A feature extraction method for chemical sensors in electronic noses

L. Carmel; S. Levy; D. Lancet; D. Harel

doi:10.1016/S0925-4005(03)00247-8

A feature extraction method for chemical sensors in electronic noses

L. Carmel^*, S. Levy, D. Lancet, D. Harel

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

124 Scopus citations

Abstract

We propose a new feature extraction method for use with chemical sensors. It is based on fitting a parametric analytic model of the sensor's response over time to the measured signal, and taking the set of best-fitting parameters as the features. The process of finding the features is fast and robust, and the resulting set of features is shown to significantly enhance the performance of subsequent classification algorithms. Moreover, the model that we have developed fits equally well to sensors of different technologies and embeddings, suggesting its applicability to a diverse repertoire of sensors and analytic devices.

Original language	English
Pages (from-to)	67-76
Number of pages	10
Journal	Sensors and Actuators, B: Chemical
Volume	93
Issue number	1-3
DOIs	https://doi.org/10.1016/S0925-4005(03)00247-8
State	Published - 1 Aug 2003
Externally published	Yes
Event	Proceedings of the Ninth International Meeting on Chemical Engineering - Boston, MA, United States Duration: 7 Jul 2003 → 10 Jul 2003

Keywords

Curve fitting
Electronic nose
Feature extraction
Metal-oxide sensors
Quartz-microbalance sensors

Access to Document

10.1016/S0925-4005(03)00247-8

Cite this

@article{6883a5d5e8884b4b9804ee612995a4e8,

title = "A feature extraction method for chemical sensors in electronic noses",

abstract = "We propose a new feature extraction method for use with chemical sensors. It is based on fitting a parametric analytic model of the sensor's response over time to the measured signal, and taking the set of best-fitting parameters as the features. The process of finding the features is fast and robust, and the resulting set of features is shown to significantly enhance the performance of subsequent classification algorithms. Moreover, the model that we have developed fits equally well to sensors of different technologies and embeddings, suggesting its applicability to a diverse repertoire of sensors and analytic devices.",

keywords = "Curve fitting, Electronic nose, Feature extraction, Metal-oxide sensors, Quartz-microbalance sensors",

author = "L. Carmel and S. Levy and D. Lancet and D. Harel",

year = "2003",

month = aug,

day = "1",

doi = "10.1016/S0925-4005(03)00247-8",

language = "אנגלית",

volume = "93",

pages = "67--76",

journal = "Sensors and Actuators, B: Chemical",

issn = "0925-4005",

publisher = "Elsevier B.V.",

number = "1-3",

note = "Proceedings of the Ninth International Meeting on Chemical Engineering ; Conference date: 07-07-2003 Through 10-07-2003",

}

TY - JOUR

T1 - A feature extraction method for chemical sensors in electronic noses

AU - Carmel, L.

AU - Levy, S.

AU - Lancet, D.

AU - Harel, D.

PY - 2003/8/1

Y1 - 2003/8/1

N2 - We propose a new feature extraction method for use with chemical sensors. It is based on fitting a parametric analytic model of the sensor's response over time to the measured signal, and taking the set of best-fitting parameters as the features. The process of finding the features is fast and robust, and the resulting set of features is shown to significantly enhance the performance of subsequent classification algorithms. Moreover, the model that we have developed fits equally well to sensors of different technologies and embeddings, suggesting its applicability to a diverse repertoire of sensors and analytic devices.

AB - We propose a new feature extraction method for use with chemical sensors. It is based on fitting a parametric analytic model of the sensor's response over time to the measured signal, and taking the set of best-fitting parameters as the features. The process of finding the features is fast and robust, and the resulting set of features is shown to significantly enhance the performance of subsequent classification algorithms. Moreover, the model that we have developed fits equally well to sensors of different technologies and embeddings, suggesting its applicability to a diverse repertoire of sensors and analytic devices.

KW - Curve fitting

KW - Electronic nose

KW - Feature extraction

KW - Metal-oxide sensors

KW - Quartz-microbalance sensors

UR - http://www.scopus.com/inward/record.url?scp=0038450265&partnerID=8YFLogxK

U2 - 10.1016/S0925-4005(03)00247-8

DO - 10.1016/S0925-4005(03)00247-8

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:0038450265

SN - 0925-4005

VL - 93

SP - 67

EP - 76

JO - Sensors and Actuators, B: Chemical

JF - Sensors and Actuators, B: Chemical

IS - 1-3

T2 - Proceedings of the Ninth International Meeting on Chemical Engineering

Y2 - 7 July 2003 through 10 July 2003

ER -

A feature extraction method for chemical sensors in electronic noses

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this