings of IEEE Sensors

SP - 1

EP - 3

BT - IEEE SENSORS 2017 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 16th IEEE SENSORS Conference, ICSENS 2017

Y2 - 30 October 2017 through 1 November 2017

ER -