Evolutionary model trees for handling continuous classes in machine learning

Model trees are a particular case of decision trees employed to solve regression problems. They have the advantage of presenting an interpretable output, helping the end-user to get more confidence in the prediction and providing the basis for the end-user to have new insight about the data, confirming or rejecting hypotheses previously formed. Moreover, model trees present an acceptable level of predictive performance in comparison to most techniques used for solving regression problems. Since generating the optimal model tree is an NP-Complete problem, traditional model tree induction algorithms make use of a greedy top-down divide-and-conquer strategy, which may not converge to the global optimal solution. In this paper, we propose a novel algorithm based on the use of the evolutionary algorithms paradigm as an alternate heuristic to generate model trees in order to improve the convergence to globally near-optimal solutions. We call our new approach evolutionary model tree induction (E-Motion). We test its predictive performance using public UCI data sets, and we compare the results to traditional greedy regression/model trees induction algorithms, as well as to other evolutionary approaches. Results show that our method presents a good trade-off between predictive performance and model comprehensibility, which may be crucial in many machine learning applications. (C) 2010 Elsevier Inc. All rights reserved.

Forest structure in a mosaic of rainforest sites: The effect of fragmentation and recovery after clear cut

A variety of human-induced disturbances such as forest fragmentation and recovery after deforestation for pasture or agricultural activities have resulted in a complex landscape mosaic in the Una region of northeastern Brazil. Using a set of vegetation descriptors, we investigated the main structural changes observed in forest categories that comprise the major components of the regional landscape and searched for potential key descriptors that could be used to discriminate among different forest categories. We assessed the forest structure of five habitat categories defined as (I) interiors and (2) edges of large fragments of old-growth forest (>1000 ha), (3) interiors and (4) edges of small forest fragments (<100 ha), and (5) early secondary forests. Forest descriptors used here were: frequency of herbaceous lianas and woody climbers, number of standing dead trees, number of fallen trunks, litter depth, number of pioneer plants (early secondary and shade-intolerant species), vertical foliage stratification profile and distribution Of trees in different diameter classes. Edges and interiors of forest fragments were significantly different only in the number of standing dead trees. Secondary forests and edges of fragments showed differences in litter depth, fallen trunks and number of pioneer trees, and secondary forests were significantly different from fragment interiors in the number of standing dead trees and the number of pioneer trees. Horizontal and vertical structure evaluated via ordination analysis showed that fragment interiors, compared to secondary forests, were characterized by a greater number of medium (25-35 cm) and large (35-50 cm) trees and smaller numbers of thin trees (5-10 cm). There was great heterogeneity at the edges of small and large fragments, as these sites were distributed along almost the entire gradient. Most interiors of large and small fragments presented higher values of foliage densities at higher strata ( 15-20 m and at 20-25 m height), and lower densities at 1-5 m. All secondary forests and some fragment edge sites showed an opposite tendency. A discriminant function highlighted differences among forest categories, with transects of large fragment interiors and secondary forests representing two extremes along a disturbance gradient determined by foliage structure (densities at 15-20 m and 20-25 m), with the edges of both large and small fragments and the interiors of small fragments scattered across the gradient. The major underlying processes determining patterns of forest disturbance in the study region are discussed, highlighting the importance of forest fragments, independently of its size, as forests recovery after clear cut show a greatly distinct structure, with profound implications on fauna movements. (C) 2009 Elsevier BY. All rights reserved.

