Computationally efficient environmental monitoring with electronic nose

A potential technology for ambient assisted living

Muhammad Hassan, Muhammad Umar, Amine Bermak, Amine Ait Si Ali, Abbes Amira

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recently, ambient assisted living technologies have emerged to improve the quality of life of ageing populations. Identification of health-endangering indoor gases with a hardware-friendly solution may provide an early warning of unhealthy living conditions. Electronic nose technology, using an array of non-selective gas sensors, is a potential candidate to achieve this objective, but state-of-The-Art gas classifiers hinder the development of low-cost and compact solutions. In this paper, we introduce a very simple classifier that transforms the multi-gas identification problem into pair-wise binary classification problems. This classifier is based on the resultant sign of the difference between values of the sensors' features for all possible pairs of sensors in each binary classification problem. A classifier qualification metric is defined to evaluate its suitability with given data of the target gases. As a case study, experimental data of four health-endangering gases, namely, formaldehyde, carbon monoxide, nitrogen dioxide and sulfur dioxide, is acquired in the laboratory by developing an array of commercially available gas sensors fabricated by Figaro Inc. and FIS Inc. A classification accuracy of 94.56% is achieved in distinguishing the target gasses with our proposed classifier. This performance is comparable to that of computation intensive state-of-The-Art gas classifiers despite our classifier's simple implementation.

Original languageEnglish
Title of host publicationISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509007936
DOIs
Publication statusPublished - 22 Nov 2016
Externally publishedYes
Event2nd Annual IEEE International Symposium on Systems Engineering, ISSE 2016 - Edinburgh, United Kingdom
Duration: 3 Oct 20165 Oct 2016

Other

Other2nd Annual IEEE International Symposium on Systems Engineering, ISSE 2016
CountryUnited Kingdom
CityEdinburgh
Period3/10/165/10/16

Fingerprint

Ambient Assisted Living
Environmental Monitoring
Classifiers
Classifier
Electronics
Monitoring
Gases
Gas Sensor
Binary Classification
Chemical sensors
Classification Problems
Health
Sulfur Dioxide
Sensor
Carbon Monoxide
Early Warning
Target
Quality of Life
Qualification
Sensors

Keywords

  • binary classifiers
  • electronic nose
  • environmental monitoring
  • pair of sensors

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation

Cite this

Hassan, M., Umar, M., Bermak, A., Ali, A. A. S., & Amira, A. (2016). Computationally efficient environmental monitoring with electronic nose: A potential technology for ambient assisted living. In ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers [7753122] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SysEng.2016.7753122

Computationally efficient environmental monitoring with electronic nose : A potential technology for ambient assisted living. / Hassan, Muhammad; Umar, Muhammad; Bermak, Amine; Ali, Amine Ait Si; Amira, Abbes.

ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers. Institute of Electrical and Electronics Engineers Inc., 2016. 7753122.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hassan, M, Umar, M, Bermak, A, Ali, AAS & Amira, A 2016, Computationally efficient environmental monitoring with electronic nose: A potential technology for ambient assisted living. in ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers., 7753122, Institute of Electrical and Electronics Engineers Inc., 2nd Annual IEEE International Symposium on Systems Engineering, ISSE 2016, Edinburgh, United Kingdom, 3/10/16. https://doi.org/10.1109/SysEng.2016.7753122
Hassan M, Umar M, Bermak A, Ali AAS, Amira A. Computationally efficient environmental monitoring with electronic nose: A potential technology for ambient assisted living. In ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers. Institute of Electrical and Electronics Engineers Inc. 2016. 7753122 https://doi.org/10.1109/SysEng.2016.7753122
Hassan, Muhammad ; Umar, Muhammad ; Bermak, Amine ; Ali, Amine Ait Si ; Amira, Abbes. / Computationally efficient environmental monitoring with electronic nose : A potential technology for ambient assisted living. ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{22ce0e28cfe94202a9d04d68711e4f10,
title = "Computationally efficient environmental monitoring with electronic nose: A potential technology for ambient assisted living",
abstract = "Recently, ambient assisted living technologies have emerged to improve the quality of life of ageing populations. Identification of health-endangering indoor gases with a hardware-friendly solution may provide an early warning of unhealthy living conditions. Electronic nose technology, using an array of non-selective gas sensors, is a potential candidate to achieve this objective, but state-of-The-Art gas classifiers hinder the development of low-cost and compact solutions. In this paper, we introduce a very simple classifier that transforms the multi-gas identification problem into pair-wise binary classification problems. This classifier is based on the resultant sign of the difference between values of the sensors' features for all possible pairs of sensors in each binary classification problem. A classifier qualification metric is defined to evaluate its suitability with given data of the target gases. As a case study, experimental data of four health-endangering gases, namely, formaldehyde, carbon monoxide, nitrogen dioxide and sulfur dioxide, is acquired in the laboratory by developing an array of commercially available gas sensors fabricated by Figaro Inc. and FIS Inc. A classification accuracy of 94.56{\%} is achieved in distinguishing the target gasses with our proposed classifier. This performance is comparable to that of computation intensive state-of-The-Art gas classifiers despite our classifier's simple implementation.",
keywords = "binary classifiers, electronic nose, environmental monitoring, pair of sensors",
author = "Muhammad Hassan and Muhammad Umar and Amine Bermak and Ali, {Amine Ait Si} and Abbes Amira",
year = "2016",
month = "11",
day = "22",
doi = "10.1109/SysEng.2016.7753122",
language = "English",
booktitle = "ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Computationally efficient environmental monitoring with electronic nose

