Publication result detail

Electronic Nose Odor Classification with Advanced Decision Tree Structures

GÜNEY, S.; ATASOY, A.; BURGET, R.

Original Title

Electronic Nose Odor Classification with Advanced Decision Tree Structures

English Title

Electronic Nose Odor Classification with Advanced Decision Tree Structures

Type

Peer-reviewed article not indexed in WoS or Scopus

Original Abstract

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.

English abstract

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.

Keywords

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

Key words in English

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

Authors

GÜNEY, S.; ATASOY, A.; BURGET, R.

RIV year

2014

Released

31.08.2013

ISBN

1210-2512

Periodical

Radioengineering

Volume

2011

Number

1

State

Czech Republic

Pages from

1

Pages to

9

Pages count

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"
}