Detail publikace

Electronic Nose Odor Classification with Advanced Decision Tree Structures

Originální název

Electronic Nose Odor Classification with Advanced Decision Tree Structures

Anglický název

Electronic Nose Odor Classification with Advanced Decision Tree Structures

Jazyk

en

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.

BibTex


@article{BUT100907,
  author="Radim {Burget} and Ayten {Atasoy} and Selda {Güney}",
  title="Electronic Nose Odor Classification with Advanced Decision Tree Structures",
  annote="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.",
  chapter="100907",
  number="1",
  volume="2011",
  year="2013",
  month="august",
  pages="1--9",
  type="journal article - other"
}