Data-driven modeling of nano-nose gas sensor arrays

Tommy Sonne Alstrøm; Jan Larsen; Claus Højgård Nielsen; Niels Bent Larsen

Data-driven modeling of nano-nose gas sensor arrays

Tommy Sonne Alstrøm, Jan Larsen, Claus Højgård Nielsen, Niels Bent Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

635 Downloads (Orbit)

Abstract

We present a data-driven approach to classification of Quartz Crystal Microbalance (QCM) sensor data. The sensor is a nano-nose gas sensor that detects concentrations of analytes down to ppm levels using plasma polymorized coatings. Each sensor experiment takes approximately one hour hence the number of available training data is limited. We suggest a data-driven classification model which work from few examples. The paper compares a number of data-driven classification and quantification schemes able to detect the gas and the concentration level. The data-driven approaches are based on state-of-the-art machine learning methods and the Bayesian learning paradigm.

Original language	English
Title of host publication	Signal Processing, Sensor Fusion, and Target Recognition Xix : Defense, Security and Sensing
Volume	7697
Place of Publication	Bellingham
Publisher	SPIE - International Society for Optical Engineering
Publication date	2010
Publication status	Published - 2010
Event	SPIE Defense, Security and Sensing 2010 - Orlando, United States Duration: 5 Apr 2010 → 9 Apr 2010

Conference

Conference	SPIE Defense, Security and Sensing 2010
Country/Territory	United States
City	Orlando
Period	05/04/2010 → 09/04/2010

Series	Proceedings of SPIE - The International Society for Optical Engineering
ISSN	0277-786X

Keywords

Concentration Level Estimation
Gaussian Process Regression (GPR)
Classification
Principal Component Analysis (PCA)
Polymer Coated Quartz Crystal Microbalance Sensor (QCM)
Non-negative Matrix Factorization (NMF)
Principal Component Regression (PCR)
Artificial Neural Network (ANN)

Access to Document

Article

OpenUrl availability

Full text

Cite this

Alstrøm, Tommy Sonne ; Larsen, Jan ; Nielsen, Claus Højgård et al. / Data-driven modeling of nano-nose gas sensor arrays. Signal Processing, Sensor Fusion, and Target Recognition Xix: Defense, Security and Sensing. Vol. 7697 Bellingham : SPIE - International Society for Optical Engineering, 2010. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{afa1f7c35ae9409cab2dc2e9761a7408,

title = "Data-driven modeling of nano-nose gas sensor arrays",

abstract = "We present a data-driven approach to classification of Quartz Crystal Microbalance (QCM) sensor data. The sensor is a nano-nose gas sensor that detects concentrations of analytes down to ppm levels using plasma polymorized coatings. Each sensor experiment takes approximately one hour hence the number of available training data is limited. We suggest a data-driven classification model which work from few examples. The paper compares a number of data-driven classification and quantification schemes able to detect the gas and the concentration level. The data-driven approaches are based on state-of-the-art machine learning methods and the Bayesian learning paradigm.",

keywords = "Concentration Level Estimation, Gaussian Process Regression (GPR), Classification, Principal Component Analysis (PCA), Polymer Coated Quartz Crystal Microbalance Sensor (QCM), Non-negative Matrix Factorization (NMF), Principal Component Regression (PCR), Artificial Neural Network (ANN)",

author = "Alstr{\o}m, \{Tommy Sonne\} and Jan Larsen and Nielsen, \{Claus H{\o}jg{\aa}rd\} and Larsen, \{Niels Bent\}",

year = "2010",

language = "English",

volume = "7697",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE - International Society for Optical Engineering",

booktitle = "Signal Processing, Sensor Fusion, and Target Recognition Xix",

note = "SPIE Defense, Security and Sensing 2010 ; Conference date: 05-04-2010 Through 09-04-2010",

}

Alstrøm, TS, Larsen, J, Nielsen, CH & Larsen, NB 2010, Data-driven modeling of nano-nose gas sensor arrays. in Signal Processing, Sensor Fusion, and Target Recognition Xix: Defense, Security and Sensing. vol. 7697, SPIE - International Society for Optical Engineering, Bellingham, Proceedings of SPIE - The International Society for Optical Engineering, SPIE Defense, Security and Sensing 2010, Orlando, Florida, United States, 05/04/2010.

Data-driven modeling of nano-nose gas sensor arrays. / Alstrøm, Tommy Sonne; Larsen, Jan; Nielsen, Claus Højgård et al.
Signal Processing, Sensor Fusion, and Target Recognition Xix: Defense, Security and Sensing. Vol. 7697 Bellingham: SPIE - International Society for Optical Engineering, 2010. (Proceedings of SPIE - The International Society for Optical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Data-driven modeling of nano-nose gas sensor arrays

AU - Alstrøm, Tommy Sonne

AU - Larsen, Jan

AU - Nielsen, Claus Højgård

AU - Larsen, Niels Bent

PY - 2010

Y1 - 2010

N2 - We present a data-driven approach to classification of Quartz Crystal Microbalance (QCM) sensor data. The sensor is a nano-nose gas sensor that detects concentrations of analytes down to ppm levels using plasma polymorized coatings. Each sensor experiment takes approximately one hour hence the number of available training data is limited. We suggest a data-driven classification model which work from few examples. The paper compares a number of data-driven classification and quantification schemes able to detect the gas and the concentration level. The data-driven approaches are based on state-of-the-art machine learning methods and the Bayesian learning paradigm.

AB - We present a data-driven approach to classification of Quartz Crystal Microbalance (QCM) sensor data. The sensor is a nano-nose gas sensor that detects concentrations of analytes down to ppm levels using plasma polymorized coatings. Each sensor experiment takes approximately one hour hence the number of available training data is limited. We suggest a data-driven classification model which work from few examples. The paper compares a number of data-driven classification and quantification schemes able to detect the gas and the concentration level. The data-driven approaches are based on state-of-the-art machine learning methods and the Bayesian learning paradigm.

KW - Concentration Level Estimation

KW - Gaussian Process Regression (GPR)

KW - Classification

KW - Principal Component Analysis (PCA)

KW - Polymer Coated Quartz Crystal Microbalance Sensor (QCM)

KW - Non-negative Matrix Factorization (NMF)

KW - Principal Component Regression (PCR)

KW - Artificial Neural Network (ANN)

M3 - Article in proceedings

VL - 7697

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Signal Processing, Sensor Fusion, and Target Recognition Xix

PB - SPIE - International Society for Optical Engineering

CY - Bellingham

T2 - SPIE Defense, Security and Sensing 2010

Y2 - 5 April 2010 through 9 April 2010

ER -

Data-driven modeling of nano-nose gas sensor arrays

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this