A survey of evolutionary algorithms for decision-tree induction

This paper presents a survey of evolutionary algorithms that are designed for decision-tree induction. In this context, most of the paper focuses on approaches that evolve decision trees as an alternate heuristics to the traditional top-down divide-and-conquer approach. Additionally, we present some alternative methods that make use of evolutionary algorithms to improve particular components of decision-tree classifiers. The paper's original contributions are the following. First, it provides an up-to-date overview that is fully focused on evolutionary algorithms and decision trees and does not concentrate on any specific evolutionary approach. Second, it provides a taxonomy, which addresses works that evolve decision trees and works that design decision-tree components by the use of evolutionary algorithms. Finally, a number of references are provided that describe applications of evolutionary algorithms for decision-tree induction in different domains. At the end of this paper, we address some important issues and open questions that can be the subject of future research.

Contribution to economic evaluation of systems that value animal welfare at farm

The demand for "welfare friendly" products increases as public conscience and perception on livestock production systems grow. The public and policy-makers demand scientific information for education and to guide decision processes. This paper describes some of the last decade contributions made by scientists on the technical, economical and market areas of farm animal welfare. Articles on animal welfare were compiled on the following themes: 1) consumer behavior, 2) technical and economical viability, 3) public regulation, and 4) private certification policies. Most studies on the economic evaluation of systems that promote animal welfare involved species destined to produce export items, such as eggs, beef and pork. Few studies were found on broilers, dairy cows and fish, and data regarding other species, such as horses, sheep and goats were not found. Scientists understand that farm animal welfare is not only a matter of ethics, but also an essential tool to gain and maintain markets. However, it is unfortunate that little attention is paid to species that are not economically important for exports. Studies that emphasize on more humane ways to raise animals and that provide economic incentives to the producer are needed. An integrated multidisciplinary approach is necessary to highlight the benefits of introducing animal welfare techniques to existing production systems.

Economic viability of retrofiting emitters in center pivot irrigation systems

Although several studies have been conducted to evaluate the uniformity of water application under center pivot irrigation systems, there are few studies concerning the economic perspective of such coefficient. The aim of this study is to present a methodology to accomplish an economic analysis as support for the decision-making to retrofit emitters in center pivot irrigation systems, and to attribute an economic meaning to the uniformity coefficient of water application taking into account the response function productivity to the amount of water applied and the sale price of the crops. In the hypothetic calculation example considering the variation of revenue of potato crop under center pivot irrigation system, it was verified that the area with uniformity coefficient of water application of 90% brought an income increase of BR$ 1,992.00, considering an area about 1,0 ha. Thus, it can be concluded that the methodology presented has met the objectives proposed in the study and made it possible to attribute an economical meaning to the coefficient of water uniformity application.

Active cutaneous warming systems to prevent intraoperative hypothermia: a systematic review

This study analyzed the evidence available in the literature concerning the effectiveness of different active cutaneous warming systems to prevent intraoperative hypothermia. This is a systematic review with primary studies found in the following databases: CINAHL, EMBASE, Cochrane Register of Controlled Trials and Medline. The sample comprised 23 randomized controlled trials. There is evidence in the literature indicating that the circulating water garment system is the most effective in maintaining patient body temperature. These results can support nurses in the decision-making process concerning the implementation of effective measures to maintain normothermia, though the decision of health services concerning which system to choose should also take into account its cost-benefit status given the cost related to the acquisition of such systems.

Web Scale Discovery Systems – How to assess the best solution

The University of São Paulo has been experiencing the increase in contents in electronic and digital formats, distributed by different suppliers and hosted remotely or in clouds, and is faced with the also increasing difficulties related to facilitating access to this digital collection by its users besides coexisting with the traditional world of physical collections. A possible solution was identified in the new generation of systems called Web Scale Discovery, which allow better management, data integration and agility of search. Aiming to identify if and how such a system would meet the USP demand and expectation and, in case it does, to identify what the analysis criteria of such a tool would be, an analytical study with an essentially documental base was structured, as from a revision of the literature and from data available in official websites and of libraries using this kind of resources. The conceptual base of the study was defined after the identification of software assessment methods already available, generating a standard with 40 analysis criteria, from details on the unique access interface to information contents, web 2.0 characteristics, intuitive interface, facet navigation, among others. The details of the studies conducted into four of the major systems currently available in this software category are presented, providing subsidies for the decision-making of other libraries interested in such systems.

PRoSPer: perceptual similarity queries in medical CBIR systems through user profiles

In this paper, we present a novel approach to perform similarity queries over medical images, maintaining the semantics of a given query posted by the user. Content-based image retrieval systems relying on relevance feedback techniques usually request the users to label relevant/irrelevant images. Thus, we present a highly effective strategy to survey user profiles, taking advantage of such labeling to implicitly gather the user perceptual similarity. The profiles maintain the settings desired for each user, allowing tuning of the similarity assessment, which encompasses the dynamic change of the distance function employed through an interactive process. Experiments on medical images show that the method is effective and can improve the decision making process during analysis.