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.

A model of macadamia with application to pruning in orchards

A self-organising model of macadamia, expressed using L-Systems, was used to explore aspects of canopy management. A small set of parameters control the basic architecture of the model, with a high degree of self-organisation occurring to determine the fate and growth of buds. Light was sensed at the leaf level and used to represent vigour and accumulated basipetally. Buds also sensed light so as to provide demand in the subsequent redistribution of the vigour. Empirical relationships were derived from a set of 24 completely digitised trees after conversion to multiscale tree graphs (MTG) and analysis with the OpenAlea software library. The ability to write MTG files was embedded within the model so that various tree statistics could be exported for each run of the model. To explore the parameter space a series of runs was completed using a high-throughput computing platform. When combined with MTG generation and analysis with OpenAlea it provided a convenient way in which thousands of simulations could be explored. We allowed the model trees to develop using self-organisation and simulated cultural practices such as hedging, topping, removal of the leader and limb removal within a small representation of an orchard. The model provides insight into the impact of these practices on potential for growth and the light distribution within the canopy and to the orchard floor by coupling the model with a path-tracing program to simulate the light environment. The lessons learnt from this will be applied to other evergreen, tropical fruit and nut trees.

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.

A study on the inclusion of forest canopy morphology data in numerical simulations for the purpose of wind resource assessment

A series of numerical simulations of the flow over a forest stand have been conducted using two different turbulence closure models along with various levels of canopy morphology data. Simulations have been validated against Stereoscopic Particle Image Velocimetry measurements from a wind tunnel study using one hundred architectural model trees, the porosities of which have been assessed using a photographic technique. It has been found that an accurate assessment of the porosity of the canopy, and specifically the variability with height, improves simulation quality regardless of the turbulence closure model used or the level of canopy geometry included. The observed flow field and recovery of the wake is in line with characteristic canopy flows published in the literature and it was found that the shear stress transport turbulence model was best able to capture this detail numerically.

TESTING STATISTICAL HYPOTHESIS ON RANDOM TREES AND APPLICATIONS TO THE PROTEIN CLASSIFICATION PROBLEM

Efficient automatic protein classification is of central importance in genomic annotation. As an independent way to check the reliability of the classification, we propose a statistical approach to test if two sets of protein domain sequences coming from two families of the Pfam database are significantly different. We model protein sequences as realizations of Variable Length Markov Chains (VLMC) and we use the context trees as a signature of each protein family. Our approach is based on a Kolmogorov-Smirnov-type goodness-of-fit test proposed by Balding et at. [Limit theorems for sequences of random trees (2008), DOI: 10.1007/s11749-008-0092-z]. The test statistic is a supremum over the space of trees of a function of the two samples; its computation grows, in principle, exponentially fast with the maximal number of nodes of the potential trees. We show how to transform this problem into a max-flow over a related graph which can be solved using a Ford-Fulkerson algorithm in polynomial time on that number. We apply the test to 10 randomly chosen protein domain families from the seed of Pfam-A database (high quality, manually curated families). The test shows that the distributions of context trees coming from different families are significantly different. We emphasize that this is a novel mathematical approach to validate the automatic clustering of sequences in any context. We also study the performance of the test via simulations on Galton-Watson related processes.

Nickel sorption capacity of ground xylem of Quercus ilex trees and effects of selected ligands present in the xylem sap

In this work the influence of four different ligands present in the xylem sap of Quercus ilex (histidine, citric, oxalic and aspartic acids) on Ni(II) adsorption by xylem was investigated. Grinded xylem was trapped in acrylic columns and solutions of Ni(II), in the absence and presence of the four ligands prepared in KNO(3) 0-1 mol L(-1) at pH 5.5, were percolated through the column. Aliquots of solutions were recovered in the column end for Ni determination by graphite furnace atomic absorption spectrometry (GFAAS). The experimental. data to describe Ni sorption by xylem in both the presence and absence of ligands was better explained by the Freundlich isotherm model. The decreasing affinity order of ligands for Ni was: oxalic acid > citric acid > histidine > aspartic acid. On the other hand, the Ni(II) adsorption by xylem increased following the inverse sequence of ligands. Potentiometric titrations of acidic groups were carried out to elucidate the sorption site groups available in Q. ilex xylem. The potentiometric titration has shown three sorption sites: pK(a) 2.6 (57.7% of the sorption sites), related to monobasic aliphatic carboxylic acids or nitrogen aromatic bases, pK(a) 8.1 (9.6%) and pK(a) 9.9 (32.7%), related to phenolic groups. (C) 2008 Elsevier GmbH. All rights reserved.

