2011
DOI: 10.1016/j.snb.2011.05.042
|View full text |Cite
|
Sign up to set email alerts
|

A new feature extraction method for odour classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
12
0

Year Published

2012
2012
2019
2019

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 24 publications
(12 citation statements)
references
References 29 publications
0
12
0
Order By: Relevance
“…This procedure involves extracting certain significant characteristics from the sensor response curves (features) in order to produce a set of numerical data that can be processed by the recognition and classification system of the electronic nose [ 41 , 58 ]. Different features can be extracted and used depending on the characteristics of the electronic nose used such as, for example, the type of sensors adopted, and the stability of the responses of the latter to the reference gas, to variations in humidity and temperature levels [ 59 ].…”
Section: Electronic Nosesmentioning
confidence: 99%
See 1 more Smart Citation
“…This procedure involves extracting certain significant characteristics from the sensor response curves (features) in order to produce a set of numerical data that can be processed by the recognition and classification system of the electronic nose [ 41 , 58 ]. Different features can be extracted and used depending on the characteristics of the electronic nose used such as, for example, the type of sensors adopted, and the stability of the responses of the latter to the reference gas, to variations in humidity and temperature levels [ 59 ].…”
Section: Electronic Nosesmentioning
confidence: 99%
“…The methods for electronic nose data processing and classification (qualitative or quantitative) include specific algorithms, such as “K-Nearest Neighbors” (KNN) [ 66 ], “Discriminant Function Analysis” (DFA) [ 67 72 ], “Partial Last Squares Interpolation” (PLS) [ 73 ], or more complex systems, such as “Artificial Neural Networks” (ANN) [ 74 , 75 ] and Fuzzy Logic [ 59 , 76 ].…”
Section: Electronic Nosesmentioning
confidence: 99%
“…SVMs have been demonstrated to be a powerful learning method 38 and their use in the elds of electronic nose and tongue is gaining more importance every day. 23,39,40 SVMs were originally designed for binary clas-sication. Currently there are two types of approaches for multiclass SVMs.…”
Section: System Performance Evaluation and Development Of Classicatimentioning
confidence: 99%
“…The cross-sensitivity and broad spectrum characteristic of gas sensors array make the gas detection possible. In recent years, new publications on qualitative analysis of various gases using e-noses have been proposed by many researchers (D'Amico et al, 2010;Röck et al, 2008;Brudzewski et al, 2012;Güney and Atasoy, 2012;Cano et al, 2011;Ehret et al, 2011;Chen et al, 2011). However, concentration estimation for quantification analysis is always a challengeable task compared with qualitative analysis in e-nose.…”
Section: Introductionmentioning
confidence: 99%