This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms

Xianzhang Zeng

^1,†,

Muhammad Shahzeb

^1,†,

Xin Cheng

²,

Qiang Shen

¹,

Hongyang Xiao

³,

Cao Xia

¹,

Yuanlin Xia

¹,

Yubo Huang

Jingfei Xu

^4,5,* and

Zhuqing Wang

^1,*

School of Mechanical Engineering, Sichuan University, Chengdu 610065, China

Graduate School of International Cultural Studies, Tohoku University, Kawauchi 41, Aoba Ku, Sendai 980-8577, Miyagi, Japan

Pittsburgh Institute, Sichuan University, Chengdu 610225, China

⁴

Rehabilitation Medicine Center, West China Hospital, Sichuan University, Chengdu 610041, China

⁵

Key Laboratory of Rehabilitation Medicine in Sichuan Province, West China Hospital, Sichuan University, Chengdu 610041, China

Authors to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Micromachines 2024, 15(12), 1501; https://doi.org/10.3390/mi15121501

Submission received: 13 November 2024 / Revised: 5 December 2024 / Accepted: 12 December 2024 / Published: 16 December 2024

Download Versions Notes

Abstract

This study addresses the challenge of multi-dimensional and small gas sensor data classification using a gelatin–carbon black (CB-GE) composite film sensor, achieving 91.7% accuracy in differentiating gas types (ethanol, acetone, and air). Key techniques include Principal Component Analysis (PCA) for dimensionality reduction, the Synthetic Minority Over-sampling Technique (SMOTE) for data augmentation, and the Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) algorithms for classification. PCA improved KNN and SVM classification, boosting the Area Under the Curve (AUC) scores by 15.7% and 25.2%, respectively. SMOTE increased KNN’s accuracy by 2.1%, preserving data structure better than polynomial fitting. The results demonstrate a scalable approach to enhancing classification accuracy under data constraints. This approach shows promise for expanding gas sensor applicability in fields where data limitations previously restricted reliability and effectiveness.

Keywords: machine learning; gas sensor; PCA; SMOTE; KNN

Share and Cite

MDPI and ACS Style

Zeng, X.; Shahzeb, M.; Cheng, X.; Shen, Q.; Xiao, H.; Xia, C.; Xia, Y.; Huang, Y.; Xu, J.; Wang, Z. An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms. Micromachines 2024, 15, 1501. https://doi.org/10.3390/mi15121501

AMA Style

Zeng X, Shahzeb M, Cheng X, Shen Q, Xiao H, Xia C, Xia Y, Huang Y, Xu J, Wang Z. An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms. Micromachines. 2024; 15(12):1501. https://doi.org/10.3390/mi15121501

Chicago/Turabian Style

Zeng, Xianzhang, Muhammad Shahzeb, Xin Cheng, Qiang Shen, Hongyang Xiao, Cao Xia, Yuanlin Xia, Yubo Huang, Jingfei Xu, and Zhuqing Wang. 2024. "An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms" Micromachines 15, no. 12: 1501. https://doi.org/10.3390/mi15121501

APA Style

Zeng, X., Shahzeb, M., Cheng, X., Shen, Q., Xiao, H., Xia, C., Xia, Y., Huang, Y., Xu, J., & Wang, Z. (2024). An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms. Micromachines, 15(12), 1501. https://doi.org/10.3390/mi15121501

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI