# 2006.bib

@inproceedings{GamLamRig06-DTMIB-IW,
author = { Giacomo Gamberoni and Evelina Lamma and Fabrizio Riguzzi and Sergio Storari and Chiara Scapoli},
title = {Marker Analysis with APRIORI-Based Algorithms},
booktitle = {Notes from the Workshop on Data and Text Mining for Integrative Biology of the 17th European Conference on Machine Learning ({ECML}'2006) and the 10th European Conference on Principles and Practice of Knowledge Discovery in Databases ({PKDD}'2006)},
month = sep,
year = {2006},
editor = {Melanie Hilario and Claire N\'edellec},
pages = {61--66},
http = {http://www.ecmlpkdd2006.org/ws-dtib.pdf},
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/GamLamRig-DTMIB.pdf},
abstract = {In genetic studies, polygenic diseases are often analyzed searching for marker patterns that play a significant role in the susceptibility to the disease. In this paper we consider a dataset regarding periodontitis, that includes the analysis of nine genetic markers for 148 patients. We analyze these data by using two APRIORI-based algorithms: APRIORI-SD and APRIORI with filtering. The discovered rules (especially those found by APRIORI with filtering) confirmed the results published on periodontitis.}
}

@article{LamMelNan06-TITB-IJ,
author = {Evelina Lamma and Paola Mello and Annamaria Nanetti and
Fabrizio Riguzzi and Sergio Storari and Gianfranco Valastro},
title = {Artificial Intelligence Techniques for Monitoring Dangerous Infections},
journal = {IEEE Transaction on Information Technology in Biomedicine},
year = {2006},
publisher = {IEEE Computer Society Press},
volume = {10},
number = {1},
pages = {143-155},
month = jan,
issn = {1089-7771},
doi = {10.1109/TITB.2005.855537},
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/LamMelNanRigStoVal-TITB06.pdf},
url = {http://dx.medra.org/10.1109/TITB.2005.855537},
abstract = {
The monitoring and detection of nosocomial infections is a very
important problem arising in hospitals. A hospital-acquired or
nosocomial infection is a disease that develops after the
admission into the hospital and it is the consequence of a
treatment, not necessarily a surgical one, performed by the
medical staff. Nosocomial infections are dangerous because they
are caused by bacteria which have dangerous (critical) resistance
to antibiotics. This problem is very serious all over the world.
In Italy, actually almost 5-8\% of the patients admitted into
hospitals develop this kind of infection. In order to reduce this
figure, policies for controlling infections should be adopted by
medical practitioners. In order to support them in this complex
task, we have developed a system, called MERCURIO, capable of
managing different aspects of the problem. The objectives of this
system are the validation of microbiological data and the
creation of a real time epidemiological information system. The
system is useful for laboratory physicians, because it supports
them in the execution of the microbiological analyses; for
clinicians, because it supports them in the definition of the
prophylaxis, of the most suitable antibiotic therapy and in the
monitoring of patients' infections, and for epidemiologists,
because it allows them to identify outbreaks and to study
infection dynamics. In order to achieve these objectives we have
adopted expert system and data mining techniques. We have also
integrated a statistical module that monitors the diffusion of
nosocomial infections over time in the hospital and that strictly
interacts with the knowledge based module. Data mining techniques
have been used for improving the system knowledge base. The
knowledge discovery process is not antithetic, but complementary
to the one based on manual knowledge elicitation. In order to
verify the reliability of the tasks performed by MERCURIO and the
usefulness of the knowledge discovery approach, we performed a
test based on a dataset of real infection events. In the
validation task MERCURIO achieved an accuracy of 98.5\%, a
sensitivity of 98.5\% and a specificity of 99\%. In the therapy
suggestion task MERCURIO achieved very high Accuracy and
Specificity as well. The  executed test provided many insights to
experts too (we discovered some of their mistakes). The knowledge
discovery approach was very effective in validating part of
MERCURIO knowledge base and also in extending it with new
validation rules, confirmed by  interviewed microbiologists and
peculiar to the hospital laboratory under consideration.},
keywords = {Microbiology,  Knowledge Based Systems, Decision Support Systems,
Data Mining, Classification},
}

