Implementation of neural networks for the identification of single molecules

Benjamin P. Bowen, Allan Scruggs, Jörg Enderlein, Markus Sauer, Neal Woodbury

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The effectiveness of neural networks and the optimization of parameters for implementing neural networks were evaluated for use in the identification of single molecules according to their fluorescence lifetime. The best network architecture and training parameters were determined for both ideal and nonideal single-molecule fluorescence data. The effectiveness of the neural network is compared to that of the maximum likelihood estimator on the basis of its ability to correctly identify single molecules. For ideal single-molecule data, it was found that the neural networks and the maximum likelihood estimator perform approximately equally well. For nonideal single-molecule fluorescence data, neural networks were able to correctly identify a larger percentage of single-molecule events than the MLE method.

Original languageEnglish (US)
Pages (from-to)4799-4804
Number of pages6
JournalJournal of Physical Chemistry A
Volume108
Issue number21
DOIs
StatePublished - May 27 2004

Fingerprint

Neural networks
Molecules
molecules
Fluorescence
estimators
fluorescence
Maximum likelihood
Maximum likelihood estimation
Network architecture
education
life (durability)
optimization

ASJC Scopus subject areas

  • Physical and Theoretical Chemistry

Cite this

Implementation of neural networks for the identification of single molecules. / Bowen, Benjamin P.; Scruggs, Allan; Enderlein, Jörg; Sauer, Markus; Woodbury, Neal.

In: Journal of Physical Chemistry A, Vol. 108, No. 21, 27.05.2004, p. 4799-4804.

Research output: Contribution to journalArticle

Bowen, Benjamin P. ; Scruggs, Allan ; Enderlein, Jörg ; Sauer, Markus ; Woodbury, Neal. / Implementation of neural networks for the identification of single molecules. In: Journal of Physical Chemistry A. 2004 ; Vol. 108, No. 21. pp. 4799-4804.
@article{6f7094d5871240df9a3bb8d0f1a0550d,
title = "Implementation of neural networks for the identification of single molecules",
abstract = "The effectiveness of neural networks and the optimization of parameters for implementing neural networks were evaluated for use in the identification of single molecules according to their fluorescence lifetime. The best network architecture and training parameters were determined for both ideal and nonideal single-molecule fluorescence data. The effectiveness of the neural network is compared to that of the maximum likelihood estimator on the basis of its ability to correctly identify single molecules. For ideal single-molecule data, it was found that the neural networks and the maximum likelihood estimator perform approximately equally well. For nonideal single-molecule fluorescence data, neural networks were able to correctly identify a larger percentage of single-molecule events than the MLE method.",
author = "Bowen, {Benjamin P.} and Allan Scruggs and J{\"o}rg Enderlein and Markus Sauer and Neal Woodbury",
year = "2004",
month = "5",
day = "27",
doi = "10.1021/jp036456v",
language = "English (US)",
volume = "108",
pages = "4799--4804",
journal = "Journal of Physical Chemistry A",
issn = "1089-5639",
publisher = "American Chemical Society",
number = "21",

}

TY - JOUR

T1 - Implementation of neural networks for the identification of single molecules

AU - Bowen, Benjamin P.

AU - Scruggs, Allan

AU - Enderlein, Jörg

AU - Sauer, Markus

AU - Woodbury, Neal

PY - 2004/5/27

Y1 - 2004/5/27

N2 - The effectiveness of neural networks and the optimization of parameters for implementing neural networks were evaluated for use in the identification of single molecules according to their fluorescence lifetime. The best network architecture and training parameters were determined for both ideal and nonideal single-molecule fluorescence data. The effectiveness of the neural network is compared to that of the maximum likelihood estimator on the basis of its ability to correctly identify single molecules. For ideal single-molecule data, it was found that the neural networks and the maximum likelihood estimator perform approximately equally well. For nonideal single-molecule fluorescence data, neural networks were able to correctly identify a larger percentage of single-molecule events than the MLE method.

AB - The effectiveness of neural networks and the optimization of parameters for implementing neural networks were evaluated for use in the identification of single molecules according to their fluorescence lifetime. The best network architecture and training parameters were determined for both ideal and nonideal single-molecule fluorescence data. The effectiveness of the neural network is compared to that of the maximum likelihood estimator on the basis of its ability to correctly identify single molecules. For ideal single-molecule data, it was found that the neural networks and the maximum likelihood estimator perform approximately equally well. For nonideal single-molecule fluorescence data, neural networks were able to correctly identify a larger percentage of single-molecule events than the MLE method.

UR - http://www.scopus.com/inward/record.url?scp=2942616713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942616713&partnerID=8YFLogxK

U2 - 10.1021/jp036456v

DO - 10.1021/jp036456v

M3 - Article

AN - SCOPUS:2942616713

VL - 108

SP - 4799

EP - 4804

JO - Journal of Physical Chemistry A

JF - Journal of Physical Chemistry A

SN - 1089-5639

IS - 21

ER -