T2 - A potential technology for ambient assisted living

AU - Hassan, Muhammad

AU - Umar, Muhammad

AU - Bermak, Amine

AU - Ali, Amine Ait Si

AU - Amira, Abbes

PY - 2016/11/22

Y1 - 2016/11/22

N2 - Recently, ambient assisted living technologies have emerged to improve the quality of life of ageing populations. Identification of health-endangering indoor gases with a hardware-friendly solution may provide an early warning of unhealthy living conditions. Electronic nose technology, using an array of non-selective gas sensors, is a potential candidate to achieve this objective, but state-of-The-Art gas classifiers hinder the development of low-cost and compact solutions. In this paper, we introduce a very simple classifier that transforms the multi-gas identification problem into pair-wise binary classification problems. This classifier is based on the resultant sign of the difference between values of the sensors' features for all possible pairs of sensors in each binary classification problem. A classifier qualification metric is defined to evaluate its suitability with given data of the target gases. As a case study, experimental data of four health-endangering gases, namely, formaldehyde, carbon monoxide, nitrogen dioxide and sulfur dioxide, is acquired in the laboratory by developing an array of commercially available gas sensors fabricated by Figaro Inc. and FIS Inc. A classification accuracy of 94.56% is achieved in distinguishing the target gasses with our proposed classifier. This performance is comparable to that of computation intensive state-of-The-Art gas classifiers despite our classifier's simple implementation.

AB - Recently, ambient assisted living technologies have emerged to improve the quality of life of ageing populations. Identification of health-endangering indoor gases with a hardware-friendly solution may provide an early warning of unhealthy living conditions. Electronic nose technology, using an array of non-selective gas sensors, is a potential candidate to achieve this objective, but state-of-The-Art gas classifiers hinder the development of low-cost and compact solutions. In this paper, we introduce a very simple classifier that transforms the multi-gas identification problem into pair-wise binary classification problems. This classifier is based on the resultant sign of the difference between values of the sensors' features for all possible pairs of sensors in each binary classification problem. A classifier qualification metric is defined to evaluate its suitability with given data of the target gases. As a case study, experimental data of four health-endangering gases, namely, formaldehyde, carbon monoxide, nitrogen dioxide and sulfur dioxide, is acquired in the laboratory by developing an array of commercially available gas sensors fabricated by Figaro Inc. and FIS Inc. A classification accuracy of 94.56% is achieved in distinguishing the target gasses with our proposed classifier. This performance is comparable to that of computation intensive state-of-The-Art gas classifiers despite our classifier's simple implementation.

KW - binary classifiers

KW - electronic nose

KW - environmental monitoring

KW - pair of sensors

UR - http://www.scopus.com/inward/record.url?scp=85006476268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006476268&partnerID=8YFLogxK

U2 - 10.1109/SysEng.2016.7753122

DO - 10.1109/SysEng.2016.7753122

M3 - Conference contribution

BT - ISSE 2016 - 2016 International Symposium on Systems Engineering - Proceedings Papers

PB - Institute of Electrical and Electronics Engineers Inc.

ER -