Detail publikačního výsledku

Electronic Nose Odor Classification with Advanced Decision Tree Structures

GÜNEY, S.; ATASOY, A.; BURGET, R.

Originální název

Electronic Nose Odor Classification with Advanced Decision Tree Structures

Anglický název

Electronic Nose Odor Classification with Advanced Decision Tree Structures

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

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.

Klíčová slova

Electronic nose, odor classification, machine learning, data-mining.

Klíčová slova v angličtině

Electronic nose, odor classification, machine learning, data-mining.

Autoři

GÜNEY, S.; ATASOY, A.; BURGET, R.

Rok RIV

2014

Vydáno

31.08.2013

ISSN

1210-2512

Periodikum

Radioengineering

Svazek

2011

Číslo

1

Stát

Česká republika

Strany od

1

Strany do

9

Strany počet

9

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"
}