Using Bayesian networks with rule extraction to infer the risk of weed infestation in a corn-crop

This paper describes the modeling of a weed infestation risk inference system that implements a collaborative inference scheme based on rules extracted from two Bayesian network classifiers. The first Bayesian classifier infers a categorical variable value for the weed-crop competitiveness using as input categorical variables for the total density of weeds and corresponding proportions of narrow and broad-leaved weeds. The inferred categorical variable values for the weed-crop competitiveness along with three other categorical variables extracted from estimated maps for the weed seed production and weed coverage are then used as input for a second Bayesian network classifier to infer categorical variables values for the risk of infestation. Weed biomass and yield loss data samples are used to learn the probability relationship among the nodes of the first and second Bayesian classifiers in a supervised fashion, respectively. For comparison purposes, two types of Bayesian network structures are considered, namely an expert-based Bayesian classifier and a naive Bayes classifier. The inference system focused on the knowledge interpretation by translating a Bayesian classifier into a set of classification rules. The results obtained for the risk inference in a corn-crop field are presented and discussed. (C) 2009 Elsevier Ltd. All rights reserved.

Sources of Variations When Comparing Concrete Carbonation Results

Carbonation is one of the main concerns for concrete service life in tropical countries. The mechanism and materials that produce it have been widely studied as well as natural and accelerated methods to report and analyze it. In spite of reported investigations, there is a need for information that could allow an adequate interpretation of the results of the standardization process. This lack of information can produce variations not only in the interpretation but also in the predictions of service life. The purpose of this paper is to analyze and discuss variables that could be sources of error, especially when performing accelerated tests. As a result, a methodologies to minimize variations when interpreting and comparing results is proposed, such as specimen geometry and preconditioning, spacing, relative humidity, and CO(2) concentration.