Scalable multiplexed machine learning gas sensor chips for food classification
Science Advances · 2026
DOI: 10.1126/sciadv.aec7965 ↗At a glance
Journal article in Science Advances, 2026. Written by Carla Bassil and 10 co-authors. Institution: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA. Major MEDLINE topics: Machine Learning, Gases, Food Analysis, Biosensing Techniques. Cited 1 times so far (Crossref); 61 references. The full text is freely available in PubMed Central. Funded by: National Science Foundation, U.S. Department of Energy, Berkeley Sensors and Actuators Center.
Abstract (original language)
Multiplexed gas sensor arrays combined with machine learning have unlocked previously inaccessible applications for scent-based sensing. Current platforms are limited by overlapping sensing materials with similar compositions, leading to highly correlated responses, or multistep deposition processes that hinder scalability. In this work, we developed a 16-element monolithic chip with fully distinct sensing layers, enabling a truly heterogeneous array. The system consists of highly sensitive carbon nanotube field effect transistors that are functionalized through a single-step microdispensing method compatible with automated pipetting systems. The resulting chip produces characteristic signal patterns in response to object-specific scent profiles and, when combined with machine learning algorithms, can perform automated object identification. We demonstrate the classification of 16 different objects, including food spoilage and nut allergens, with a 92.6% overall prediction accuracy.
Subjects
MeSH terms (MEDLINE)
Substances
Authors and institutions
- Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA.
- Materials Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
- Berkeley Sensor and Actuator Center, University of California, Berkeley, CA, USA.
- Department of Mechanical Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Department of Materials Science and Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Kavli Energy NanoScience Institute, Berkeley, CA, USA.
ORCID profiles: Carla Bassil, Kichul Lee, Xun Liao, Yifei Zhan, Theodorus Jonathan Wijaya, Minhyun Kim, Il-Doo Kim, Inkyu Park, Ali Javey
Funding
- National Science Foundation
- U.S. Department of Energy
- Berkeley Sensors and Actuators Center
- Bakar Ignite Scholars Program
Cite
APA
Bassil, C., Lee, K., Liao, X., Krishnan, D., Zhan, Y., Wijaya, T. J., Hester, E., Kim, M., Kim, I. D., Park, I., & Javey, A. (2026). Scalable multiplexed machine learning gas sensor chips for food classification. Science Advances. https://doi.org/10.1126/sciadv.aec7965
Vancouver
Bassil C, Lee K, Liao X, Krishnan D, Zhan Y, Wijaya TJ, et al. Scalable multiplexed machine learning gas sensor chips for food classification. Science Advances. 2026. doi:10.1126/sciadv.aec7965
BibTeX
@article{Bassil2026,
author = {Bassil, Carla and Lee, Kichul and Liao, Xun and Krishnan, Divya and Zhan, Yifei and Wijaya, Theodorus Jonathan and Hester, Edward and Kim, Minhyun and Kim, Il-Doo and Park, Inkyu and Javey, Ali},
title = {Scalable multiplexed machine learning gas sensor chips for food classification},
journal = {Science Advances},
year = {2026},
doi = {10.1126/sciadv.aec7965}
}
EUVIMED