Mixture Gases Classification Based on Multi-Label One-Dimensional Deep Convolutional Neural Network

Xiaojin Zhao, Zhihuang Wen, Xiaofang Pan, Wenbin Ye, Amine Bermak

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multi-label-way-based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of ethylene, CO, and methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is first applied in the mixture gases' recognition. In addition, the proposed 1D-DCNN with multi-label way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine, artificial neural network, k-nearest neighbor, and random forest, the proposed 1D-DCNN exhibits a higher recognition accuracy (96.30%) based on our extensive experimental results using ten-fold cross validation.

Original languageEnglish
Article number8611207
Pages (from-to)12630-12637
Number of pages8
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Gas mixtures
Labels
Gases
Neural networks
Pattern recognition
Methane
Carbon Monoxide
Binary mixtures
Convolution
Support vector machines
Ethylene
ethylene

Keywords

  • deep convolutional neural network
  • Mixture gases recognition
  • multi-label classification

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Mixture Gases Classification Based on Multi-Label One-Dimensional Deep Convolutional Neural Network. / Zhao, Xiaojin; Wen, Zhihuang; Pan, Xiaofang; Ye, Wenbin; Bermak, Amine.

In: IEEE Access, Vol. 7, 8611207, 01.01.2019, p. 12630-12637.

Research output: Contribution to journalArticle

Zhao, Xiaojin ; Wen, Zhihuang ; Pan, Xiaofang ; Ye, Wenbin ; Bermak, Amine. / Mixture Gases Classification Based on Multi-Label One-Dimensional Deep Convolutional Neural Network. In: IEEE Access. 2019 ; Vol. 7. pp. 12630-12637.
@article{66d9fe8a8fea4fe4a7b66ca104f7d5e4,
title = "Mixture Gases Classification Based on Multi-Label One-Dimensional Deep Convolutional Neural Network",
abstract = "In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multi-label-way-based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of ethylene, CO, and methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is first applied in the mixture gases' recognition. In addition, the proposed 1D-DCNN with multi-label way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine, artificial neural network, k-nearest neighbor, and random forest, the proposed 1D-DCNN exhibits a higher recognition accuracy (96.30{\%}) based on our extensive experimental results using ten-fold cross validation.",
keywords = "deep convolutional neural network, Mixture gases recognition, multi-label classification",
author = "Xiaojin Zhao and Zhihuang Wen and Xiaofang Pan and Wenbin Ye and Amine Bermak",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2892754",
language = "English",
volume = "7",
pages = "12630--12637",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Mixture Gases Classification Based on Multi-Label One-Dimensional Deep Convolutional Neural Network

AU - Zhao, Xiaojin

AU - Wen, Zhihuang

AU - Pan, Xiaofang

AU - Ye, Wenbin

AU - Bermak, Amine

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multi-label-way-based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of ethylene, CO, and methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is first applied in the mixture gases' recognition. In addition, the proposed 1D-DCNN with multi-label way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine, artificial neural network, k-nearest neighbor, and random forest, the proposed 1D-DCNN exhibits a higher recognition accuracy (96.30%) based on our extensive experimental results using ten-fold cross validation.

AB - In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multi-label-way-based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of ethylene, CO, and methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is first applied in the mixture gases' recognition. In addition, the proposed 1D-DCNN with multi-label way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine, artificial neural network, k-nearest neighbor, and random forest, the proposed 1D-DCNN exhibits a higher recognition accuracy (96.30%) based on our extensive experimental results using ten-fold cross validation.

KW - deep convolutional neural network

KW - Mixture gases recognition

KW - multi-label classification

UR - http://www.scopus.com/inward/record.url?scp=85061329404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061329404&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2892754

DO - 10.1109/ACCESS.2019.2892754

M3 - Article

AN - SCOPUS:85061329404

VL - 7

SP - 12630

EP - 12637

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8611207

ER -