• DocumentCode
    14074
  • Title

    Machine Learning for Nanomaterial Toxicity Risk Assessment

  • Author

    Gernand, Jeremy M. ; Casman, Elizabeth A.

  • Volume
    29
  • Issue
    3
  • fYear
    2014
  • fDate
    May-June 2014
  • Firstpage
    84
  • Lastpage
    88
  • Abstract
    Many questions about the mechanisms of nanomaterial toxicity are unanswered and an applicable general theory of nanomaterial toxicity doesn´t seem to be on the horizon. To help with this problem, the authors use machine learning algorithms with quantitative analytical capabilities in a meta-analysis of carbon nanotube pulmonary toxicity studies. Such analyses can identify the material varieties most likely to be the riskiest and guide future development towards those most likely to pose the least risk.
  • Keywords
    carbon nanotubes; learning (artificial intelligence); risk management; toxicology; carbon nanotube pulmonary toxicity studies; machine learning algorithms; material varieties; meta-analysis; nanomaterial toxicity risk assessment; quantitative analytical capabilities; Carbon nanotubes; Learning systems; Machine learning; Nanobioscience; Nanomaterials; Proteins; industrial health; intelligent systems; machine learning; meta-analysis; nanomaterial toxicity; risk assessment; safety management;
  • fLanguage
    English
  • Journal_Title
    Intelligent Systems, IEEE
  • Publisher
    ieee
  • ISSN
    1541-1672
  • Type

    jour

  • DOI
    10.1109/MIS.2014.48
  • Filename
    6871719