TIME -RESOLVED MACHINE LEARNING FRAMEWORK FOR VOC DETECTION USING ZNO NANOSTRUCTURED SENSORS

admin July 19, 2026

Authors:

B. Paramita,R. Sunipa,B. Utpal,

DOI NO:

https://doi.org/10.26782/jmcms.2026.07.00013

Keywords:

ZnO,Formaldehyde,Acetone,Supervised Machine Learning,Gradient Boost,ANN.,

Abstract

The presence of volatile organic compounds (VOCs) is generally understood through their effects on the environment and human health. This paper presents a ZnO nano-foam-like thin film sensor to detect acetone and formaldehyde at 190- 2020 ppm in controlled laboratory settings. A quasi-steady time-resolved machine learning methodology is used to overcome the poor selectivity of ZnO-based sensors. A short portion of the sensor response is used to extract features instead of just the steady-state values, giving a more accurate representation of the dynamic sensing behavior. Various machine learning algorithms are evaluated for VOC classification. Among these, Artificial Neural Networks (ANN) have the best accuracy of 98%, whereas Gradient Boosting performs more balanced in terms of precision and recall. The findings indicate that time-resolved features could be added to enhance the classification performance without the necessity to use sophisticated sensor arrays. This paper demonstrates the integration of nanostructured sensing materials with machine learning for VOC classification using experimentally acquired sensor data. The experimentally acquired sensor data was used to validate the proposed framework under controlled laboratory conditions, demonstrating its feasibility for VOC classification

Refference:

I. Acharyya, S., K. Mondal, and S. Basu. “Single Resistive Sensor for Selective Detection of Multiple VOCs Employing SnO₂ Hollow Spheres and Machine Learning Algorithm: A Proof of Concept.” Sensors and Actuators B: Chemical, vol. 321, 2020, p. 128484. 10.1016/j.snb.2020.128484.
II. Banerjee, N., B. Bhowmik, S. Roy, C. K. Sarkar, and P. Bhattacharyya. “Anomalous Recovery Characteristics of Pd Modified ZnO Nanorod Based Acetone Sensor.” Journal of Nanoscience and Nanotechnology, vol. 13, no. 10, 2013, pp. 6826–6834. 10.1166/jnn.2013.7786.
III. Banerjee, N., S. Roy, C. K. Sarkar, and P. Bhattacharyya. “High Dynamic Range Methanol Sensor Based on Aligned ZnO Nanorods.” IEEE Sensors Journal, vol. 13, no. 5, 2013, pp. 1669–1676. 10.1109/JSEN.2013.2237822.
IV. Binson, V. A., N. A. A. Rahim, and R. Shahriman. “Non-Invasive Diagnosis of COPD with E-Nose Using XGBoost Algorithm.” Proceedings of the 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems. IEEE, 2021, pp. 297–301. 10.1109/ACCESS51619.2021.9563303.
V. Dalis, C. “Volatile Organic Compound Assessment as a Screening Tool for Early Detection of Gastrointestinal Diseases.” Microorganisms, vol. 11, no. 7, 2023, p. 1822. https://www.mdpi.com/2076-2607/11/7/1822.
VI. Fan, X., et al. “Exhaled VOC Detection in Lung Cancer Screening: A Comprehensive Meta-Analysis.” BMC Cancer, vol. 24, no. 1, 2024, p. 775. 10.1186/s12885-024-12537-7.
VII. Ghosh, R., and A. Talukdar. “Lung Disease Classification from Chest X-Ray Images Using Ensemble Learning.” 2024 IEEE Calcutta Conference (CALCON), Kolkata, India, 2024, pp. 1–5. 10.1109/CALCON63337.2024.10914228.
VIII. Hayasaka, T., et al. “An Electronic Nose Using a Single Graphene FET and Machine Learning for Water, Methanol, and Ethanol.” Microsystems & Nanoengineering, vol. 6, no. 1, 2020, pp. 1–9. 10.1038/s41378-020-0161-3.
IX. Itoh, T., Y. Koyama, W. Shin, T. Akamatsu, A. Tsuruta, Y. Masuda, and K. Uchiyama. “Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases.” Sensors, vol. 20, no. 9, 2020, p. 2687. 10.3390/s20092687.
X. Jaeschke, C., M. Klein, R. Götz, C. Schütze, and S. Zimmermann. “An Innovative Modular eNose System Based on a Unique Combination of Analog and Digital Metal Oxide Sensors.” ACS Sensors, vol. 4, 2019, pp. 2277–2281. 10.1021/acssensors.9b01244.
XI. Mei, H., J. Peng, T. Wang, et al. “Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor Array.” Nano-Micro Letters, vol. 16, 2024, p. 269. 10.1007/s40820-024-01489-z.
XII. Singh, S., S. S., P. Gajje, C. Adak, R. P. Shukla, and V. Kamble. “Metal Oxide-Based Gas Sensor Array for the VOCs Analysis in Complex Mixtures Using Machine Learning.” Sensors, vol. 23, no. 8, 2023, p. 1703. 10.3390/s23081703.
XIII. Venkatesh, C., K. Ramana, S. Y. Lakkisetty, S. S. Band, S. Agarwal, and A. Mosavi. “A Neural Network and Optimization Based Lung Cancer Detection System in CT Images.” Frontiers in Public Health, vol. 10, 2022, article 769692. 10.3389/fpubh.2022.769692.
XIV. Wang, H., S. Sun, J. Wang, and C. Zhao. “EEMD and GUCNN-XGBoost Joint Recognition Algorithm for Detection of Precursor Chemicals Based on Semiconductor Gas Sensor.” IEEE Transactions on Instrumentation and Measurement, vol. 71, 2022, pp. 1–12. 10.1109/TIM.2022.3197762.
XV. Wilson, A. D. “Developments of Recent Applications for Early Diagnosis of Diseases Using Electronic-Nose and Other VOC-Detection Devices.” Sensors, vol. 23, no. 18, 2023, p. 7885. https://www.mdpi.com/1424-8220/23/18/7885.
XVI. Wilson, A. D., and L. B. Forse. “Potential for Early Noninvasive COVID-19 Detection Using Electronic-Nose Technologies and Disease-Specific VOC Metabolic Biomarkers.” Sensors, vol. 23, no. 6, 2023, p. 2887. 10.3390/s23062887.
XVII. Zhang, T., Y. Cao, M. Chen, and L. Xie. “Recent Advances in CNTs-Based Sensors for Detecting the Quality and Safety of Food and Agro-Products.” Journal of Food Measurement and Characterization, vol. 17, no. 5, 2023, pp. 3061–3075. 10.1007/s11694-023-01850-7.

View Download