@book{JRC48204,
	editor = {},
	address = {Heidelberg (Germany)},
	year = {2008},
	author = {Mascherini M and Fabio F and Stefanini FM},
	isbn = {},
	abstract = {Bayesian Networks are increasingly used to represent conditional independence relations among variables and causal information in problem domains in which decisions are based on probabilistic reasoning. Structural learning is NPhard therefore the database of observed cases must be often supplemented with search heuristics based on prior information. In this paper we present a software package for R, called MASTINO, that extends the existing DEAL package by providing new tools for learning Bayesian Networks and Conditional Gaussian networks in a score-and-search framework, such as the score function P-metric and the M-GA genetic algorithm. MASTINO is freely available under the terms of the GNU General Public License Version 2, and it has been recently submitted to be part of the CRAN repository. Meanwhile it can be downloaded from the website: http://statind.jrc.it/mastino.
		Keywords: Bayesian Networks, Structural Learning, R Package 1 Introduction Bayesian Networks (BNs), Cowell et al. (1999), are a widespread tool in many areas of artificial intelligence and statistics because of efficient algorithms which make probabilistic inference effective in highly structured problem domains.
		BNs are suited to represent conditional independence relationships but they have been extended to represent causal information, Spirtes et al. (2000), and utility of decisions, so that probabilistic expert systems are increasingly developed in areas ranging from technology to medical problem domains.
		Inference about the structure of a BN, also called structural learning, has been proved to be a NP-hard problem, Chickering (1995). Structural learning is typically performed by combining expert¿s priori knowledge with the information contained in a database of cases. Several heuristics have been shown to work in practice and it seems that specialized problem domains take benefits from problem-dependent tuning. A software package for R, (R Development Core Team, 2008), suited to quickly implement hypothesized heuristics and
		},
	title = {MASTINO: Learning Bayesian Networks Using R
		},
	url = {},
	volume = {},
	number = {},
	journal = {},
	pages = {1-8},
	issn = {},
	publisher = {Physica Verlag},
	doi = {}