Abstract
Urban search and rescue (USAR) operations require sensing modalities that remain effective under conditions where visibility-dependent techniques are degraded by dust, smoke, debris, or occlusion. This work presents a presence-gated volatile organic compound (VOC) sensing approach intended to support triage decisions in USAR scenarios. The system combines an actively sampled metal-oxide gas sensor array with environmental compensation and embedded inference, while a 24 GHz FMCW radar is used to verify human presence through micro-motion cues and suppress chemistry-only false alarms. The sensing pipeline is designed for microcontroller-class execution, employing deterministic timing, duty-cycled operation, and compact feature extraction suitable for resource-constrained platforms. Offline evaluation was conducted using tethered data collection to assess instrument-level separability across controlled exposure conditions, including fresh air, surrogate injury-related VOC mixtures, and reference gases. Results are reported in terms of confusion matrices, ROC and precision–recall curves, and feature-importance analysis, emphasizing system behavior and feasibility rather than diagnostic performance. The findings demonstrate that presence-gated VOC sensing can provide a complementary information channel for USAR applications, while large-scale field validation and biological specificity remain topics for future investigation.
Similar content being viewed by others
Data availability
The datasets generated and/or analyzed during the current study are publicly available on Mendeley Data and can be accessed at https://data.mendeley.com/datasets/jfsgrp5kzc/2 (https://doi.org/10.17632/jfsgrp5kzc.2). Requests for additional information regarding the dataset should be directed to the corresponding author, Milon Selvam Dennison at milon.selvam@kiu.ac.ug.
Abbreviations
- ADC:
-
Analog to digital converter
- AP:
-
Average precision
- AUC:
-
Area under the curve
- CO:
-
Carbon monoxide
- CO2 :
-
Carbon dioxide
- CV:
-
Cross-validation
- eCO2 :
-
Equivalent carbon dioxide estimate
- ESP32:
-
Espressif ESP32 microcontroller
- EWMA:
-
Exponentially weighted moving average
- F1:
-
F1 score
- FMCW:
-
Frequency modulated continuous wave (radar)
- GDM:
-
Gas distribution mapping
- GPIO:
-
General purpose input/output
- H2S:
-
Hydrogen sulfide
- I/O:
-
Input/output
- IAQ:
-
Indoor air quality
- J48:
-
C4.5 decision tree (J48)
- LED:
-
Light emitting diode
- MCU:
-
Microcontroller unit
- mmWave:
-
Millimeter wave
- MOX:
-
Metal oxide (semiconductor)
- NDIR:
-
Non-dispersive infrared
- NH3 :
-
Ammonia
- OLED:
-
Organic light emitting diode
- OR:
-
Olfactory receptor
- OSL:
-
Odor source localization
- PAS:
-
Photoacoustic spectroscopy
- PC:
-
Personal computer
- PR:
-
Precision recall
- PSD:
-
Power spectral density
- PTR-MS:
-
Proton transfer reaction mass spectrometry
- Q15:
-
Q1.15 fixed-point format (16-bit signed; 1 integer bit, 15 fractional bits)
- RF:
-
Random forest (algorithm)
- RH:
-
Relative humidity
- RGB:
-
Red green blue (camera)
- ROC:
-
Receiver operating characteristic
- SBC:
-
Single-board computer
- SIFT-MS:
-
Selected ion flow tube mass spectrometry
- SLAM:
-
Simultaneous localization and mapping
- SNR:
-
Signal-to-noise ratio
- SVP:
-
Saturation vapor pressure
- TVOC:
-
Total volatile organic compounds
- UART:
-
Universal asynchronous receiver–transmitter
- UAV:
-
Unmanned aerial vehicle
- UGV:
-
Unmanned ground vehicle
- UI:
-
User interface
- USAR:
-
Urban search and rescue
- USB:
-
Universal serial bus
- UX:
-
User experience
- VOC:
-
Volatile organic compound
- Wi-Fi:
-
Wireless fidelity
- ppb:
-
Parts per billion
- ppm:
-
Parts per million
References
Güntner, A. T. et al. Sniffing entrapped humans with sensor arrays. Anal. Chem. 90, 4940–4945 (2018).
Sunnucks, E. J. et al. Performance of a novel electronic nose for the detection of volatile organic compounds relating to starvation or human decomposition post-mass disaster. Sensors 24, 5918 (2024).
