Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 7, Issue 1, 2026

Comparative Study on the Performance of Classification Models in Exhaled VOCs Sensing Applications

Download as PDF

DOI: 10.23977/autml.2026.070119 | Downloads: 1 | Views: 17

Author(s)

Ling Jiang 1, Chilin Zhang 2, Xianhua Zhong 1,3

Affiliation(s)

1 School of Life Health Information Science and Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
2 Chongqing Postdoctoral Research Station of Medical Electronics and Information Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
3 Chongqing Postdoctoral Research Station of Medical Electronics and Information Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China; Chongqing Engineering Laboratory of Digital Medical Equipment and Systems, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

Corresponding Author

Xianhua Zhong

ABSTRACT

The volatile organic compounds (VOCs) in exhaled breath are important disease biomarkers, and their rapid and accurate identification is of great significance for early disease screening. Regarding the issue of the applicability of classification models in the VOCs identification of colorimetric sensor arrays under small sample conditions, this study focused on the array response data of 20 typical exhaled VOCs, constructed and compared models such as linear discriminant analysis (LDA), hierarchical cluster analysis (HCA), support vector machine (SVM), and residual network (ResNet), and systematically evaluated their classification performance. The results showed that HCA and LDA are suitable for stability assessment and preliminary classification of the sensing array; SVM is suitable for small-scale classification tasks; ResNet34 achieved 100% recognition accuracy on the validation set and achieved a good balance between recognition performance and computational complexity, making it more suitable for high-precision and on-site detection scenarios. This study provides a basis for model selection for exhaled VOCs detection based on multiple sensors or multiple response modes, and has reference significance for promoting the application of colorimetric sensor arrays in clinical early diagnosis.

KEYWORDS

Exhaled VOCs; Colorimetric Sensor Array; Classification Model; Performance Comparison

CITE THIS PAPER

Ling Jiang, Chilin Zhang, Xianhua Zhong. Comparative Study on the Performance of Classification Models in Exhaled VOCs Sensing Applications. Automation and Machine Learning (2026). Vol. 7, No. 1, 150-161. DOI: http://dx.doi.org/10.23977/autml.2026.070119.

REFERENCES

[1] Allard-Coutu A, Singh K, David D, et al. Volatile organic compounds: A promising new frontier for cancer screening[J]. Tumor Discovery, 2024, 3(2): 2061.
[2] Pereira J, Porto-Figueira P, Cavaco C, et al. Breath Analysis as a Potential and Non-Invasive Frontier in Disease Diagnosis: An Overview[J]. Metabolites, 2015, 5(1): 3.
[3] Das S, Pal S, Mitra M. Significance of Exhaled Breath Test in Clinical Diagnosis: A Special Focus on the Detection of Diabetes Mellitus[J]. Journal of Medical & Biological Engineering, 2016, 36(5): 605-624.
[4] Dalis C, Mesfin F M, Manohar K, et al. Volatile Organic Compound Assessment as a Screening Tool for Early Detection of Gastrointestinal Diseases[J]. Microorganisms, 2023, 11(7): 25.
[5] Moura PC, Raposo M, Vassilenko V. Breath volatile organic compounds (VOCs) as biomarkers for the diagnosis of pathological conditions: A review[J]. Biomed J. 2023, 46(4): 100623.
[6] Schoolaert E, Hoogenboom R, De Clerck K. Colorimetric Nanofibers as Optical Sensors[J]. Advanced Functional Materials, 2017: 1702646.
[7] Queralto N, Berliner AN, Goldsmith B, et al. Lim SH. Detecting cancer by breath volatile organic compound analysis: a review of array-based sensors[J]. J Breath Res. 2014, 8(2): 027112.
[8] Faura G, Boix-Lemonche G, Holmeide AK, et al. Colorimetric and Electrochemical Screening for Early Detection of Diabetes Mellitus and Diabetic Retinopathy-Application of Sensor Arrays and Machine Learning[J]. Sensors (Basel). 2022, 22(3): 718.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 5209
Visits: 261690

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.