Deep Learning Characterization of Volatile Organic Compounds with Spectrometer-on-Card

Ander Cejudo, Ander Cejudo, Markel Arrojo, Miriam Gutiérrez, Miriam Gutiérrez, Karen López-Linares, Karen López-Linares, Hossam Haick, Iván Macía, Iván Macía, Iván Macía, Cristina Martín, Cristina Martín, Cristina Martín

2025

Abstract

The exposome encompasses all environmental exposures that affect internal biological processes throughout a person’s life, influencing health outcomes. Among these exposures, volatile organic compounds (VOCs) are particularly significant, as they are closely related to respiratory issues, cardiovascular diseases, cancer, and other health conditions. Detecting some of them is therefore critical for assessing environmental impacts on health. In this study, we use a low-cost, highly portable SPectrometer-On-Card (SPOC) device designed to characterize complex mixtures by separating VOCs through its layers. The device was previously tested to detect VOCs in controlled laboratory conditions. Hereby, we explore artificial intelligence algorithms to identify patterns in the signals captured by the SPOC in closer to real-word conditions. Specifically, we focus on two different use cases including direct exposure to a VOC source and indoors versus outdoors signal recognition. Our top-performing model, a recurrent neural network, achieves accuracies of 92,4% and 97,2% for each use case, respectively, effectively identifying exposures in the first case and correctly classifying 87,5% of exposures in the second. These results demonstrate the potential of our methodology applied to SPOC data for broader health-related applications, such as detecting incomplete combustions, identifying diseases like cancer through exhaled breath, and detecting leaks from industrial plants.

Paper Citation

in Harvard Style

Cejudo A., Arrojo M., Gutiérrez M., López-Linares K., Haick H., Macía I. and Martín C. (2025). Deep Learning Characterization of Volatile Organic Compounds with Spectrometer-on-Card. In Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE; ISBN 978-989-758-743-6, SciTePress, pages 197-207. DOI: 10.5220/0013210300003938

in Bibtex Style

@conference{ict4awe25,
author={Ander Cejudo and Markel Arrojo and Miriam Gutiérrez and Karen López-Linares and Hossam Haick and Iván Macía and Cristina Martín},
title={Deep Learning Characterization of Volatile Organic Compounds with Spectrometer-on-Card},
booktitle={Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE},
year={2025},
pages={197-207},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013210300003938},
isbn={978-989-758-743-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE
TI - Deep Learning Characterization of Volatile Organic Compounds with Spectrometer-on-Card
SN - 978-989-758-743-6
AU - Cejudo A.
AU - Arrojo M.
AU - Gutiérrez M.
AU - López-Linares K.
AU - Haick H.
AU - Macía I.
AU - Martín C.
PY - 2025
SP - 197
EP - 207
DO - 10.5220/0013210300003938
PB - SciTePress