Přístupnostní navigace
E-application
Search Search Close
Publication result detail
GÜNEY, S.; ATASOY, A.; BURGET, R.
Original Title
Electronic Nose Odor Classification with Advanced Decision Tree Structures
English Title
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
Keywords
Electronic nose, odor classification, machine learning, data-mining.
Key words in English
Authors
RIV year
2014
Released
31.08.2013
ISBN
1210-2512
Periodical
Radioengineering
Volume
2011
Number
1
State
Czech Republic
Pages from
Pages to
9
Pages count
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" }