You are here

Year 2002

  1. Annamaria Rizzoli; Stefano Merler; Cesare Furlanello; C. Chemini; C. Genchi,
    Geographical Information Systems and Bootstrap Aggregation (Bagging) of Tree-Based Classifiers for Lyme Disease Risk Assessment in Trentino, Italian Alps,
    , pp. 485 -
  2. Cesare Furlanello; Stefano Merler; Stefano Menegon; S. Mancuso; G. Bertiato,
    New WEBGIS technologies for geolocation of epidemiological data: an application for the surveillance of the risk of Lyme borreliosis disease,
    , pp. 241 -
  3. G.R. Hess; S.E. Randolph; P. Arneberg; C. Chmini; Cesare Furlanello; J. Harwood; M. Roberts; J. Swinton,
    Spatial aspects of disease dynamics,
  4. Bruno Caprile; Cesare Furlanello; Stefano Merler,
    Highlighting Hard Patterns via Adaboost Weights Evolution,
    Proceedings of the Third International Workshop on Multiple Classifier Systems [MCS 2002],
    , pp. 72-
  5. Cesare Furlanello; Stefano Merler; Giuseppe Jurman; Maria Serafini,
    Gene selection and classification with support vector machines applied to microarray data,
    Primo Workshop Nazionale sulla Bioinformatica,
  6. Stefano Merler; Cesare Furlanello; Annamaria Rizzoli; C. Chemini,
    Mapping tick borne diseases risk in Trentino, Italian Alps,
    Book of abstracts of the 4th International Conference on Ticks and Tick-borne Pathogens [TTP 4],
  7. Stefano Menegon; Steno Fontanari; Radim Blazek; Markus Neteler; Stefano Merler; Cesare Furlanello,
    Wildlife management and landscape analysis in the grass gis,
    Proceedings of the Open Source Free Software GIS - GRASS users conference 2002,
  8. Cesare Furlanello; Stefano Merler; Giuseppe Jurman; Maria Serafini,
    Entropy-based gene ranking without selection bias for the predictive classification of microarray data,
    We describe a ranking method for the identification of biomedically important genes for diagnosis and therapy, and provide an experimental schema for the development of predictive classification models on microarray data. This combined approach is designed to correct the selection bias problem (too optimistic prediction errors estimated by rules tested on samples previously used in the feature selection process). Our E--RFE ranking algorithm is a wrapper based on the entropy of the distribution of weights obtained from a SVM classifier. In order to control and speed-up the ranking process, E--RFE eliminates chunks of uninteresting genes until the remaining distribution stabilizes into higher entropy levels, then proceeding at shorter elimination steps as in the original recursive feature elimination RFE method. To control the selection bias, we use an external stratified partition resampling scheme and an internal K-fold cross-validation for the E--RFE feature ranking at each run. This double intensive model selection and error estimation process is made viable by a speed-up factor of 1/100 of E-RFE with respect to RFE, without a decrease of classification accuracy. The experimental scheme supports the identification of gene candidates with the highest contribute to predictive accuracy,