• Real-Time Gas Identification a...

Treffer: Real-Time Gas Identification at Room Temperature Using UV-Modulated Sb-Doped SnO 2 Sensors via Machine Learning

Title:
Real-Time Gas Identification at Room Temperature Using UV-Modulated Sb-Doped SnO 2 Sensors via Machine Learning
Authors:
Yan-Fong Lin, Yu-Chen Chi, Sheng-Hong Tseng, Te-Fu Wang, Ying-Tsung Lin, Min-Ta Yang, Chih-Hao Lin, Su-Yu Liao, Chun-Ying Huang
Publication Year:
2025
Subject Terms:
Medicine, Space Science, Biological Sciences not elsewhere classified, Chemical Sciences not elsewhere classified, Physical Sciences not elsewhere classified, method exclusively employs, dimensional optical fingerprint, different illumination conditions, achieve nearly 100, uv light intensity, support vector machine, require multiple parameters, response monitoring systems, instantaneous response detection, gas response (<, five distinct levels, 3 , 2 , time gas identification, r <, gas discrimination, use uv, machine learning, dependent parameters, sensor response, study presents, sole metric, sensors combined, room temperature, reducing gases
Document Type:
Fachzeitschrift article in journal/newspaper
Language:
unknown
DOI:
10.1021/acssensors.5c01183.s001
Availability:
https://doi.org/10.1021/acssensors.5c01183.s001
https://figshare.com/articles/journal_contribution/Real-Time_Gas_Identification_at_Room_Temperature_Using_UV-Modulated_Sb-Doped_SnO_sub_2_sub_Sensors_via_Machine_Learning/29462985
Rights:
CC BY-NC 4.0
Accession Number:
edsbas.5FFE2CA9
Database:
BASE

Weitere Informationen

This study presents a novel approach for real-time gas identification at room temperature. We use UV-modulated Sb-doped SnO 2 sensors combined with machine learning. Our method exclusively employs the gas response ( R ) as the sole metric. This eliminates the need for time-dependent parameters such as response and recovery times. By modulating the UV light intensity at five distinct levels (5, 10, 15, 20, and 30 mW/cm 2 ), we generate a five-dimensional optical fingerprint. This fingerprint captures subtle variations in sensor response under different illumination conditions. Gas discrimination was evaluated for both oxidizing gases (O 3 and NO 2 ) and reducing gases (NH 3 and H 2 ). Our machine learning results show that Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) achieve nearly 100% accuracy when four UV intensity levels are used. Using R as the sole input metric allows for instantaneous response detection, which is essential for real-time gas identification. This approach addresses the limitations of conventional thermally activated sensors that require multiple parameters and paves the way for the development of rapid-response monitoring systems.