Trimmer, C. et al. Genetic variation across the human olfactory receptor repertoire alters odor perception. Proc. Natl. Acad. Sci. U. S. A. 116, 9475–9480 (2019).
Malnic, B., Godfrey, P. A. & Buck, L. B. The human olfactory receptor gene family. Proc. Natl. Acad. Sci. U. S. A. 101, 2584–2589 (2004).
Amann, A. et al. The human volatilome: Volatile organic compounds (VOCs) in exhaled breath, skin emanations, urine, feces and saliva. J. Breath Res. 8, 034001 (2014).
Persaud, K. & Dodd, G. Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose. Nature 299, 352–355 (1982).
Geng, J., Mokhtarzadeh, A. A. & Ding, N. Biomimetic electronic nose for coffee detection based on nano sensor arrays and machine learning algorithms. In 2023 International Conference on the Cognitive Computing and Complex Data (ICCD) 181–184 (IEEE, Huaian, China, 2023). https://doi.org/10.1109/ICCD59681.2023.10420808.
Robbiani, S., Lotesoriere, B. J., Dellacà, R. L. & Capelli, L. Physical confounding factors affecting gas sensors response: A review on effects and compensation strategies for electronic nose applications. Chemosensors 11, 514 (2023).
Shi, Y., Shi, Y., Niu, H., Liu, J. & Sun, P. Structure optimization and data processing method of electronic nose bionic chamber for detecting ammonia emissions from livestock excrement fermentation. Sensors 24, 1628 (2024).
Yan, M. et al. Humidity compensation based on power-law response for MOS sensors to VOCs. Sens. Actuators B Chem. 334, 129601 (2021).
Chen, P. et al. Structure design and performance study of bionic electronic nasal cavity. Biomimetics 10, 555 (2025).
Prakash, S. et al. Is TinyML sustainable?. Commun. ACM 66, 68–77 (2023).
Huang, Y., Doh, I.-J. & Bae, E. Design and validation of a portable machine learning-based electronic nose. Sensors 21, 3923 (2021).
Rankin-Turner, S. & McMeniman, C. J. A headspace collection chamber for whole body volatilomics. Analyst 147, 5210–5222 (2022).
Reeves, N. et al. Volatile organic compounds in the early diagnosis of non-healing surgical wounds: A systematic review. World J. Surg. 46, 1669–1677 (2022).
Salinas Alvarez, C., Sierra-Sosa, D., Garcia-Zapirain, B., Yoder-Himes, D. & Elmaghraby, A. Detection of volatile compounds emitted by bacteria in wounds using gas sensors. Sensors 19, 1523 (2019).
Pei, T., Liao, T., Wan, X., Wang, B. & Hao, D. Spatial blind source estimation of respiratory rate and heart rate detection based on frequency-modulated continuous wave radar. Sensors 25, 1198 (2025).
Lee, H., Kim, B.-H., Park, J.-K. & Yook, J.-G. A novel vital-sign sensing algorithm for multiple subjects based on 24-GHz FMCW Doppler radar. Remote Sens. 11, 1237 (2019).
Sacco, G., Piuzzi, E., Pittella, E. & Pisa, S. An FMCW radar for localization and vital signs measurement for different chest orientations. Sensors 20, 3489 (2020).
Anyfantis, A. & Blionas, S. Design and Development of a mobile e-nose platform for real time victim localization in confined spaces during USaR operations. In 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) 1–6 (IEEE, Dubrovnik, Croatia, 2020). https://doi.org/10.1109/I2MTC43012.2020.9129247.
Burgués, J., Esclapez, M. D., Doñate, S. & Marco, S. RHINOS: A lightweight portable electronic nose for real-time odor quantification in wastewater treatment plants. iScience 24, 103371 (2021).
Meléndez, F. et al. Portable electronic nose based on digital and analog chemical sensors for 2,4,6-trichloroanisole discrimination. Sensors 22, 3453 (2022).
Domènech-Gil, G. et al. Electronic nose for improved environmental methane monitoring. Environ. Sci. Technol. 58, 352–361 (2024).
Chen, Q. et al. A mobile E-Nose prototype for online breath analysis. Adv Sens Res 3, 2300018 (2024).
Xu, P. et al. Temperature and humidity compensation for MOS gas sensor based on random forests. In Intelligent Computing, Networked Control, and Their Engineering Applications (eds Yue, D. et al.) vol. 762 135–145 (Springer Singapore, Singapore, 2017).
