Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization

Tommy Sonne Alstrøm, Kasper Bayer Frøhling, Jan Larsen, Mikkel Nørgaard Schmidt, Michael Bache, Michael Stenbæk Schmidt, Mogens Havsteen Jakobsen, Anja Boisen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Due to applications in areas such as diagnostics and environmental safety, detection of molecules at very low concentrations has attracted recent attention. A powerful tool for this is Surface Enhanced Raman Spectroscopy (SERS) where substrates form localized areas of electromagnetic “hot spots” where the signal-to-noise (SNR) ratio is greatly amplified. However, at low concentrations hot spots with target molecules bound are rare. Furthermore, traditional detection relies on having uncontaminated sensor readings which is unrealistic in a real world detection setting. In this paper, we propose a Bayesian Non-negative Matrix Factorization (NMF) approach to identify locations of target molecules. The proposed method is able to successfully analyze the spectra and extract the target spectrum. A visualization of the loadings of the basis vector is created and the results show a clear SNR enhancement. Compared to traditional data processing, the NMF approach enables a more reproducible and sensitive sensor.
Original languageEnglish
Title of host publicationProceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
EditorsMamadou Mboup, Tülay Adali , Éric Moreau, Jan Larsen
Number of pages6
PublisherIEEE
Publication date2014
ISBN (Print)978-1-4799-3694-6
DOIs
Publication statusPublished - 2014
Event24th IEEE International Workshop on Machine Learning for Signal Processing - Reims Centre des Congrès, Reims, France
Duration: 21 Sep 201424 Sep 2014
Conference number: 24
http://mlsp2014.conwiz.dk/home.htm
http://mlsp2014.conwiz.dk/home.htm

Conference

Conference24th IEEE International Workshop on Machine Learning for Signal Processing
Number24
LocationReims Centre des Congrès
CountryFrance
CityReims
Period21/09/201424/09/2014
Internet address

Keywords

  • Bioengineering
  • Communication, Networking and Broadcast Technologies
  • Computing and Processing
  • Engineering Profession
  • Signal Processing and Analysis
  • 17β-Estradiol
  • Abstracts
  • Biosensing
  • Non-negative Matrix Factorization (NMF)
  • Spectroscopy
  • Surface Enhanced Raman Spectroscopy (SERS)
  • Unsupervised Learning

Cite this

Alstrøm, T. S., Frøhling, K. B., Larsen, J., Schmidt, M. N., Bache, M., Schmidt, M. S., ... Boisen, A. (2014). Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization. In M. Mboup, T. Adali , É. Moreau, & J. Larsen (Eds.), Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) IEEE. https://doi.org/10.1109/MLSP.2014.6958925
Alstrøm, Tommy Sonne ; Frøhling, Kasper Bayer ; Larsen, Jan ; Schmidt, Mikkel Nørgaard ; Bache, Michael ; Schmidt, Michael Stenbæk ; Jakobsen, Mogens Havsteen ; Boisen, Anja. / Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization. Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) . editor / Mamadou Mboup ; Tülay Adali ; Éric Moreau ; Jan Larsen. IEEE, 2014.
@inproceedings{675670024fbd4b9ca416122723769219,
title = "Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization",
abstract = "Due to applications in areas such as diagnostics and environmental safety, detection of molecules at very low concentrations has attracted recent attention. A powerful tool for this is Surface Enhanced Raman Spectroscopy (SERS) where substrates form localized areas of electromagnetic “hot spots” where the signal-to-noise (SNR) ratio is greatly amplified. However, at low concentrations hot spots with target molecules bound are rare. Furthermore, traditional detection relies on having uncontaminated sensor readings which is unrealistic in a real world detection setting. In this paper, we propose a Bayesian Non-negative Matrix Factorization (NMF) approach to identify locations of target molecules. The proposed method is able to successfully analyze the spectra and extract the target spectrum. A visualization of the loadings of the basis vector is created and the results show a clear SNR enhancement. Compared to traditional data processing, the NMF approach enables a more reproducible and sensitive sensor.",
keywords = "Bioengineering, Communication, Networking and Broadcast Technologies, Computing and Processing, Engineering Profession, Signal Processing and Analysis, 17β-Estradiol, Abstracts, Biosensing, Non-negative Matrix Factorization (NMF), Spectroscopy, Surface Enhanced Raman Spectroscopy (SERS), Unsupervised Learning",
author = "Alstr{\o}m, {Tommy Sonne} and Fr{\o}hling, {Kasper Bayer} and Jan Larsen and Schmidt, {Mikkel N{\o}rgaard} and Michael Bache and Schmidt, {Michael Stenb{\ae}k} and Jakobsen, {Mogens Havsteen} and Anja Boisen",
year = "2014",
doi = "10.1109/MLSP.2014.6958925",
language = "English",
isbn = "978-1-4799-3694-6",
editor = "Mboup, {Mamadou } and {Adali }, {T{\"u}lay } and Moreau, {{\'E}ric } and Jan Larsen",
booktitle = "Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)",
publisher = "IEEE",
address = "United States",

