Electronic Nose Odor Classification with Advanced Decision Tree Structures
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 differ...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Spolecnost pro radioelektronicke inzenyrstvi
2013-09-01
|
Series: | Radioengineering |
Subjects: | |
Online Access: | http://www.radioeng.cz/fulltexts/2013/13_03_0874_0882.pdf |
id |
doaj-3fdef8b818a84bbe88fdac2a1f86ca6b |
---|---|
record_format |
Article |
spelling |
doaj-3fdef8b818a84bbe88fdac2a1f86ca6b2020-11-24T22:52:37ZengSpolecnost pro radioelektronicke inzenyrstviRadioengineering1210-25122013-09-01223874882Electronic Nose Odor Classification with Advanced Decision Tree StructuresS. GuneyA. AtasoyR. BurgetElectronic 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 k-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.www.radioeng.cz/fulltexts/2013/13_03_0874_0882.pdfElectronic nosesensor systemsmachine learningdata-mining |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
S. Guney A. Atasoy R. Burget |
spellingShingle |
S. Guney A. Atasoy R. Burget Electronic Nose Odor Classification with Advanced Decision Tree Structures Radioengineering Electronic nose sensor systems machine learning data-mining |
author_facet |
S. Guney A. Atasoy R. Burget |
author_sort |
S. Guney |
title |
Electronic Nose Odor Classification with Advanced Decision Tree Structures |
title_short |
Electronic Nose Odor Classification with Advanced Decision Tree Structures |
title_full |
Electronic Nose Odor Classification with Advanced Decision Tree Structures |
title_fullStr |
Electronic Nose Odor Classification with Advanced Decision Tree Structures |
title_full_unstemmed |
Electronic Nose Odor Classification with Advanced Decision Tree Structures |
title_sort |
electronic nose odor classification with advanced decision tree structures |
publisher |
Spolecnost pro radioelektronicke inzenyrstvi |
series |
Radioengineering |
issn |
1210-2512 |
publishDate |
2013-09-01 |
description |
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 k-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. |
topic |
Electronic nose sensor systems machine learning data-mining |
url |
http://www.radioeng.cz/fulltexts/2013/13_03_0874_0882.pdf |
work_keys_str_mv |
AT sguney electronicnoseodorclassificationwithadvanceddecisiontreestructures AT aatasoy electronicnoseodorclassificationwithadvanceddecisiontreestructures AT rburget electronicnoseodorclassificationwithadvanceddecisiontreestructures |
_version_ |
1725665379396616192 |