Application of machine learning models for data interpretation from an array of gas sensors

Kat-Kim Phan; Matthew Southworth; Varun Teja Kolluru; Rahul Rawat; Arash Takshi; Ehsan Sheybani

doi:10.1117/12.2677893

28 September 2023 Application of machine learning models for data interpretation from an array of gas sensors

Kat-Kim Phan, Matthew Southworth, Varun Teja Kolluru, Rahul Rawat, Arash Takshi, Ehsan Sheybani

Proceedings Volume 12661, Organic and Hybrid Sensors and Bioelectronics XVI; 1266102 (2023) https://doi.org/10.1117/12.2677893
Event: SPIE Organic Photonics + Electronics, 2023, San Diego, California, United States

Abstract

With the increasing demand in using electronic noses (e-noses) for various medical, industrial, and military applications, the technology of such devices is still struggling with the limitations in the gas sensors. Particularly, a limitation is in the relatively poor sensitivity and selectivity of the commercially available sensors for measuring the concentrations of various gases and volatile organic compounds (VOCs). The shortcoming has been addressed by employing machine learning (ML) methods to analyze signals from an array of gas sensors. However, with different ML models, it is required to study the effect of different models on data interpretation. In this study, we have designed a microcontroller-based system equipped with eight different gas/VOC sensors, designed for detecting CO₂, O₂, CO, NO, NO₂, NH₃, alcohol, and acetone. The sensors were tested with streams of air mixed with various VOCs including methanol, ethanol, and isopropanol at different flow rates. The collected data from the sensors were analyzed using PCA, LDA, and CNN methods for not only recognizing the signatures of different gases, but also differentiating between them and recognizing their ratio in a mixture. The results of the studies are promising for designing more effective hardware equipped with an ML modeling system to analyze the concentration of various gases and VOCs in a mixed situation.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Kat-Kim Phan, Matthew Southworth, Varun Teja Kolluru, Rahul Rawat, Arash Takshi, and Ehsan Sheybani "Application of machine learning models for data interpretation from an array of gas sensors", Proc. SPIE 12661, Organic and Hybrid Sensors and Bioelectronics XVI, 1266102 (28 September 2023); https://doi.org/10.1117/12.2677893

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available