The evolution of jumping performance in anurans: morphological correlates and ecological implications

We investigated the evolution of anuran locomotor performance and its morphological correlates as a function of habitat use and lifestyles. We reanalysed a subset of the data reported by Zug (Smithson. Contrib. Zool. 1978; 276: 1-31) employing phylogenetically explicit statistical methods (n = 56 species), and assembled morphological data on the ratio between hind-limb length and snout-vent length (SVL) from the literature and museum specimens for a large subgroup of the species from the original paper (n = 43 species). Analyses using independent contrasts revealed that classifying anurans into terrestrial, semi-aquatic, and arboreal categories cannot distinguish between the effects of phylogeny and ecological diversification in anuran locomotor performance. However, a more refined classification subdividing terrestrial species into `fossorials` and `non-fossorials`, and arboreal species into `open canopy`, `low canopy` and `high canopy`, suggests that part of the variation in locomotor performance and in hind-limb morphology can be attributed to ecological diversification. In particular, fossorial species had significantly lower jumping performances and shorter hind limbs than other species after controlling for SVL, illustrating how the trade-off between burrowing efficiency and jumping performance has resulted in morphological specialization in this group.

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.