Scalable Multiplexed Machine Learning Gas Sensor Chips for Food Classification

Carla Bassil and Ali Javey

EECS Department, University of California, Berkeley

Technical Report No. UCB/

December 1, 2025

This publication is archived. It is kept only for reference purposes, so it is no longer being updated and may not meet accessibility standards. If you need this content in a different format, please email webteam@eecs.berkeley.edu.

Multiplexed gas sensor arrays combined with machine learning have opened new avenues for scent-based sensing. Current platforms are limited by overlapping sensing materials with similar compositions, leading to highly correlated responses, or multi-step deposition processes that hinder scalability. In this work, we demonstrate 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 micro-dispensing method compatible with automated pipetting systems. The resulting chip produces unique signal patterns in response to object-specific scent profiles and when combined with machine learning algorithms, can perform automated object identification. As an example, we demonstrate the classification of 16 different objects, including food spoilage and nut allergens with an overall prediction accuracy of 92.6%.

Advisors: Ali Javey

BibTeX citation:

@mastersthesis{Bassil:32032,
    Author= {Bassil, Carla and Javey, Ali},
    Title= {Scalable Multiplexed Machine Learning Gas Sensor Chips for Food Classification},
    School= {EECS Department, University of California, Berkeley},
    Year= {2025},
    Month= {Dec},
    Number= {UCB/},
    Abstract= {Multiplexed gas sensor arrays combined with machine learning have opened new avenues for scent-based sensing. Current platforms are limited by overlapping sensing materials with similar compositions, leading to highly correlated responses, or multi-step deposition processes that hinder scalability. In this work, we demonstrate 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 micro-dispensing method compatible with automated pipetting systems. The resulting chip produces unique signal patterns in response to object-specific scent profiles and when combined with machine learning algorithms, can perform automated object identification. As an example, we demonstrate the classification of 16 different objects, including food spoilage and nut allergens with an overall prediction accuracy of 92.6%.},
}

EndNote citation:

%0 Thesis
%A Bassil, Carla 
%A Javey, Ali 
%T Scalable Multiplexed Machine Learning Gas Sensor Chips for Food Classification
%I EECS Department, University of California, Berkeley
%D 2025
%8 December 1
%@ UCB/
%F Bassil:32032