Browsing by Author "Oliveira, J. V."
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Anti-Phytophthora cinnamomi activity of Phlomis purpurea plant and root extractsPublication . Neves, D.; Caetano, P.; Oliveira, J. V.; Maia, Cristiana; Sousa, N.; Salgado, M.; Dionisio, L.; Magan, N.; Cravador, A.Phlomis purpurea (Lamiaceae), found in Quercus suber and Quercus ilex ssp. rotundifolia forest habitats in southern Portugal, is a non-host for the oomycete Phytophthora cinnamomi, the main biotic factor involved in cork oak and holm oak decline in the Iberian Peninsula. The effect of P. purpurea crude ethanol root extract was evaluated in vitro on P. cinnamomi mycelial growth, sporangial production, zoospore release and germination as well as on chlamydospore production and viability. The protection of cork oak against infection by the pathogen was also evaluated in planta. At 10 mg ml-1, in vitro inhibition of the pathogen structures was 85-100 %. In addition, P. purpurea plants were shown to protect Q. suber and Q. ilex from P. cinnamomi infection and to reduce the inoculum potential in glasshouse trials, indicating the ability to reduce root infection by the pathogen. The results suggest that P. purpurea has the potential to reduce disease spread and that their root extracts could provide candidate substances for control of the important pathogen, P. cinnamomi. © 2013 KNPV.
- Completely supervised training algorithms for B-spline neural networks and neuro-fuzzy systemsPublication . Ruano, Antonio; Cabrita, Cristiano Lourenço; Oliveira, J. V.; Kóczy, László T.Complete supervised training algorithms for B-spline neural networks and fuzzy rule-based systems are discussed. By interducing the relationship between B-spline neural networks and certain types of fuzzy models, training algorithms developed initially for neural networks can be adapted by fuzzy systems.
- Supervised training algorithms for B-spline neural networks and fuzzy systemsPublication . Ruano, Antonio; Cabrita, Cristiano Lourenço; Oliveira, J. V.; Tikk, D.; Kóczy, László T.Complete supervised training algorithms for B-spline neural networks and fuzzy rule-based systems are discussed. By introducing the relationships between B-spline neural networks and Mamdani (satisfying certain assumptions) fuzzy model, training algorithms developed initially for neural networks can be adapted to fuzzy systems. The standard training criterion is reformulated, by separating the linear and nonlinear parameters. By employing this reformulated criterion with the Levenberg-Marquardt algorithm, a new training method, offering a fast rate of convergence is obtained. It is also shown that the standard Error-Back Propagation algorithm, the most common training method for this class of systems, exhibits a very poor performance.
- Supervised training algorithms for B-Spline neural networks and neuro-fuzzy systemsPublication . Ruano, Antonio; Cabrita, Cristiano Lourenço; Oliveira, J. V.; Kóczy, László T.Complete supervised training algorithms for B-Spline neural networks and fuzzy rulebased systems are discussed. By introducing the relationships between B-Spline neural networks and Mamdani (satisfying certain assumptions) and Takagi±Kang±Sugeno fuzzy models, training algorithms developed initially for neural networks can be adapted to fuzzy systems. The standard training criterion is reformulated, by separating its linear and nonlinear parameters. By employing this reformulated criterion with the Levenberg-Marquardt algorithm, a new training method, offering a fast rate of convergence is obtained. It is also shown that the standard Error-Back Propagation algorithm, the most common training method for this class of systems, exhibits a very poor and unreliable performance.