biblio_i03.bib
@INBOOK{annr,
AUTHOR = {C. Furlanello and M. Serafini and S. Merler and G. Jurman},
EDITOR = {D.C. Wunsch II and M. Hasselmo and K. Venayagamoorthy and D. Wang},
TITLE = {Advances in Neural Network Research: IJCNN 2003},
CHAPTER = {An accelerated procedure for recursive feature ranking on
microarray data},
PUBLISHER = {Elsevier},
YEAR = {2003}
}
@ARTICLE{furlanello2004control,
AUTHOR = {C. Furlanello and M. Serafini and S. Merler and G. Jurman},
TITLE = {CONTROL OF SELECTION BIAS IN MICROARRAY DATA ANALYSIS},
YEAR = {2003},
JOURNAL = {Minerva Biotecnologica},
VOLUME = 15,
PAGES = { 217--222},
NUMBER = 4
}
@ARTICLE{furlanello2003entropy,
AUTHOR = {C. Furlanello and M. Serafini and S. Merler and G. Jurman},
TITLE = {Entropy-{B}ased {G}ene {R}anking without {S}election {B}ias for the {P}redictive {C}lassification of {M}icroarray {D}ata},
YEAR = {2003},
JOURNAL = {BMC Bioinformatics},
NUMBER = {4},
VOLUME = {},
PAGES = {54},
PDF = {http://www.biomedcentral.com/1471-2105/4/54},
ABSTRACT = {We describe the E--RFE method for gene ranking,
useful for the identification of markers in the predictive
classification of array data. The method supports a practical modeling
scheme designed to avoid the construction of classification rules
based on the selection of very small gene subsets (an effect known as
the selection bias, in which too optimistic predictive errors are
estimated due to testing on samples already considered in the feature
selection process). \newline
\textbf{Results:} With E--RFE, we speed up the recursive feature e
limination (RFE) with SVM classifiers by eliminating chunks of
uninteresting genes using to an entropy measure of the SVM weights
distribution. An optimal subset of genes is selected according to a
two-strata model evaluation procedure: modeling is replicated by an
external stratified-partition resampling scheme, and, within each run,
an internal K-fold cross-validation is used for E--RFE ranking. Also,
the optimal number of genes can be estimated according to the
saturation of Zipf's law profiles.\newline
\textbf{Conclusions:} Without a decrease of classification accuracy,
E--RFE allows a speed-up factor of 100 with respect to standard RFE,
however, improving on alternative parametric RFE reduction strategies.
A process for gene selection and error estimation is, thus, made
practical, ensuring control of the selection bias, and providing
additional diagnostic indicators of gene importance.}
}
@ARTICLE{merler2003anaccelerated,
AUTHOR = {C. Furlanello and M. Serafini and S. Merler and G. Jurman},
TITLE = { An accelerated procedure for recursive feature ranking on
microarray data},
YEAR = {2003},
JOURNAL = {Neural Networks},
NUMBER = {5--6},
VOLUME = {16},
PAGES = {641--648},
ABSTRACT = { We describe a new wrapper algorithm for fast feature ranking in
classification problems. The \mbox{E--RFE} (Entropy-based Recursive
Feature Elimination) method eliminates chunks of uninteresting
features according to the entropy of the weights distribution of a
SVM classifier. With specific regard to DNA microarray datasets, the
method is designed to support computationally intensive model
selection in classification problems in which the number of features
is much larger than the number of samples. We test \mbox{E--RFE} on
synthetic and real data sets, comparing it with other SVM-based
methods. The speed-up obtained with \mbox{E--RFE} supports predictive
modeling on high dimensional microarray data.}
}
@INPROCEEDINGS{furlanello2003gis,
AUTHOR = {C. Furlanello and M. Neteler and S. Merler and S. Menegon and S. Fontanari and A. Donini and A. Rizzoli and C. Chemini},
TITLE = {{GIS} and the {R}andom {F}orest {P}redictor: {I}ntegration in {R} for {T}ick-borne {D}isease {R}isk {A}ssessment},
BOOKTITLE = {Proceedings of the 3rd International Workshop on Distributed Statistical Computing},
PUBLISHER = {},
EDITOR = {K. Hornik and F. Leisch},
PAGES = {},
YEAR = {Vienna, Austria, March 20-22, 2003},
ABSTRACT = { We discuss how sophisticated machine learning methods may
be rapidly integrated within a GIS for the development of new
approaches in landscape epidemiology. A multitemporal predictive map
is obtained by modeling in \texttt{R}\xspace, analyzing geodata and
digital maps in \texttt{GRASS}\xspace, and managing biodata samples
and weather data in \texttt{PostgreSQL}\xspace. In particular, we
present a risk mapping system for tick-borne diseases, applied to
model the risk of exposure to Lyme borreliosis and tick-borne
encephalitis (TBE) in Trentino, Italian Alps.},
LINK = {http://mpa.itc.it/papers/furlanello2003gis.pdf}
}
@ARTICLE{merler2003automatic,
AUTHOR = {S. Merler and C. Furlanello and B. Larcher and A. Sboner},
TITLE = {Automatic Model Selection in Cost-sensitive Boosting},
YEAR = {2003},
JOURNAL = {Information Fusion},
NUMBER = {1},
VOLUME = {4},
PAGES = {3--10},
ABSTRACT = { This paper introduces SSTBoost, a predictive classification
methodology designed to target the accuracy of a modified boosting
algorithm towards required sensitivity and specificity constraints.
