Consensus-based identification of spectral signatures for classification of high-dimensional biomedical spectra. Pranckeviciene, E., Baumgartner, R., & Somorjai, R. In Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. August 23-26, Cambridge, UK., volume 2, pages 319–322, 2004. IEEE.
Consensus-based identification of spectral signatures for classification of high-dimensional biomedical spectra [link]Link  abstract   bibtex   
The identification of spectral signatures is crucial for the classification/profiling of biomedical spectra. Because only limited number of biomedical samples of high dimensionality is typically available, dimensionality reduction techniques (identification of discriminatory features) are essential for robust classifier development. We show, on three real-world biomedical datasets, the potential of a consensus-based identification of important feature subsets, using a genetic algorithm and a sparse linear classifier. When training data are in short supply, the proposed methodology leads to more stable subset identification and higher classification accuracy.
@inproceedings{pranckeviciene2004consensus,
  title={Consensus-based identification of spectral signatures for classification of high-dimensional biomedical spectra},
  author={Pranckeviciene, Erinija and Baumgartner, Richard and Somorjai, Ray},
  booktitle={Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. August 23-26, Cambridge, UK.},
  volume={2},
  pages={319--322},
  year={2004},
  publisher={IEEE},
  abstract={The identification of spectral signatures is crucial for the classification/profiling of biomedical spectra. Because only limited number of biomedical samples of high dimensionality is typically available, dimensionality reduction techniques (identification of discriminatory features) are essential for robust classifier development. We show, on three real-world biomedical datasets, the potential of a consensus-based identification of important feature subsets, using a genetic algorithm and a sparse linear classifier. When training data are in short supply, the proposed methodology leads to more stable subset identification and higher classification accuracy.},
  keywords={genetic algorithms, robustness, biomarkers, PCA, training data, mathematical programming, linear programming, feature extraction, data mining},
url_Link={http://ieeexplore.ieee.org/document/1334189/}
%url_Paper={http://erinijapranckeviciene.net/biomedical_projects/Spectral_signatures_ICPR04.pdf}

}

Downloads: 0