Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications

Yuntao Wu; Jinchang Ren; Rongjun Chen; Huimin Zhao; Amir Hussain

doi:10.1007/978-981-96-2885-8_28

Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications

Yuntao Wu
, Jinchang Ren^*
, Rongjun Chen
, Huimin Zhao
, Amir Hussain

^*Corresponding author for this work

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

Abstract

This paper focuses on the gas data processing and pattern recognition modules of detection and proposes a time-domain feature extraction method based on Singular Spectrum Analysis (SSATFE). This method effectively captures and reduces the dimensionality of gas signals, making the data more manageable for classification. To evaluate the extracted features, tree-based classifiers like decision trees and random forests were used. These models handle non-linear relationships well and are robust to noise, which is common in gas sensor data. Experiments on the UCL dataset show the classifiers’ ability to use the key components extracted by the SSA method for accurate gas detection.

Original language	English
Title of host publication	Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings
Editors	Amir Hussain, Bo Jiang, Jinchang Ren, Mufti Mahmud, Erfu Yang, Aihua Zheng, Chenglong Li, Shuqiang Wang, Zhi Gao, Zhicheng Zhao
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	283-293
Number of pages	11
ISBN (Print)	9789819628841
DOIs	https://doi.org/10.1007/978-981-96-2885-8_28
State	Published - 2025
Externally published	Yes
Event	14th International Conference on Brain Inspired Cognitive Systems, BICS 2024 - Hefei, China Duration: 6 Dec 2024 → 8 Dec 2024

Publication series

Name	Lecture Notes in Computer Science
Volume	15498 LNAI
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	14th International Conference on Brain Inspired Cognitive Systems, BICS 2024
Country/Territory	China
City	Hefei
Period	6/12/24 → 8/12/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Keywords

Gas classification
Random forest
Singular spectrum analysis

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-981-96-2885-8_28

Cite this

Wu, Y., Ren, J., Chen, R., Zhao, H., & Hussain, A. (2025). Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications. In A. Hussain, B. Jiang, J. Ren, M. Mahmud, E. Yang, A. Zheng, C. Li, S. Wang, Z. Gao, & Z. Zhao (Eds.), Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings (pp. 283-293). (Lecture Notes in Computer Science; Vol. 15498 LNAI). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-2885-8_28

Wu, Yuntao ; Ren, Jinchang ; Chen, Rongjun et al. / Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications. Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings. editor / Amir Hussain ; Bo Jiang ; Jinchang Ren ; Mufti Mahmud ; Erfu Yang ; Aihua Zheng ; Chenglong Li ; Shuqiang Wang ; Zhi Gao ; Zhicheng Zhao. Springer Science and Business Media Deutschland GmbH, 2025. pp. 283-293 (Lecture Notes in Computer Science).

@inproceedings{7b5dc41881fe42b4a8be06635133a4da,

title = "Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications",

abstract = "This paper focuses on the gas data processing and pattern recognition modules of detection and proposes a time-domain feature extraction method based on Singular Spectrum Analysis (SSATFE). This method effectively captures and reduces the dimensionality of gas signals, making the data more manageable for classification. To evaluate the extracted features, tree-based classifiers like decision trees and random forests were used. These models handle non-linear relationships well and are robust to noise, which is common in gas sensor data. Experiments on the UCL dataset show the classifiers{\textquoteright} ability to use the key components extracted by the SSA method for accurate gas detection.",

keywords = "Gas classification, Random forest, Singular spectrum analysis",

author = "Yuntao Wu and Jinchang Ren and Rongjun Chen and Huimin Zhao and Amir Hussain",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 14th International Conference on Brain Inspired Cognitive Systems, BICS 2024 ; Conference date: 06-12-2024 Through 08-12-2024",

year = "2025",

doi = "10.1007/978-981-96-2885-8\_28",

language = "English",

isbn = "9789819628841",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "283--293",

editor = "Amir Hussain and Bo Jiang and Jinchang Ren and Mufti Mahmud and Erfu Yang and Aihua Zheng and Chenglong Li and Shuqiang Wang and Zhi Gao and Zhicheng Zhao",

