Browsing by Author "Ledo, L."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Ecotoxicological endpoints, are they useful tools to support ecological status assessment in strongly modified water bodies?Publication . Palma, Patrícia; Ledo, L.; Alvarenga, P.Although man-made reservoirs represent an important water supply source in countries where water scarcity has become a problem, little work has been done on the evaluation of their ecological status. Taking this in account, the general aim of this study was to assess the usefulness of ecotoxicological endpoints in the potential ecological status characterization of water reservoirs, with the purpose of their possible integration in evaluation programs developed under the Water Framework Directive (WFD). To achieve this purpose, a group of bioassays were selected to evaluate both water and sediment compartments at the Alqueva reservoir (the biggest from the Iberian Peninsula), with representative species from different taxonomic and functional groups: Vibrio fischeri, Thamnocephalus platyurus, Daphnia magna and Heterocypris incongruens. The ecotoxicological assessment showed that sublethal endpoints (e.g., luminescence, growth or reproduction), would be more useful and sensitive to identify toxicity patterns in this type of water body. In general, the results from this ecotoxicological tool-box agreed with the potential ecological status established according to the WFD, which indicates that the bioassays complement the ecological assessment. Furthermore, the use of an ecotoxicological approach can be extremely useful, especially in cases where the biotic indices are difficult to establish, such as in man-made reservoirs. However, when pollutant concentrations are very low, and/or when nutrients and organic matter concentrations are high, the two approaches do not fit, requiring further research to determine which organisms are more sensitive and the best biotic indices to use under those conditions. (C) 2015 Elsevier B.V. All rights reserved.
- Synthesis of probabilistic fuzzy classifiers using GK clustering and bayesian estimationPublication . Ledo, L.; Delgado, M. R.; Valente de Oliveira, JOSÉThe paper presents an automatic rule-base design of probabilistic fuzzy systems developed for classification tasks. The objective here is to present a methodology that allows the user to obtain a fuzzy classifier directly from training data, in which rules' antecedents are defined on the basis of clustering techniques and probabilistic consequents allow the presence of all classes in the same individual rule, each class associated with a measure of probability. The probability measure is calculated based on Bayes' theorem using an ideal region of the rule to update a priori information. The clustering process which supports the automatic partition of the input universe is based on the Gustafson-Kessel algorithm and is associated with a principal component analysis to reduce the dimensionality of the input data, improving this way the interpretability of the resulting classifier. The proposed approach is applied to Wine, Wisconsin breast cancer, Sonar e Ionosphere data sets. Results are compared with those of two other classifiers and show that the proposed approach can be an alternative to automatically set antecedents and consequents of probabilistic fuzzy classifiers.