Skip to main navigation Skip to search Skip to main content

Simulation of the usage of Gaussian mixture models for the purpose of modelling virtual mass spectrometry data

  • Lublin University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

This article presents the method of the processing of mass spectrometry data. Mass spectra are modelled with Gaussian Mixture Models. Every peak of the spectrum is represented by a single Gaussian. Its parameters describe the location, height and width of the corresponding peak of the spectrum. An authorial version of the Expectation Maximisation Algorithm was used to perform all calculations. Errors were estimated with a virtual mass spectrometer. The discussed tool was originally designed to generate a set of spectra within defined parameters.

Original languageEnglish
Title of host publicationMedical Informatics in a United and Healthy Europe - Proceedings of MIE 2009
Subtitle of host publicationThe 22nd International Congress of the European Federation for Medical Informatics
PublisherIOS Press
Pages804-808
Number of pages5
ISBN (Print)9781607500445
DOIs
Publication statusPublished - 2009
Event22nd International Conference on Medical Informatics Europe, MIE 2009 - Sarajevo, Bosnia and Herzegovina
Duration: 30 Aug 20092 Sept 2009

Publication series

NameStudies in Health Technology and Informatics
Volume150
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference22nd International Conference on Medical Informatics Europe, MIE 2009
Country/TerritoryBosnia and Herzegovina
CitySarajevo
Period30/08/092/09/09

Keywords

  • Expectation maximization algorithm
  • GMM
  • Mass spectrometry

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Fingerprint

Dive into the research topics of 'Simulation of the usage of Gaussian mixture models for the purpose of modelling virtual mass spectrometry data'. Together they form a unique fingerprint.

Cite this