Abdullah, A. N. et al. Correction model for metal oxide sensor drift caused by ambient temperature and humidity. Sensors 22, 3301 (2022).
Rajapakse, V., Karunanayake, I. & Ahmed, N. Intelligence at the extreme edge: A survey on reformable TinyML. ACM Comput. Surv. 55, 1–30 (2023).
Lee, J., Park, K. & Kim, Y. Deep learning-based device-free localization scheme for simultaneous estimation of indoor location and posture using FMCW radars. Sensors 22, 4447 (2022).
Lv, W., He, W., Lin, X. & Miao, J. Non-contact monitoring of human vital signs using FMCW millimeter wave radar in the 120 GHz band. Sensors 21, 2732 (2021).
Vergassola, M., Villermaux, E. & Shraiman, B. I. ‘Infotaxis’ as a strategy for searching without gradients. Nature 445, 406–409 (2007).
Gongora, A. et al. Information-driven gas distribution mapping for autonomous mobile robots. Sensors 23, 5387 (2023).
Francis, A., Li, S., Griffiths, C. & Sienz, J. Gas source localization and mapping with mobile robots: A review. J. Field Robotics 39, 1341–1373 (2022).
Li, B., Zhou, Q., Peng, S. & Liao, Y. Recent advances of SnO2-based sensors for detecting volatile organic compounds. Front. Chem. 8, 321 (2020).
Quinlan, J. R. Induction of decision trees. Mach. Learn. 1, 81–106 (1986).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32–35 (1950).
Bosch, S. et al. Electronic nose sensor drift affects diagnostic reliability and accuracy of disease-specific algorithms. Sensors 22, 9246 (2022).
Betty, C. A., Choudhury, S. & Girija, K. G. Discerning specific gas sensing at room temperature by ultrathin SnO2 films using impedance approach. Sensors Actuators B Chem. 173, 781–788 (2012).
Yan, J. et al. Electronic nose feature extraction methods: A review. Sensors 15, 27804–27831 (2015).
Guo, X. et al. A novel feature extraction approach using window function capturing and QPSO-SVM for enhancing electronic nose performance. Sensors 15, 15198–15217 (2015).
Fawcett, T. An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861–874 (2006).
Niculescu-Mizil, A. & Caruana, R. Predicting good probabilities with supervised learning. In Proceedings of the 22nd International Conference on Machine Learning - ICML ’05 625–632 (ACM Press, Bonn, Germany, 2005). https://doi.org/10.1145/1102351.1102430.
Vergara, L. & Salazar, A. On the optimum linear soft fusion of classifiers. Appl. Sci. 15, 5038 (2025).
Raschka, S. Model evaluation, model selection, and algorithm selection in machine learning. Preprint at https://doi.org/10.48550/ARXIV.1811.12808 (2018).
Rehman, S. U., Ali, A., Khan, A. M. & Okpala, C. Human activity recognition: A comparative study of validation methods and impact of feature extraction in wearable sensors. Algorithms 17, 556 (2024).
Acknowledgements
We extend our sincere gratitude to the Faculty of Mechanical and Materials Engineering and Faculty of Computer Science and Software Engineering at Huaiyin Institute of Technology for providing an enriching academic environment and invaluable resources.
Funding
This research received no external funding from any public or private agencies.
Author information
Authors and Affiliations
Contributions
Ervan N. Tanggono—Methodology, Software, Validation, Formal Analysis, Resources, Data Curation, Writing—Original Draft Preparation, Project Administration. Amir A. Mokhtarzadeh—Conceptualization, Software, Validation, Resources, Writing—Review & Editing, Supervision, Project Administration. Kaveendran Balasubramaniam—Validation, Resources, Supervision. Jing Pin Zou—Investigation, Data Curation, Visualization, Project Administration. Hera Naeem—Formal Analysis, Investigation, Visualization. Parvez Mosharof—Writing—Original Draft Preparation, Writing—Review & Editing, Visualization. Milon Selvam Dennison—Writing—Review & Editing. All authors have read and agreed to the published version of the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Tanggono, E.N., Mokhtarzadeh, A.A., Balasubramaniam, K. et al. Presence-gated VOC sensing for urban search and rescue applications. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40990-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40990-w
