Number of the records: 1
A chemiresistive sensor array based on polyaniline nanocomposites and machine learning classification
- 1.
SYSNO ASEP 0566244 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title A chemiresistive sensor array based on polyaniline nanocomposites and machine learning classification Author(s) Kroutil, J. (CZ)
Laposa, A. (CZ)
Ahmad, A. (CZ)
Voves, J. (CZ)
Povolný, V. (CZ)
Klimša, Ladislav (FZU-D) ORCID
Davydova, Marina (FZU-D) RID, ORCID
Husák, M. (CZ)Number of authors 8 Source Title Beilstein Journal of Nanotechnology. - : Beilstein - Institut zur Foerderung der Chemischen Wissenschaften - ISSN 2190-4286
Roč. 13, April (2022), s. 411-423Number of pages 13 s. Language eng - English Country DE - Germany Keywords feature extraction ; gas sensor ; pattern recognition ; sensor array Subject RIV BM - Solid Matter Physics ; Magnetism OECD category Condensed matter physics (including formerly solid state physics, supercond.) R&D Projects GA22-04533S GA ČR - Czech Science Foundation (CSF) Research Infrastructure CzechNanoLab - 90110 - Vysoké učení technické v Brně Method of publishing Open access Institutional support FZU-D - RVO:68378271 UT WOS 000792480700001 EID SCOPUS 85130803268 DOI 10.3762/bjnano.13.34 Annotation The selective detection of ammonia (NH3), nitrogen dioxide (NO2), carbon oxides (CO2 and CO), acetone ((CH3)2CO), and toluene (C6H5CH3) is investigated by means of a gas sensor array based on polyaniline nanocomposites. The array composed by seven different conductive sensors with composite sensing layers are measured and analyzed using machine learning. Statistical tools, such as principal component analysis and linear discriminant analysis, are used as dimensionality reduction methods. Five different classification methods, namely k-nearest neighbors algorithm, support vector machine, random forest, decision tree classifier, and Gaussian process classification (GPC) are compared to evaluate the accuracy of target gas determination. We found the Gaussian process classification model trained on features extracted from the data by principal component analysis to be a highly accurate method reach to 99% of the classification of six different gases. Workplace Institute of Physics Contact Kristina Potocká, potocka@fzu.cz, Tel.: 220 318 579 Year of Publishing 2023 Electronic address https://hdl.handle.net/11104/0337633
Number of the records: 1