booktitle = "Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings",

address = "Germany",

}

Wu, Y, Ren, J, Chen, R, Zhao, H & Hussain, A 2025, Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications. in A Hussain, B Jiang, J Ren, M Mahmud, E Yang, A Zheng, C Li, S Wang, Z Gao & Z Zhao (eds), Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings. Lecture Notes in Computer Science, vol. 15498 LNAI, Springer Science and Business Media Deutschland GmbH, pp. 283-293, 14th International Conference on Brain Inspired Cognitive Systems, BICS 2024, Hefei, China, 6/12/24. https://doi.org/10.1007/978-981-96-2885-8_28

Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications. / Wu, Yuntao; Ren, Jinchang; Chen, Rongjun et al.
Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings. ed. / Amir Hussain; Bo Jiang; Jinchang Ren; Mufti Mahmud; Erfu Yang; Aihua Zheng; Chenglong Li; Shuqiang Wang; Zhi Gao; Zhicheng Zhao. Springer Science and Business Media Deutschland GmbH, 2025. p. 283-293 (Lecture Notes in Computer Science; Vol. 15498 LNAI).

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

TY - GEN

T1 - Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications

AU - Wu, Yuntao

AU - Ren, Jinchang

AU - Chen, Rongjun

AU - Zhao, Huimin

AU - Hussain, Amir

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - This paper focuses on the gas data processing and pattern recognition modules of detection and proposes a time-domain feature extraction method based on Singular Spectrum Analysis (SSATFE). This method effectively captures and reduces the dimensionality of gas signals, making the data more manageable for classification. To evaluate the extracted features, tree-based classifiers like decision trees and random forests were used. These models handle non-linear relationships well and are robust to noise, which is common in gas sensor data. Experiments on the UCL dataset show the classifiers’ ability to use the key components extracted by the SSA method for accurate gas detection.

AB - This paper focuses on the gas data processing and pattern recognition modules of detection and proposes a time-domain feature extraction method based on Singular Spectrum Analysis (SSATFE). This method effectively captures and reduces the dimensionality of gas signals, making the data more manageable for classification. To evaluate the extracted features, tree-based classifiers like decision trees and random forests were used. These models handle non-linear relationships well and are robust to noise, which is common in gas sensor data. Experiments on the UCL dataset show the classifiers’ ability to use the key components extracted by the SSA method for accurate gas detection.

KW - Gas classification

KW - Random forest

KW - Singular spectrum analysis

UR - https://www.scopus.com/pages/publications/105000891179

U2 - 10.1007/978-981-96-2885-8_28

DO - 10.1007/978-981-96-2885-8_28

M3 - Conference contribution

AN - SCOPUS:105000891179

SN - 9789819628841

T3 - Lecture Notes in Computer Science

SP - 283

EP - 293

BT - Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings

A2 - Hussain, Amir

A2 - Jiang, Bo

A2 - Ren, Jinchang

A2 - Mahmud, Mufti

A2 - Yang, Erfu

A2 - Zheng, Aihua

A2 - Li, Chenglong

A2 - Wang, Shuqiang

A2 - Gao, Zhi

A2 - Zhao, Zhicheng

PB - Springer Science and Business Media Deutschland GmbH

T2 - 14th International Conference on Brain Inspired Cognitive Systems, BICS 2024

Y2 - 6 December 2024 through 8 December 2024

ER -

Wu Y, Ren J, Chen R, Zhao H, Hussain A. Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications. In Hussain A, Jiang B, Ren J, Mahmud M, Yang E, Zheng A, Li C, Wang S, Gao Z, Zhao Z, editors, Advances in Brain Inspired Cognitive Systems - 14th International Conference, BICS 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 283-293. (Lecture Notes in Computer Science). doi: 10.1007/978-981-96-2885-8_28

Effective Gas Classification Using Singular Spectrum Analysis and Random Forest in Electronic Nose Applications

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this