Annual and polyetic progression of citrus canker on trees protected with copper sprays

The effects of copper sprays on annual and polyetic progress of citrus canker, caused by Xanthomonas citri subsp. citri, in the presence of the Asian citrus leafminer (Phyllocnistis citrella), were evaluated in a study conducted in a commercial orchard in northwest Parana state, Brazil, where citrus canker is endemic. Nonlinear monomolecular, logistic and Gompertz models were fitted to monthly disease incidence data (proportion of leaves with symptoms) for each treatment for three seasons. The logistic model provided the best estimate of disease progress for all years and treatments evaluated and logistic parameter estimates were used to describe polyetic disease dynamics. Although citrus canker incidence increased during each of the seasons studied, it decreased over the whole study period, more so in copper-treated trees than in water-sprayed controls. Copper treatment reduced disease incidence compared with controls in every year, especially 2004-2005, when incidence was ca. 10-fold higher in controls than in treated plots (estimated asymptote values 0 center dot 82 and 0 center dot 07, respectively). Copper treatment also reduced estimated initial disease incidence and epidemic growth rates every year.

Spatial pattern of black spot incidence within citrus trees related to disease severity and pathogen dispersal

Guignardia citricarpa, the causal agent of citrus black spot, forms airborne ascospores on decomposing citrus leaves and water-spread conidia on fruits, leaves and twigs. The spatial pattern of diseased fruit in citrus tree canopies was used to assess the importance of ascospores and conidia in citrus black spot epidemics in Sao Paulo State, Brazil. The aggregation of diseased fruit in the citrus tree canopy was quantified by the binomial dispersion index (D) and the binary form of Taylor`s Power Law for 303 trees in six groves. D was significantly greater than 1 in 251 trees. The intercept of the regression line of Taylor`s Power Law was significantly greater than 0 and the slope was not different from 1, implying that diseased fruit was aggregated in the canopy independent of disease incidence. Disease incidence (p) and severity (S) were assessed in 2875 citrus trees. The incidence-severity relationship was described (R-2 = 88.7%) by the model ln(S) = ln(a) + bCLL(p) where CLL = complementary log-log transformation. The high severity at low incidence observed in many cases is also indicative of low distance spread of G. citricarpa spores. For the same level of disease incidence, some trees had most of the diseased fruit with many lesions and high disease severity, whereas other trees had most of the fruit with few lesions and low disease severity. Aggregation of diseased fruit in the trees suggests that splash-dispersed conidia have an important role in increasing the disease in citrus trees in Brazil.

An overview of APSIM, a model designed for farming systems simulation

The Agricultural Production Systems Simulator (APSIM) is a modular modelling framework that has been developed by the Agricultural Production Systems Research Unit in Australia. APSIM was developed to simulate biophysical process in farming systems, in particular where there is interest in the economic and ecological outcomes of management practice in the face of climatic risk. The paper outlines APSIM's structure and provides details of the concepts behind the different plant, soil and management modules. These modules include a diverse range of crops, pastures and trees, soil processes including water balance, N and P transformations, soil pH, erosion and a full range of management controls. Reports of APSIM testing in a diverse range of systems and environments are summarised. An example of model performance in a long-term cropping systems trial is provided. APSIM has been used in a broad range of applications, including support for on-farm decision making, farming systems design for production or resource management objectives, assessment of the value of seasonal climate forecasting, analysis of supply chain issues in agribusiness activities, development of waste management guidelines, risk assessment for government policy making and as a guide to research and education activity. An extensive citation list for these model testing and application studies is provided. Crown Copyright (C) 2002 Published by Elsevier Science B.V. All rights reserved.