The SSTBoost method is demonstrated in practice for the automated
medical diagnosis of cancer on a set of skin lesions (42 melanomas
and 110 naevi) described by geometric and colorimetric features. A
cost-sensitive variant of the AdaBoost algorithm is combined with a
procedure for the automatic selection of optimal cost parameters.
Within each boosting step, different weights are considered for
errors on false negatives and false positives, and differently
updated for negatives and positives. Given only a target region in
the ROC space, the method also completely automates the selection of
the cost parameters ratio, tipically of uncertain definition. On the
cancer diagnosis problem, SSTBoost outperformed in accuracy and
stability a battery of specialized automatic systems based on
different types of multiple classifier combinations and a panel of
expert dermatologists. The method thus can be applied for the early
diagnosis of melanoma cancer or in other problems in which an
automated cost-sensitive classification is required.},
LINK = {http://mpa.itc.it/papers/merler2003automatic.pdf}
}
@INPROCEEDINGS{furlanello2002gene,
AUTHOR = {C. Furlanello and M. Serafini and S. Merler and G. Jurman},
TITLE = {Gene selection and classification by {E}ntropy-based {R}ecursive {F}eature {E}limination},
BOOKTITLE = {International Joint Conference on Neural Networks},
PUBLISHER = {},
EDITOR = {},
PAGES = {3077--3082},
YEAR = { Portland, Oregon, July 20-24, 2003.},
ABSTRACT = {We analyse E-RFE (Entropy-based Recursive Feature
Elimination), a new wrapper algorithm for fast feature ranking in
classification problems. The E-RFE method operates the elimination of
chunks of uninteresting features according to the entropy of the
weights distribution of a SVM classifier. The method is designed to
support computationally intensive model selection in classification
problems in which the number of features is much larger than the
number of samples. We proofread the elimination procedure on
synthetic data sets, and we demonstrate the applicability of E-RFE for
the identification of biomedically important genes in predictive
classification of microarray data.}
}
@ARTICLE{mitasovaneteler2003,
AUTHOR = {H. Mitasova and M. Neteler},
TITLE = {Free {G}eneral-purpose {GIS}. {A} {G}eographic {R}esources {A}nalysis
{S}upport {S}ystem},
JOURNAL = {{GIM} {I}nternational},
NUMBER = {11},
VOLUME = {17},
YEAR = 2003,
PAGES = {40-43},
ABSTRACT = {The Geographic Resources Analysis, GRASS, a general purpose
GIS originally developed by U.S. Army Corps of Engineers Laboratory, has
grown into one of the main components of Open Source and Free Software
geospatial computational infrastructure. Current developments led by
international team of programmers, focus on improving the 2D and 3D raster
and vector data processing and analysis tools and 3D visualization
capabilities in the wake of publishing of the code under GPL in 1999.
Applications in the area of epidemiology, coastal management and water flow
modelling provide a snapshot of the capabilities.},
LINK = {http://www.gim-international.com/}
}
@INPROCEEDINGS{AntoniolClusteringGA2003,
AUTHOR = {G. Antoniol and M. Di Penta and M. Neteler},
TITLE = {Moving to Smaller Libraries via Clustering and Genetic
Algorithms},
BOOKTITLE = {CSMR 2003, 7th IEEE European Conference on Software
Maintenance and Reengineering},
YEAR = {2003},
PAGES = {307--316},
URL = {http://www.scoda.unisannio.it/~antoniol/publications/papers/csmr2003lib.pdf},
ABSTRACT = {There may be several reasons to reduce a software system
to its bare bone removing the extra fat introduced during development
or evolution. Porting the software system on embedded devices or
palmtops are just two examples.
This paper presents an approach to re-factoring libraries with the aim
of reducing the memory requirements of executables. The approach is
organized in two steps. The first step defines an initial solution
based on clustering methods, while the subsequent phase refines the
initial solution via genetic algorithms.
In particular, a novel genetic algorithm approach, considering the
initial clusters as the starting population, adopting a
knowledge-based mutation function and a multi-objective fitness
function, is proposed.
The approach has been applied to several medium and large-size open
source software systems such as GRASS, KDE-QT, Samba and MySQL,
allowing to effectively produce smaller, loosely coupled libraries,
and to reduce the memory requirement for each application.}
}
@ARTICLE{raghavan2003GRASS,
AUTHOR = {V. Raghavan and K. Kita and K. Iwao and M. Neteler},
TITLE = {Open source {GIS} {GRASS} for developing spatial data infrastructure
- {P}resent status and future potential},
JOURNAL = {Journal of Information Science and Technology Association},
NUMBER = {53},
VOLUME = {4},
YEAR = 2003,
PAGES = {216-222},
ABSTRACT = {This article outlines the salient features and current state
of development of the Open Source GIS GRASS. We discuss the concepts and
issues related to the development of GRASS that represents the only full
fledged, multi-platform GIS available as OSS. Further, we highlight the
potential of GRASS GIS in developing spatial data infrastructure and put
forth a proposal for establishing a GRASS Consortium to support, nurture and
accelerate furher developments.},
LINK = {http://www.infosta.or.jp/journal/back2003e.html}
}