Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network

Research output: Contribution to conferencePosterOther research output

Abstract

We demonstrate a machine learning technique for data classification. In particular, we have classified Raman spectral data obtained from extracellular vesicles using a convolutional neural network (CNN).
In this research, 300 spectra from four types of EVs were divided into a training- (60%), validation- (20%) and testing-dataset (20%). Training was performed with the training set and the model is validated with validation set. After the training process, the predictive ability was evaluated with testing set which was not involved in any way during the learning process. We show CNN trained on raw Raman spectra and CNN trained on baseline-corrected Raman data. Classified testing datasets show an accuracy in excess of 90%.
Original languageEnglish
Publication statusPublished - 30 Aug 2018
EventXXVI International Conference on Raman Spectroscopy, ICORS 2018 - International Convention Center Jeju, Jeju, Korea, Republic of
Duration: 26 Aug 201831 Aug 2018
Conference number: 26
http://www.icors2018.org

Conference

ConferenceXXVI International Conference on Raman Spectroscopy, ICORS 2018
Abbreviated titleICORS
CountryKorea, Republic of
CityJeju
Period26/08/1831/08/18
Internet address

Fingerprint

Raman scattering
Neural networks
Testing
Learning systems

Keywords

  • Raman Spectroscopy
  • Extracellular vesicles
  • Label-free biosensing
  • Machine Learning
  • Convolutional neural networks

Cite this

Lee, W., & Offerhaus, H. L. (2018). Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network. Poster session presented at XXVI International Conference on Raman Spectroscopy, ICORS 2018, Jeju, Korea, Republic of.
Lee, Wooje ; Offerhaus, H.L. . / Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network. Poster session presented at XXVI International Conference on Raman Spectroscopy, ICORS 2018, Jeju, Korea, Republic of.
@conference{873a499bebb04726bc43051619ba486e,
title = "Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network",
abstract = "We demonstrate a machine learning technique for data classification. In particular, we have classified Raman spectral data obtained from extracellular vesicles using a convolutional neural network (CNN). In this research, 300 spectra from four types of EVs were divided into a training- (60{\%}), validation- (20{\%}) and testing-dataset (20{\%}). Training was performed with the training set and the model is validated with validation set. After the training process, the predictive ability was evaluated with testing set which was not involved in any way during the learning process. We show CNN trained on raw Raman spectra and CNN trained on baseline-corrected Raman data. Classified testing datasets show an accuracy in excess of 90{\%}.",
keywords = "Raman Spectroscopy, Extracellular vesicles, Label-free biosensing, Machine Learning, Convolutional neural networks",
author = "Wooje Lee and H.L. Offerhaus",
year = "2018",
month = "8",
day = "30",
language = "English",
note = "XXVI International Conference on Raman Spectroscopy, ICORS 2018, ICORS ; Conference date: 26-08-2018 Through 31-08-2018",
url = "http://www.icors2018.org",

}

Lee, W & Offerhaus, HL 2018, 'Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network' XXVI International Conference on Raman Spectroscopy, ICORS 2018, Jeju, Korea, Republic of, 26/08/18 - 31/08/18, .

Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network. / Lee, Wooje ; Offerhaus, H.L. .

2018. Poster session presented at XXVI International Conference on Raman Spectroscopy, ICORS 2018, Jeju, Korea, Republic of.

Research output: Contribution to conferencePosterOther research output

TY - CONF

T1 - Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network

AU - Lee, Wooje

AU - Offerhaus, H.L.

PY - 2018/8/30

Y1 - 2018/8/30

N2 - We demonstrate a machine learning technique for data classification. In particular, we have classified Raman spectral data obtained from extracellular vesicles using a convolutional neural network (CNN). In this research, 300 spectra from four types of EVs were divided into a training- (60%), validation- (20%) and testing-dataset (20%). Training was performed with the training set and the model is validated with validation set. After the training process, the predictive ability was evaluated with testing set which was not involved in any way during the learning process. We show CNN trained on raw Raman spectra and CNN trained on baseline-corrected Raman data. Classified testing datasets show an accuracy in excess of 90%.

AB - We demonstrate a machine learning technique for data classification. In particular, we have classified Raman spectral data obtained from extracellular vesicles using a convolutional neural network (CNN). In this research, 300 spectra from four types of EVs were divided into a training- (60%), validation- (20%) and testing-dataset (20%). Training was performed with the training set and the model is validated with validation set. After the training process, the predictive ability was evaluated with testing set which was not involved in any way during the learning process. We show CNN trained on raw Raman spectra and CNN trained on baseline-corrected Raman data. Classified testing datasets show an accuracy in excess of 90%.

KW - Raman Spectroscopy

KW - Extracellular vesicles

KW - Label-free biosensing

KW - Machine Learning

KW - Convolutional neural networks

M3 - Poster

ER -

Lee W, Offerhaus HL. Classifying Raman Spectra of Extracellular Vesicles using a Convolutional Neural Network. 2018. Poster session presented at XXVI International Conference on Raman Spectroscopy, ICORS 2018, Jeju, Korea, Republic of.