}

Alstrøm, TS, Frøhling, KB, Larsen, J, Schmidt, MN, Bache, M, Schmidt, MS, Jakobsen, MH & Boisen, A 2014, Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization. in M Mboup, T Adali , É Moreau & J Larsen (eds), Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) . IEEE, 24th IEEE International Workshop on Machine Learning for Signal Processing, Reims, France, 21/09/2014. https://doi.org/10.1109/MLSP.2014.6958925

Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization. / Alstrøm, Tommy Sonne; Frøhling, Kasper Bayer; Larsen, Jan; Schmidt, Mikkel Nørgaard; Bache, Michael; Schmidt, Michael Stenbæk; Jakobsen, Mogens Havsteen; Boisen, Anja.

Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) . ed. / Mamadou Mboup; Tülay Adali ; Éric Moreau; Jan Larsen. IEEE, 2014.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization

AU - Alstrøm, Tommy Sonne

AU - Frøhling, Kasper Bayer

AU - Larsen, Jan

AU - Schmidt, Mikkel Nørgaard

AU - Bache, Michael

AU - Schmidt, Michael Stenbæk

AU - Jakobsen, Mogens Havsteen

AU - Boisen, Anja

PY - 2014

Y1 - 2014

N2 - Due to applications in areas such as diagnostics and environmental safety, detection of molecules at very low concentrations has attracted recent attention. A powerful tool for this is Surface Enhanced Raman Spectroscopy (SERS) where substrates form localized areas of electromagnetic “hot spots” where the signal-to-noise (SNR) ratio is greatly amplified. However, at low concentrations hot spots with target molecules bound are rare. Furthermore, traditional detection relies on having uncontaminated sensor readings which is unrealistic in a real world detection setting. In this paper, we propose a Bayesian Non-negative Matrix Factorization (NMF) approach to identify locations of target molecules. The proposed method is able to successfully analyze the spectra and extract the target spectrum. A visualization of the loadings of the basis vector is created and the results show a clear SNR enhancement. Compared to traditional data processing, the NMF approach enables a more reproducible and sensitive sensor.

AB - Due to applications in areas such as diagnostics and environmental safety, detection of molecules at very low concentrations has attracted recent attention. A powerful tool for this is Surface Enhanced Raman Spectroscopy (SERS) where substrates form localized areas of electromagnetic “hot spots” where the signal-to-noise (SNR) ratio is greatly amplified. However, at low concentrations hot spots with target molecules bound are rare. Furthermore, traditional detection relies on having uncontaminated sensor readings which is unrealistic in a real world detection setting. In this paper, we propose a Bayesian Non-negative Matrix Factorization (NMF) approach to identify locations of target molecules. The proposed method is able to successfully analyze the spectra and extract the target spectrum. A visualization of the loadings of the basis vector is created and the results show a clear SNR enhancement. Compared to traditional data processing, the NMF approach enables a more reproducible and sensitive sensor.

KW - Bioengineering

KW - Communication, Networking and Broadcast Technologies

KW - Computing and Processing

KW - Engineering Profession

KW - Signal Processing and Analysis

KW - 17β-Estradiol

KW - Abstracts

KW - Biosensing

KW - Non-negative Matrix Factorization (NMF)

KW - Spectroscopy

KW - Surface Enhanced Raman Spectroscopy (SERS)

KW - Unsupervised Learning

U2 - 10.1109/MLSP.2014.6958925

DO - 10.1109/MLSP.2014.6958925

M3 - Article in proceedings

SN - 978-1-4799-3694-6

BT - Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

A2 - Mboup, Mamadou

A2 - Adali , Tülay

A2 - Moreau, Éric

A2 - Larsen, Jan

PB - IEEE

ER -

Alstrøm TS, Frøhling KB, Larsen J, Schmidt MN, Bache M, Schmidt MS et al. Improving the robustness of Surface Enhanced Raman Spectroscopy based sensors by Bayesian Non-negative Matrix Factorization. In Mboup M, Adali T, Moreau É, Larsen J, editors, Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) . IEEE. 2014 https://doi.org/10.1109/MLSP.2014.6958925