Impact of feature reduction and operating temperature on gas identification

Muhammad Ali Akbar, Amine Ait Si Ali, Abbes Amira, Faycal Bensaali, Mohieddine Benammar, Muhammad Hassan, Amine Bermak

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Tin-oxide based gas sensor requires an operating temperature typically in the range of 200 °C to 400 °C and its performance dependents on this temperature. In this paper a deep examination has been made to analyze the best operating temperature suitable for gas identification application in which an array of sensors is used along with an appropriate feature reduction algorithm. The two most common feature reduction algorithms for gas classification are principal component analysis (PCA) and linear discriminant analysis (LDA); both of them have been used in this analytical work. The feature reduction is followed by a binary decision tree (BDT) or K-nearest neighbor (KNN) based classifier. Results obtained with data from an array of sensors used for detecting C6H6, CH2O, CO, NO2 and SO2 indicates that at 400 °C the BDT can classify 100% of gases after LDA based feature reduction, whereas KNN can classify 100% of gases at 200 °C and 300 °C using data before and after feature reduction. Furthermore, experimental results from the given sensor data suggest that with and without considering the operating temperature the BDT can classify 96% of gases using first four LDA components. While KNN can classify 98% to 99% of gases using first four LDA or first five PCA components of resulting data obtained after feature reduction. Thus, after LDA-based feature reduction both classifiers provide superior identification with minimum number of components.

Original languageEnglish
Pages (from-to)8783-8790
Number of pages8
JournalARPN Journal of Engineering and Applied Sciences
Volume10
Issue number19
Publication statusPublished - 2015
Externally publishedYes

Fingerprint

Discriminant analysis
Gases
Decision trees
Temperature
Principal component analysis
Sensors
Classifiers
Tin oxides
Chemical sensors

Keywords

  • Electronic nose
  • Feature reduction
  • Gas identification
  • Sensor array

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Akbar, M. A., Si Ali, A. A., Amira, A., Bensaali, F., Benammar, M., Hassan, M., & Bermak, A. (2015). Impact of feature reduction and operating temperature on gas identification. ARPN Journal of Engineering and Applied Sciences, 10(19), 8783-8790.

Impact of feature reduction and operating temperature on gas identification. / Akbar, Muhammad Ali; Si Ali, Amine Ait; Amira, Abbes; Bensaali, Faycal; Benammar, Mohieddine; Hassan, Muhammad; Bermak, Amine.

In: ARPN Journal of Engineering and Applied Sciences, Vol. 10, No. 19, 2015, p. 8783-8790.

Research output: Contribution to journalArticle

Akbar, MA, Si Ali, AA, Amira, A, Bensaali, F, Benammar, M, Hassan, M & Bermak, A 2015, 'Impact of feature reduction and operating temperature on gas identification', ARPN Journal of Engineering and Applied Sciences, vol. 10, no. 19, pp. 8783-8790.
Akbar MA, Si Ali AA, Amira A, Bensaali F, Benammar M, Hassan M et al. Impact of feature reduction and operating temperature on gas identification. ARPN Journal of Engineering and Applied Sciences. 2015;10(19):8783-8790.
Akbar, Muhammad Ali ; Si Ali, Amine Ait ; Amira, Abbes ; Bensaali, Faycal ; Benammar, Mohieddine ; Hassan, Muhammad ; Bermak, Amine. / Impact of feature reduction and operating temperature on gas identification. In: ARPN Journal of Engineering and Applied Sciences. 2015 ; Vol. 10, No. 19. pp. 8783-8790.
@article{4d1f919ed8d64e2cab0993a902fd0511,
title = "Impact of feature reduction and operating temperature on gas identification",
abstract = "Tin-oxide based gas sensor requires an operating temperature typically in the range of 200 °C to 400 °C and its performance dependents on this temperature. In this paper a deep examination has been made to analyze the best operating temperature suitable for gas identification application in which an array of sensors is used along with an appropriate feature reduction algorithm. The two most common feature reduction algorithms for gas classification are principal component analysis (PCA) and linear discriminant analysis (LDA); both of them have been used in this analytical work. The feature reduction is followed by a binary decision tree (BDT) or K-nearest neighbor (KNN) based classifier. Results obtained with data from an array of sensors used for detecting C6H6, CH2O, CO, NO2 and SO2 indicates that at 400 °C the BDT can classify 100{\%} of gases after LDA based feature reduction, whereas KNN can classify 100{\%} of gases at 200 °C and 300 °C using data before and after feature reduction. Furthermore, experimental results from the given sensor data suggest that with and without considering the operating temperature the BDT can classify 96{\%} of gases using first four LDA components. While KNN can classify 98{\%} to 99{\%} of gases using first four LDA or first five PCA components of resulting data obtained after feature reduction. Thus, after LDA-based feature reduction both classifiers provide superior identification with minimum number of components.",
keywords = "Electronic nose, Feature reduction, Gas identification, Sensor array",
author = "Akbar, {Muhammad Ali} and {Si Ali}, {Amine Ait} and Abbes Amira and Faycal Bensaali and Mohieddine Benammar and Muhammad Hassan and Amine Bermak",
year = "2015",
language = "English",
volume = "10",
pages = "8783--8790",
journal = "ARPN Journal of Engineering and Applied Sciences",
issn = "1819-6608",
publisher = "Asian Research Publishing Network (ARPN)",
number = "19",

