Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikačního výsledku
GÜNEY, S.; ATASOY, A.; BURGET, R.
Originální název
Electronic Nose Odor Classification with Advanced Decision Tree Structures
Anglický název
Druh
Článek recenzovaný mimo WoS a Scopus
Originální abstrakt
Electronic nose (e-nose) is an electronic device which can measure chemical compounds in air and consequently classify different odors. In this paper, an e-nose device consisting of 8 different gas sensors was designed and constructed. Using this device, 104 different experiments involving 11 different odor classes (moth, angelica root, rose, mint, polis, lemon, rotten egg, egg, garlic, grass, and acetone) were performed. The main contribution of this paper is the finding that using the chemical domain knowledge it is possible to train an accurate odor classification system. The domain knowledge about chemical compounds is represented by a decision tree whose nodes are composed of classifiers such as Support Vector Machines and -Nearest Neighbor. The overall accuracy achieved with the proposed algorithm and the constructed e-nose device was 97.18 %. Training and testing data sets used in this paper are published online.
Anglický abstrakt
Klíčová slova
Electronic nose, odor classification, machine learning, data-mining.
Klíčová slova v angličtině
Autoři
Rok RIV
2014
Vydáno
31.08.2013
ISSN
1210-2512
Periodikum
Radioengineering
Svazek
2011
Číslo
1
Stát
Česká republika
Strany od
Strany do
9
Strany počet
BibTex
@article{BUT100907, author="Radim {Burget} and Ayten {Atasoy} and Selda {Güney}", title="Electronic Nose Odor Classification with Advanced Decision Tree Structures", journal="Radioengineering", year="2013", volume="2011", number="1", pages="1--9", issn="1210-2512" }