A data-driven, flexible machine learning strategy for the classification of biomedical data. Somorjai, R. L, Alexander, M. E, Baumgartner, R., Booth, S., Bowman, C., Demko, A., Dolenko, B., Mandelzweig, M., Nikulin, A. E, Pizzi, N. J, Pranckeviciene, E., Summers, A. S, & Peter, Z. In Artificial intelligence methods and tools for systems biology, pages 67–85. Springer, 2004.
A data-driven, flexible machine learning strategy for the classification of biomedical data [link]Link  abstract   bibtex   
While biomedical data acquired from the latest spectroscopic modalities yield important information relevant to many diagnostic or prognostic procedures, they also present significant challenges for analysis, classification and interpretation. These challenges include sample sparsity, high-dimensional feature spaces, and noise/artifact signatures. Since a classifier does not exist, a classification strategy is needed, possessing five key components acting in concert: data visualization, preprocessing, feature space dimensionality reduction, reliable/robust classifier development, and classifier aggregation/fusion. These components, which should be flexible, data-driven, extensible, and computationally efficient, must provide accurate, reliable diagnosis/prognosis with the fewest maximally discriminatory, yet medically interpretable, features.
@incollection{somorjai2004data,
  title={A data-driven, flexible machine learning strategy for the classification of biomedical data},
  author={Somorjai, Rajmund L and Alexander, Murray E and Baumgartner, Richard and Booth, Stephanie and Bowman, Christopher and Demko, Aleksander and Dolenko, Brion and Mandelzweig, Marina and Nikulin, Aleksander E and Pizzi, Nicolino J and Pranckeviciene, Erinija and Summers, Arthur S and Zhilkin Peter},
  booktitle={Artificial intelligence methods and tools for systems biology},
  pages={67--85},
  year={2004},
  publisher={Springer},
  abstract={While biomedical data acquired from the latest spectroscopic modalities yield important information relevant to many diagnostic or prognostic procedures, they also present significant challenges for analysis, classification and interpretation. These challenges include sample sparsity, high-dimensional feature spaces, and noise/artifact signatures. Since a  classifier does not exist, a classification strategy is needed, possessing five key components acting in concert: data visualization, preprocessing, feature space dimensionality reduction, reliable/robust classifier development, and classifier aggregation/fusion. These components, which should be flexible, data-driven, extensible, and computationally efficient, must provide accurate, reliable diagnosis/prognosis with the fewest maximally discriminatory, yet medically interpretable, features.},
  keywords={life sciences, artificial intelligence, computer science, evolutionary biology},
  
  url_Link={http://link.springer.com/chapter/10.1007%2F978-1-4020-5811-0_5}
}

Downloads: 0