Independent component analysis of nanomechanical responses of cantilever arrays

Rick Archibald; Panos Datskos; Gerald Devault; Vincent Lamberti; Nickolay Lavrik; Don Noid; Michael Sepaniak; Pampa Dutta

doi:10.1016/j.aca.2006.11.007

Independent component analysis of nanomechanical responses of cantilever arrays

Rick Archibald, Panos Datskos, Gerald Devault, Vincent Lamberti, Nickolay Lavrik, Don Noid, Michael Sepaniak, Pampa Dutta

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

The ability to detect and identify chemical and biological elements in air or liquid environments is of far reaching importance. Performing this task using technology that minimally impacts the perceived environment is the ultimate goal. The development of functionalized cantilever arrays with nanomechanical sensing is an important step towards this goal. This report couples the feature extraction abilities of independent component analysis (ICA) and the classification techniques of neural networks to analyze the signals produced by microcantilever-array-based nanomechanical sensors. The unique capabilities of this analysis unleash the potential of this sensing technology to accurately identify chemical mixtures and concentrations. Furthermore, it is demonstrated that the knowledge of how the sensor array reacts to individual analytes in isolation is sufficient information to decode mixtures of analytes-a substantial benefit, significantly increasing the analytical utility of these sensing devices.

Original language	English
Pages (from-to)	101-105
Number of pages	5
Journal	Analytica Chimica Acta
Volume	584
Issue number	1
DOIs	https://doi.org/10.1016/j.aca.2006.11.007
State	Published - Feb 12 2007

Funding

R. Archibald would like to thank the Householder fellowship that is supported under the Mathematical, Information, and Computational Sciences Division; Office of Advanced Scientific Computing Research; U.S. Department of Energy (DE-AC05-00OR22725). We would also like to acknowledge support from the Defense Advanced Research Projects Agency. This work was partially supported by the Laboratory Director's Research and Development Program of ORNL. Additional support in part by U.S. Department of Energy, Basic Energy Sciences (DE-FG02-02ER15331) and the Environmental Protection Agency (EPA-83274001) under grants awarded to the University of Tennessee, Knoxville. Support was also provided by the Y-12 National Security Complex Plant Directed Research and Development program.

Keywords

Functionalized cantilever arrays
Independent component analysis
Nanomechanical sensors
Neural networks

Access to Document

10.1016/j.aca.2006.11.007

Cite this

@article{2cb0503b6c484035b866d96a92f04f4e,

title = "Independent component analysis of nanomechanical responses of cantilever arrays",

abstract = "The ability to detect and identify chemical and biological elements in air or liquid environments is of far reaching importance. Performing this task using technology that minimally impacts the perceived environment is the ultimate goal. The development of functionalized cantilever arrays with nanomechanical sensing is an important step towards this goal. This report couples the feature extraction abilities of independent component analysis (ICA) and the classification techniques of neural networks to analyze the signals produced by microcantilever-array-based nanomechanical sensors. The unique capabilities of this analysis unleash the potential of this sensing technology to accurately identify chemical mixtures and concentrations. Furthermore, it is demonstrated that the knowledge of how the sensor array reacts to individual analytes in isolation is sufficient information to decode mixtures of analytes-a substantial benefit, significantly increasing the analytical utility of these sensing devices.",

keywords = "Functionalized cantilever arrays, Independent component analysis, Nanomechanical sensors, Neural networks",

author = "Rick Archibald and Panos Datskos and Gerald Devault and Vincent Lamberti and Nickolay Lavrik and Don Noid and Michael Sepaniak and Pampa Dutta",

year = "2007",

month = feb,

day = "12",

doi = "10.1016/j.aca.2006.11.007",

language = "English",

volume = "584",

pages = "101--105",

journal = "Analytica Chimica Acta",

issn = "0003-2670",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Independent component analysis of nanomechanical responses of cantilever arrays

AU - Archibald, Rick

AU - Datskos, Panos

AU - Devault, Gerald

AU - Lamberti, Vincent

AU - Lavrik, Nickolay

AU - Noid, Don

AU - Sepaniak, Michael

AU - Dutta, Pampa

PY - 2007/2/12

Y1 - 2007/2/12

N2 - The ability to detect and identify chemical and biological elements in air or liquid environments is of far reaching importance. Performing this task using technology that minimally impacts the perceived environment is the ultimate goal. The development of functionalized cantilever arrays with nanomechanical sensing is an important step towards this goal. This report couples the feature extraction abilities of independent component analysis (ICA) and the classification techniques of neural networks to analyze the signals produced by microcantilever-array-based nanomechanical sensors. The unique capabilities of this analysis unleash the potential of this sensing technology to accurately identify chemical mixtures and concentrations. Furthermore, it is demonstrated that the knowledge of how the sensor array reacts to individual analytes in isolation is sufficient information to decode mixtures of analytes-a substantial benefit, significantly increasing the analytical utility of these sensing devices.

AB - The ability to detect and identify chemical and biological elements in air or liquid environments is of far reaching importance. Performing this task using technology that minimally impacts the perceived environment is the ultimate goal. The development of functionalized cantilever arrays with nanomechanical sensing is an important step towards this goal. This report couples the feature extraction abilities of independent component analysis (ICA) and the classification techniques of neural networks to analyze the signals produced by microcantilever-array-based nanomechanical sensors. The unique capabilities of this analysis unleash the potential of this sensing technology to accurately identify chemical mixtures and concentrations. Furthermore, it is demonstrated that the knowledge of how the sensor array reacts to individual analytes in isolation is sufficient information to decode mixtures of analytes-a substantial benefit, significantly increasing the analytical utility of these sensing devices.

KW - Functionalized cantilever arrays

KW - Independent component analysis

KW - Nanomechanical sensors

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=33846316307&partnerID=8YFLogxK

U2 - 10.1016/j.aca.2006.11.007

DO - 10.1016/j.aca.2006.11.007

M3 - Article

C2 - 17386591

AN - SCOPUS:33846316307

SN - 0003-2670

VL - 584

SP - 101

EP - 105

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

IS - 1

ER -

Independent component analysis of nanomechanical responses of cantilever arrays

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this