Evaluation of Classification Methods for Identifying Multiwalled Carbon Nanotubes Collected on Mixed Cellulose Ester Filter Media

Details

• Personal Author:
  Brenner SA ; Eastlake AC ; Neu-Baker NM ; Smith, Denise L. ; Zurbenko IG
• Description:
  Enhanced darkfield microscopy (EDFM) and hyperspectral imaging (HSI) are being evaluated as a potential rapid screening modality to reduce the time-to-knowledge for direct visualization and analysis of filter media used to sample nanoparticulate from work environments, as compared to the current analytical gold standard of transmission electron microscopy (TEM). Here, we compare accuracy, specificity, and sensitivity of several hyperspectral classification models and data pre-processing techniques to determine how to most effectively identify multi-walled carbon nanotubes (MWCNTs) in hyperspectral images. Several classification schemes were identified that are capable of classifying pixels as MWCNT(+) or MWCNT(-) in hyperspectral images with specificity and sensitivity over 99% on the test dataset. Functional principal component analysis (FPCA) was identified as an appropriate data pre-processing technique, testing optimally when coupled with a quadratic discriminant analysis (QDA) model with forward stepwise variable selection and with a support vector machines (SVM) model. The success of these methods suggests that EDFM-HSI may be reliably employed to assess filter media exposed to MWCNTs. Future work will evaluate the ability of EDFM-HSI to quantify MWCNTs collected on filter media using this classification algorithm framework using the best-performing model identified here - quadratic discriminant analysis with forward stepwise selection on functional principal component data - on an expanded sample set. [Description provided by NIOSH]
• Subjects:
  Occupational Exposure Occupational Health Safety
• Keywords:
  Algorithms Author Keywords: Hyperspectral Imaging Exposure Assessment Imaging Techniques Microscopy Multi-walled Carbon Nanotubes MWCNT Nanotechnology Occupational Exposure Occupational Exposure Assessment Predictive Modeling Sampling Equipment

  More +
• ISSN:
  0022-2720
• Document Type:
  Text
• Funding:
  Contract
• Genre:
  Journal Article
• Place as Subject:
  Massachusetts ; New York ; Ohio ; OSHA Region 1 ; OSHA Region 2 ; OSHA Region 5
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  DSI - Division of Science Integration
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  102-116
• Volume:
  283
• Issue:
  2
• NIOSHTIC Number:
  nn:20062526
• Citation:
  J Microsc 2021 Aug; 283(2):102-116
• Contact Point Address:
  Nicole Neu-Baker, MPH, CPH, State University of New York (SUNY) Polytechnic Institute, College of Nanoscale Science & Engineering, 257 Fuller Road, Albany, New York 12203, USA
• Email:
  nneu@sunypoly.edu
• Federal Fiscal Year:
  2021
• NORA Priority Area:
  Manufacturing
• Peer Reviewed:
  True
• Source Full Name:
  Journal of Microscopy
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:84b9a7d43b371e3bbb9c7e72114bd55a1a903e966ac5cef055aef00c32eb7c8ea1c455b84fa3f5a4251900a6f6891e356ca7017808ab62479accf61d9a972eb7
• Download URL:
  https://stacks.cdc.gov/view/cdc/225758/cdc_225758_DS1.pdf
• File Type:
  [PDF - 1.36 MB ]