Quantitative analysis of multivariate data using artificial neural networks: a tutorial review and applications to the deconvolution of pyrolysis mass spectra

Zentralbl Bakteriol. 1996 Aug;284(4):516-39. doi: 10.1016/s0934-8840(96)80004-1.


The implementation of artificial neural networks (ANNs) to the analysis of multivariate data is reviewed, with particular reference to the analysis of pyrolysis mass spectra. The need for and benefits of multivariate data analysis are explained followed by a discussion of ANNs and their optimisation. Finally, an example of the use of ANNs for the quantitative deconvolution of the pyrolysis mass spectra of Staphylococcus aureus mixed with Escherichia coli is demonstrated.

Publication types

  • Research Support, Non-U.S. Gov't
  • Review

MeSH terms

  • Escherichia coli / classification*
  • Escherichia coli / isolation & purification
  • Humans
  • Mass Spectrometry*
  • Multivariate Analysis*
  • Neural Networks, Computer*
  • Staphylococcus aureus / classification*
  • Staphylococcus aureus / isolation & purification