Word sense disambiguation via high order of learning in complex networks

Complex networks have been employed to model many real systems and as a modeling tool in a myriad of applications. In this paper, we use the framework of complex networks to the problem of supervised classification in the word disambiguation task, which consists in deriving a function from the supervised (or labeled) training data of ambiguous words. Traditional supervised data classification takes into account only topological or physical features of the input data. On the other hand, the human (animal) brain performs both low- and high-level orders of learning and it has facility to identify patterns according to the semantic meaning of the input data. In this paper, we apply a hybrid technique which encompasses both types of learning in the field of word sense disambiguation and show that the high-level order of learning can really improve the accuracy rate of the model. This evidence serves to demonstrate that the internal structures formed by the words do present patterns that, generally, cannot be correctly unveiled by only traditional techniques. Finally, we exhibit the behavior of the model for different weights of the low- and high-level classifiers by plotting decision boundaries. This study helps one to better understand the effectiveness of the model. Copyright (C) EPLA, 2012

A Bayesian Approach for Decision Making on the Identification of Genes with Different Expression Levels: An Application to Escherichia coli Bacterium Data

A common interest in gene expression data analysis is to identify from a large pool of candidate genes the genes that present significant changes in expression levels between a treatment and a control biological condition. Usually, it is done using a statistic value and a cutoff value that are used to separate the genes differentially and nondifferentially expressed. In this paper, we propose a Bayesian approach to identify genes differentially expressed calculating sequentially credibility intervals from predictive densities which are constructed using the sampled mean treatment effect from all genes in study excluding the treatment effect of genes previously identified with statistical evidence for difference. We compare our Bayesian approach with the standard ones based on the use of the t-test and modified t-tests via a simulation study, using small sample sizes which are common in gene expression data analysis. Results obtained report evidence that the proposed approach performs better than standard ones, especially for cases with mean differences and increases in treatment variance in relation to control variance. We also apply the methodologies to a well-known publicly available data set on Escherichia coli bacterium.

Nutrient reference concentrations and trophic state boundaries in subtropical reservoirs

Nutrient criteria as reference concentrations and trophic state boundaries are necessary for water management worldwide because anthropogenic eutrophication is a threat to the water uses. We compiled data on total phosphorus (TP), nitrogen (TN) and chlorophyll a (Chl a) from 17 subtropical reservoirs monitored from 2005-2009 in the Sao Paulo State (Brazil) to calculate reference concentrations through the trisection method (United States Environmental Protection Agency). By dividing our dataset into thirds we presented trophic state boundaries and frequency curves for the nutrient levels in water bodies with different enrichment conditions. TP and TN baseline concentrations (0.010 mg/L and 0.350 mg/L, respectively) were bracketed by ranges for temperate reservoirs available in the literature. We propose trophic state boundaries (upper limits for the oligotrophic category: 0.010 mg TP/L, 0.460 mg TN/L and 1.7 mu g Chl a/L; for the mesotrophic: 0.030 mg TP/L, 0.820 mg TN/L and 9.0 mu g Chl a/L). Through an example with a different dataset (from the Itupararanga Reservoir, Brazil), we encouraged the use of frequency curves to compare data from individual monitoring efforts with the expected concentrations in oligotrophic, mesotrophic and eutrophic regional systems. Such analysis might help designing recovery programs to reach targeted concentrations and mitigate the undesirable eutrophication symptoms in subtropical freshwaters.