A Compact and Explainable Machine Learning Pipeline for Low-Concentration Gas Sensor Array Classification

Öz

This study investigates whether compact and physically interpretable time-domain descriptors can support accurate low-concentration gas classification without relying on full multichannel waveforms. Using the Gas Sensor Array Low-Concentration dataset, each sample was transformed from raw sensor signals into 120 descriptors that summarize baseline behavior, variability, transient dynamics, and response magnitude. Four classical learning pipelines were evaluated through repeated stratified 5-fold cross-validation, supported by principal component analysis, descriptor ranking, sensor correlation analysis, and sensor subset experiments. The best-performing model, a radial support vector machine trained on the compact descriptor set, achieved a mean accuracy of 0.9456 and a macro-averaged F1 score of 0.9437 across 100 test folds while using 75 times fewer inputs than the raw waveform representation. An important finding is that classification performance improved systematically with concentration: accuracy was 0.9067 at 50 ppb, increased to 0.9333 at 100 ppb, and reached 0.9967 at 200 ppb. Response mean and baseline mean emerged as the most informative descriptor families, while VOCS-P, 2M012, and MQ-137 were the most discriminative sensors. Overall, the results show that compact and interpretable descriptors provide an efficient, reproducible, and practically useful benchmark for low-concentration gas classification in resource-constrained electronic nose systems.

Anahtar Kelimeler

• classification
• electronic nose
• feature engineering
• interpretability
• low-concentration gas
• sensor array
• support vector machine

Kaynakça

1. [1]. James, D, Scott, SM, Ali, Z, O’Hare, WT. 2005. Chemical sensors for electronic nose systems. Microchimica Acta; 149(1-2): 1-17.
2. [2]. Röck, F, Barsan, N, Weimar, U. 2008. Electronic nose: current status and future trends. Chemical Reviews; 108(2): 705-725.
3. [3]. Tan, J, Xu, J. 2020. Applications of electronic nose and electronic tongue in food quality-related properties determination: a review. Artificial Intelligence in Agriculture; 4: 104-115.
4. [4]. Scott, SM, James, D, Ali, Z. 2006. Data analysis for electronic nose systems. Microchimica Acta; 156(3): 183-207.
5. [5]. Ye, Z, Liu, Y, Li, Q. 2021. Recent progress in smart electronic nose technologies enabled with machine learning methods. Sensors; 21(22): 7620.
6. [6]. Zhai, Z, Liu, Y, Li, C, Wang, D, Wu, H. 2024. Electronic noses: from gas-sensitive components and practical applications to data processing. Sensors; 24(15): 4806.
7. [7]. Chowdhury, MAZ, Oehlschlaeger, MA. 2025. Artificial intelligence in gas sensing: a review. ACS Sensors; 10(3): 1538-1563.
8. [8]. Yan, J, Guo, X, Duan, S, Jia, P, Wang, L, Peng, C, Zhang, S. 2015. Electronic nose feature extraction methods: a review. Sensors; 15(11): 27804-27831.

