An intensity-region driven multi-classifier scheme for improving the classification accuracy of proteomic MS-spectra.
Panagiotis BougioukosDimitris GlotsosDionisis A. CavourasAntonis DaskalakisIoannis KalatzisSpiros KostopoulosGeorge NikiforidisAnastasios BezerianosPublished in: Comput. Methods Programs Biomed. (2010)
Keyphrases
- mass spectra
- classification scheme
- selection scheme
- training data
- mass spectrometry
- linear classifiers
- classification process
- ovarian cancer
- decision trees
- support vector machine
- input image
- medical images
- training samples
- region of interest
- intensity distribution
- classifier ensemble
- neural network
- classification algorithm
- feature space
- feature selection