Tapping the wealth of microbial data in high-throughput metabolic model reconstruction

Genome-scale metabolic models are valuable tools in the metabolic engineering process, based on the ability of these models to integrate diverse sources of data to produce global predictions of organism behavior. At the most basic level, these models require only a genome sequence to construct, and once built, they may be used to predict essential genes, culture conditions, pathway utilization, and the modifications required to enhance a desired organism behavior. In this chapter, we address two key challenges associated with the reconstruction of metabolic models: (a) leveraging existing knowledge of microbiology, biochemistry, and available omics data to produce the best possible model; and (b) applying available tools and data to automate the reconstruction process. We consider these challenges as we progress through the model reconstruction process, beginning with genome assembly, and culminating in the integration of constraints to capture the impact of transcriptional regulation. We divide the reconstruction process into ten distinct steps: (1) genome assembly from sequenced reads; (2) automated structural and functional annotation; (3) phylogenetic tree-based curation of genome annotations; (4) assembly and standardization of biochemistry database; (5) genome-scale metabolic reconstruction; (6) generation of core metabolic model; (7) generation of biomass composition reaction; (8) completion of draft metabolic model; (9) curation of metabolic model; and (10) integration of regulatory constraints. Each of these ten steps is documented in detail.

Which screening strategy using BMD measurements would be most cost effective for hip fracture prevention in elderly women? A decision analysis based on a Markov model.

INTRODUCTION: Hip fractures are responsible for excessive mortality, decreasing the 5-year survival rate by about 20%. From an economic perspective, they represent a major source of expense, with direct costs in hospitalization, rehabilitation, and institutionalization. The incidence rate sharply increases after the age of 70, but it can be reduced in women aged 70-80 years by therapeutic interventions. Recent analyses suggest that the most efficient strategy is to implement such interventions in women at the age of 70 years. As several guidelines recommend bone mineral density (BMD) screening of postmenopausal women with clinical risk factors, our objective was to assess the cost-effectiveness of two screening strategies applied to elderly women aged 70 years and older. METHODS: A cost-effectiveness analysis was performed using decision-tree analysis and a Markov model. Two alternative strategies, one measuring BMD of all women, and one measuring BMD only of those having at least one risk factor, were compared with the reference strategy "no screening". Cost-effectiveness ratios were measured as cost per year gained without hip fracture. Most probabilities were based on data observed in EPIDOS, SEMOF and OFELY cohorts. RESULTS: In this model, which is mostly based on observed data, the strategy "screen all" was more cost effective than "screen women at risk." For one woman screened at the age of 70 and followed for 10 years, the incremental (additional) cost-effectiveness ratio of these two strategies compared with the reference was 4,235 euros and 8,290 euros, respectively. CONCLUSION: The results of this model, under the assumptions described in the paper, suggest that in women aged 70-80 years, screening all women with dual-energy X-ray absorptiometry (DXA) would be more effective than no screening or screening only women with at least one risk factor. Cost-effectiveness studies based on decision-analysis trees maybe useful tools for helping decision makers, and further models based on different assumptions should be performed to improve the level of evidence on cost-effectiveness ratios of the usual screening strategies for osteoporosis.

A cell-based model of extracellular-matrix-guided endothelial cell migration during angiogenesis.

Angiogenesis, the formation of new blood vessels sprouting from existing ones, occurs in several situations like wound healing, tissue remodeling, and near growing tumors. Under hypoxic conditions, tumor cells secrete growth factors, including VEGF. VEGF activates endothelial cells (ECs) in nearby vessels, leading to the migration of ECs out of the vessel and the formation of growing sprouts. A key process in angiogenesis is cellular self-organization, and previous modeling studies have identified mechanisms for producing networks and sprouts. Most theoretical studies of cellular self-organization during angiogenesis have ignored the interactions of ECs with the extra-cellular matrix (ECM), the jelly or hard materials that cells live in. Apart from providing structural support to cells, the ECM may play a key role in the coordination of cellular motility during angiogenesis. For example, by modifying the ECM, ECs can affect the motility of other ECs, long after they have left. Here, we present an explorative study of the cellular self-organization resulting from such ECM-coordinated cell migration. We show that a set of biologically-motivated, cell behavioral rules, including chemotaxis, haptotaxis, haptokinesis, and ECM-guided proliferation suffice for forming sprouts and branching vascular trees.