The challenge of maintaining Atlantic forest biodiversity: A multi-taxa conservation assessment of specialist and generalist species in an agro-forestry mosaic in southern Bahia

Recent developments have highlighted the importance of forest amount at large spatial scales and of matrix quality for ecological processes in remnants. These developments, in turn, suggest the potential for reducing biodiversity loss through the maintenance of a high percentage of forest combined with sensitive management of anthropogenic areas. We conducted a multi-taxa survey to evaluate the potential for biodiversity maintenance in an Atlantic forest landscape that presented a favorable context from a theoretical perspective (high proportion of mature forest partly surrounded by structurally complex matrices). We sampled ferns, butterflies, frogs, lizards, bats, small mammals and birds in interiors and edges of large and small mature forest remnants and two matrices (second-growth forests and shade cacao plantations), as well as trees in interiors of small and large remnants. By considering richness, abundance and composition of forest specialists and generalists, we investigated the biodiversity value of matrix habitats (comparing them with interiors of large remnants for all groups except tree), and evaluated area (for all groups) and edge effects (for all groups except trees) in mature forest remnants. our results suggest that in landscapes comprising high amounts of mature forest and low contrasting matrices: (1) shade cacao plantations and second-growth forests harbor an appreciable number of forest specialists; (2) most forest specialist assemblages are not affected by area or edge effects, while most generalist assemblages proliferate at edges of small remnants. Nevertheless, differences in tree assemblages, especially among smaller trees, Suggest that observed patterns are unlikely to be stable over time. (C) 2009 Elsevier Ltd. All rights reserved.

Landscape and farm scale management to enhance biodiversity conservation in the cocoa producing region of southern Bahia, Brazil

In southern Bahia, Brazil, large land areas are used for the production of cocoa (Theobroma cacao), which is predominantly grown under the shade of native trees in an agroforestry system locally known as cabruca. As a dominant forest-like landscape element of the cocoa region, the cabrucas play an important role in the conservation of the region`s biodiversity. The purpose of this review is to provide the scientific basis for an action plan to reconcile cocoa production and biodiversity conservation in southern Bahia. The available research collectively highlights the diversity of responses of different species and biological groups to both the habitat quality of the cabrucas themselves and to the general characteristics of the landscape, such as the relative extent and spatial configuration of different vegetation types within the landscape mosaic. We identify factors that influence directly or indirectly the occurrence of native species in the cabrucas and the wider landscape of the cocoa region and develop recommendations for their conservation management. We show that the current scientific knowledge already provides a good basis for a biodiversity friendly management of the cocoa region of southern Bahia, although more work is needed to refine some management recommendations, especially on shade canopy composition and density, and verify their economic viability. The implementation of our recommendations should be accompanied by appropriate biological and socioeconomic monitoring and the findings should inform a broad program of adaptive management of the cabrucas and the wider cocoa landscape.

Molecular phylogeny of tribe Rhipsalideae (Cactaceae) and taxonomic implications for Schlumbergera and Hatiora

Tribe Rhipsalideae is composed of unusual epiphytic or lithophytic cacti that inhabit humid tropical and subtropical forests. Members of this tribe present a reduced vegetative body, a specialized adventitious root system, usually spineless areoles and flowers and fruits reduced in size. Despite the debate surrounding the classification of Rhipsalideae, no studies have ever attempted to reconstruct phylogenetic relationships among its members or to test the monophyly of its genera using DNA sequence data; all classifications formerly proposed for this tribe have only employed morphological data. In this study, we reconstruct the phylogeny of Rhipsalideae using plastid (trnQ-rps16, rpl32-trnL, psbA-trnH) and nuclear (ITS) markers to evaluate the classifications previously proposed for the group. We also examine morphological features traditionally used to delimit genera within Rhipsalideae in light of the resulting phylogenetic trees. In total new sequences for 35 species of Rhipsalideae were produced (out of 55: 63%). The molecular phylogeny obtained comprises four main clades supporting the recognition of genera Lepismium, Rhipsalis, Hatiora and Schlumbergera. The evidence gathered indicate that a broader genus Schlumbergera, including Hatiora subg. Rhipsalidopsis, should be recognized. Consistent morphological characters rather than homoplastic features are used in order to establish a more coherent and practical classification for the group. Nomenclatural changes and a key for the identification of the genera currently included in Rhipsalideae are provided. (C) 2011 Elsevier Inc. All rights reserved.