}

TY - JOUR

T1 - Impact of feature reduction and operating temperature on gas identification

AU - Akbar, Muhammad Ali

AU - Si Ali, Amine Ait

AU - Amira, Abbes

AU - Bensaali, Faycal

AU - Benammar, Mohieddine

AU - Hassan, Muhammad

AU - Bermak, Amine

PY - 2015

Y1 - 2015

N2 - Tin-oxide based gas sensor requires an operating temperature typically in the range of 200 °C to 400 °C and its performance dependents on this temperature. In this paper a deep examination has been made to analyze the best operating temperature suitable for gas identification application in which an array of sensors is used along with an appropriate feature reduction algorithm. The two most common feature reduction algorithms for gas classification are principal component analysis (PCA) and linear discriminant analysis (LDA); both of them have been used in this analytical work. The feature reduction is followed by a binary decision tree (BDT) or K-nearest neighbor (KNN) based classifier. Results obtained with data from an array of sensors used for detecting C6H6, CH2O, CO, NO2 and SO2 indicates that at 400 °C the BDT can classify 100% of gases after LDA based feature reduction, whereas KNN can classify 100% of gases at 200 °C and 300 °C using data before and after feature reduction. Furthermore, experimental results from the given sensor data suggest that with and without considering the operating temperature the BDT can classify 96% of gases using first four LDA components. While KNN can classify 98% to 99% of gases using first four LDA or first five PCA components of resulting data obtained after feature reduction. Thus, after LDA-based feature reduction both classifiers provide superior identification with minimum number of components.

AB - Tin-oxide based gas sensor requires an operating temperature typically in the range of 200 °C to 400 °C and its performance dependents on this temperature. In this paper a deep examination has been made to analyze the best operating temperature suitable for gas identification application in which an array of sensors is used along with an appropriate feature reduction algorithm. The two most common feature reduction algorithms for gas classification are principal component analysis (PCA) and linear discriminant analysis (LDA); both of them have been used in this analytical work. The feature reduction is followed by a binary decision tree (BDT) or K-nearest neighbor (KNN) based classifier. Results obtained with data from an array of sensors used for detecting C6H6, CH2O, CO, NO2 and SO2 indicates that at 400 °C the BDT can classify 100% of gases after LDA based feature reduction, whereas KNN can classify 100% of gases at 200 °C and 300 °C using data before and after feature reduction. Furthermore, experimental results from the given sensor data suggest that with and without considering the operating temperature the BDT can classify 96% of gases using first four LDA components. While KNN can classify 98% to 99% of gases using first four LDA or first five PCA components of resulting data obtained after feature reduction. Thus, after LDA-based feature reduction both classifiers provide superior identification with minimum number of components.

KW - Electronic nose

KW - Feature reduction

KW - Gas identification

KW - Sensor array

UR - http://www.scopus.com/inward/record.url?scp=84946406986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946406986&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84946406986

VL - 10

SP - 8783

EP - 8790

JO - ARPN Journal of Engineering and Applied Sciences

JF - ARPN Journal of Engineering and Applied Sciences

SN - 1819-6608

IS - 19

ER -