@incollection{LamRigSto06-BC,
author = {Evelina Lamma AND Fabrizio Riguzzi AND Sergio Storari},
title = {Improving the K2 Algorithm Using
Association Rule Parameters},
booktitle = {Modern Information Processing: From Theory to
Applications},
editor = {Bernadette Bouchon-Meunier and Giulianella Coletti and Ronald
Yager},
publisher = {Elsevier},
isbn = {0-444-52075-9},
year = {2006},
pages = {207--217},
doi = {10.1016/B978-044452075-3/50018-2},
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/LamRigSto-IPMUBK06.pdf},
url = {http://www.sciencedirect.com/science/article/pii/B9780444520753500182},
abstract = {
A Bayesian network is an appropriate tool to work with the
uncertainty  that is typical of real-life applications. Bayesian
network arcs represent statistical dependence between different
variables and can be automatically elicited from database by
Bayesian network learning algorithms such as K2. In the data
mining field, association rules can also be interpreted  as
expressing statistical dependence relations. In this paper we
present an extension of K2 called K2-rules that exploits a
parameter normally defined in relation to association rules for
learning Bayesian networks. We compare K2-rules with K2 and TPDA
on the problems of learning four Bayesian networks. The
experiments show that K2-rules improves both K2 and TPDA with
respect to the quality of the learned network and K2 with respect
to the execution time},
keywords = {
Bayesian Networks, Machine Learning, Association
Rules}
}

@inproceedings{FlaMarRig06-RCRA06-NW,
author = {Peter Flach and Valentina Maraldi and  Fabrizio Riguzzi},
title = {Algorithms for Efficiently and Effectively Using Background Knowledge in Tertius},
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/FlaMarRig-RCRA06.pdf},
booktitle = {Incontro del Gruppo di Lavoro
Rappresentazione della Conoscenza e Ragionamento Automatico
({RCRA}) dell'Associazione Italiana per l'Intelligenza Artificiale ({AI*IA}) dal titolo
Analisi Sperimentale e Benchmark di Algoritmi per l'Intelligenza Artificiale'', 23 giugno 2006},
keywords = {Machine Learning, Inductive Logic Programming},
abstract = {\texttt{Tertius} is an Inductive Logic Programming system that performs
confirmatory induction, i.e., it looks for the $n$ clauses that have the
highest
value of a confirmation evaluation function.  In this setting, background
knowledge is very useful because it can improve the reliability of
the evaluation function, assigning minimal confirmation to clauses that
are implied by the background knowledge and increasing the confirmation of the remaining clauses.
We propose the algorithms \emph{Background1} and \emph{Background2} that look for clauses in the background that imply
the clause under evaluation by \texttt{Tertius}. Both are based on a simplified implication test
that is correct with respect to $\theta$-subsumption but not complete.
The implication test is not complete because we want to keep the run time inside
acceptable bounds.
We compare \emph{Background1} with \emph{Background2} on two datasets.  The results
show that \emph{Background2} is more efficient than \emph{Background1}.
Moreover, we also present the
algorithm \emph{Preprocess} that infers new clauses from the background knowledge in order to
exploit it as much as possible.
The algorithm modifies the
consequence finding algorithm proposed by Inoue by reducing its
execution time while giving up completeness.
},
editor = {Marco Gavanelli and Tony Mancini},
month = jun,
year = {2006},
}

@inproceedings{LamMelRig06-RCRA06-NW,
author = {Evelina Lamma and  Paola Mello and Fabrizio Riguzzi},
title = {Exploiting Abduction for Learning from Incomplete Interpretations},
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/LamMelRig-RCRA06.pdf},
booktitle = {Incontro del Gruppo di Lavoro
Rappresentazione della Conoscenza e Ragionamento Automatico
({RCRA}) dell'Associazione Italiana per l'Intelligenza Artificiale ({AI*IA}) dal titolo
Analisi Sperimentale e Benchmark di Algoritmi per l'Intelligenza Artificiale'', 23 giugno 2006},
keywords = {Machine Learning, Inductive Logic Programming},
abstract = {In this paper we describe an approach for integrating abduction
and induction in the ILP setting of learning from interpretations
with the aim of solving the problem of incomplete information both
in the background knowledge and in the interpretations. The
approach is inspired by the techniques developed in the learning
from entailment setting for performing induction from an
incomplete background knowledge. Similarly to those techniques,
we exploit an abductive proof procedure for completing the
available background knowledge and input interpretations.

The approach has been implemented in a system called AICL that is
based on the ILP system ICL. Preliminary experiments have been
performed on a toy domain where knowledge has been gradually
removed. The experiments show that AICL has an accuracy
that is superior to the one of ICL for levels of incompleteness between 5\% and 25\%.
},
editor = {Marco Gavanelli and Tony Mancini},
month = jun,
year = {2006},
}

@techreport{Rig06-TR,
author = {Fabrizio Riguzzi},
title = {{ALLPAD}: Approximate Learning of Logic Programs with Annotated Disjunctions},
institution = {Dipartimento di Ingegneria, Universit\{a} di Ferrara},
year = 2006,
number = {CS-2006-01},
month = oct,
pdf = {http://ds.ing.unife.it/~friguzzi/Papers/ILP2006tr.pdf},
abstract = {Logic Programs with Annotated Disjunctions (LPADs) provide
a simple and elegant framework for representing probabilistic knowledge
in logic programming. In this paper I consider the problem of learning
ground LPADs starting from a set of interpretations annotated with
their probability. I present the system ALLPAD for solving this problem.
`