9. [9]. Sun, H, Tian, F, Liang, Z, et al. 2017. Sensor array optimization of electronic nose for detection of bacteria in wound infection. IEEE Transactions on Industrial Electronics; 64(9): 7350-7358.
10. [10]. Liu, B, Xie, C, Wang, Y, et al. 2021. Lung cancer detection via breath by electronic nose enhanced with a sparse group feature selection approach. Sensors and Actuators B: Chemical; 339: 129896.
11. [11]. Saha, P, Ghorai, S, Tudu, B, Bandyopadhyay, R, Bhattacharyya, N. 2014. Optimization of sensor array in electronic nose by combinational feature selection method. In: Sensing Technology: Current Status and Future Trends II. Berlin: Springer; 189-205.
12. [12]. Zhang, L, Tian, FC. 2014. A new kernel discriminant analysis framework for electronic nose recognition. Analytica Chimica Acta; 816: 8-17.
13. [13]. Zhao, W, Meng, QH, Zeng, M, Qi, PF. 2017. Stacked sparse auto-encoders based electronic nose for Chinese liquors classification. Sensors; 17(12): 2855.
14. [14]. Peng, P, Zhao, X, Pan, X, Ye, W. 2018. Gas classification using deep convolutional neural networks. Sensors; 18(2): 157.
15. [15]. Qian, J, Tian, F, Luo, Y, Lu, M, Zhang, A. 2022. A novel multisensor detection system design for low concentrations of volatile organic compounds. IEEE Transactions on Industrial Electronics; 69(5): 5314-5324.
16. [16]. Zhao, L, Tian, F, Qian, J, Li, H, Wu, Z. 2023. Feature ensemble learning for sensor array data classification under low-concentration gas. IEEE Transactions on Instrumentation and Measurement; 72: 2507809.
17. [17]. Wei, G, Li, G, Zhao, J, He, A. 2019. Development of a LeNet-5 gas identification convolutional neural network structure for electronic noses. Sensors; 19(1): 217.
18. [18]. Gamboa, JCR, Da Silva, AJ, Araujo, ICS, Albarracin, ES, Duran, CM. 2021. Validation of the rapid detection approach for enhancing the electronic nose systems performance, using different deep learning models and support vector machines. Sensors and Actuators B: Chemical; 327: 128921.
19. [19]. Guo, J, Cheng, Y, Luo, D, Wong, KY, Hung, K, Li, X. 2021. ODRP: a deep learning framework for odor descriptor rating prediction using electronic nose. IEEE Sensors Journal; 21(13): 15012-15021.
20. [20]. Huang, W, Zhang, L, Gao, W, Min, F, He, J. 2021. Shallow convolutional neural networks for human activity recognition using wearable sensors. IEEE Transactions on Instrumentation and Measurement; 70: 1-11.
21. [21]. Gao, W, Zhang, L, Huang, W, Min, F, He, J, Song, A. 2021. Deep neural networks for sensor-based human activity recognition using selective kernel convolution. IEEE Transactions on Instrumentation and Measurement; 70: 1-13.
22. [22]. Tang, Y, Zhang, L, Min, F, He, J. 2023. Multiscale deep feature learning for human activity recognition using wearable sensors. IEEE Transactions on Industrial Electronics; 70(2): 2106-2116.
23. [23]. Ziyatdinov, A, Fonollosa, J, Fernández, L, Gutierrez-Gálvez, A, Marco, S, Perera, A. 2015. Bioinspired early detection through gas flow modulation in chemo-sensory systems. Sensors and Actuators B: Chemical; 206: 538-547.
24. [24]. Jing, YQ, Meng, QH, Qi, PF, Cao, ML, Zeng, M, Ma, SG. 2016. A bioinspired neural network for data processing in an electronic nose. IEEE Transactions on Instrumentation and Measurement; 65(10): 2369-2380.
25. [25]. Sun, X, Tian, F, et al. 2017. An optimized multi-classifiers ensemble learning for identification of ginsengs based on electronic nose. Sensors and Actuators A: Physical; 266: 135-144.
26. [26]. Wang, T, Li, Y, Wang, Y, et al. 2023. Portable electronic nose system with elastic architecture and fault tolerance based on edge computing, ensemble learning, and sensor swarm. Sensors and Actuators B: Chemical; 375: 132925.
27. [27]. Sagi, O, Rokach, L. 2018. Ensemble learning: a survey. WIREs Data Mining and Knowledge Discovery; 8(4): e1249.
28. [28]. Zhou, ZH. 2012. Ensemble Methods: Foundations and Algorithms. Boca Raton: CRC Press.
29. [29]. Hansen, LK, Salamon, P. 1990. Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence; 12(10): 993-1001.
30. [30]. Schapire, RE. 1990. The strength of weak learnability. Machine Learning; 5(2): 197-227.
31. [31]. Huang, GB, Zhou, H, Ding, X, Zhang, R. 2012. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics; 42(2): 513-529.
32. [32]. Huang, G, Huang, GB, Song, S, You, K. 2015. Trends in extreme learning machines: a review. Neural Networks; 61: 32-48.
33. [33]. Kim, CH, Choi, SH, Choi, S, Lee, S. 2025. A reproducible benchmark for gas sensor array classification: from FE-ELM to ROCKET and TS2I-CNNs. Sensors; 25(20): 6270.
34. [34]. Luo, W, Dai, F, Liu, Y, Wang, X, Li, M, et al. 2025. Pulse-driven MEMS gas sensor combined with machine learning for selective gas identification. Microsystems & Nanoengineering; 11: 72.
35. [35]. Li, M, Wu, C, Wang, Z, Wu, Z, Huang, W, Chen, J, et al. 2026. Enhanced gas classification in electronic nose systems using an SMOTE-augmented machine learning framework. Sensors; 26(2): 714.
36. [36]. Wörner, J, Eimler, J, Pein-Hackelbusch, M. 2025. Long-term drift behavior in metal oxide gas sensor arrays: a one-year dataset from an electronic nose. Scientific Data; 12: 1628.