2026-06-17 カリフォルニア大学バークレー校（UCB）
The electronic nose contains 16 different gas-sensitive materials (small circles in the center) that each react to the gas molecules presented to it (left). The device records the reactions of each material and, using a machine learning model, learns which set of reactions are associated with a specific food or scent (right). Brandon Sánchez-Mejia/UC Berkeley
＜関連情報＞
- https://news.berkeley.edu/2026/06/17/the-nose-knows-electric-schnoz-can-smell-when-your-foods-gone-bad/
- https://www.science.org/doi/10.1126/sciadv.aec7965
食品分類用のスケーラブルな多重化機械学習ガスセンサーチップ Scalable multiplexed machine learning gas sensor chips for food classification
Carla Bassil, Kichul Lee, Xun Liao, Divya Krishnan, […] , and Ali Javey
Science Advances Published:17 Jun 2026
DOI:https://doi.org/10.1126/sciadv.aec7965
Abstract
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.
