showing 2 related works from this author
Optimization of Osmotic Desalination Plants for Water Supply Networks
2016
Water scarcity and the poor quality of water resources are leading to a wider diffusion of desalination plants using the Reverse Osmosis (RO) process. Unfortunately, the cost of a cubic meter of fresh water produced by an RO plants is still high and many efforts are in progress to increase the efficiency of the membranes used in osmotic plants and to limit the energy required by the process. A further reduction of the energy cost could be obtained by an optimal operation of the desalination plant so reducing the hourly energy cost, or by coupling the RO plant with an energy production plant based on direct osmosis (Pressure Retarded Osmosis PRO). The economic viability of the desalination p…
INFERENCE BASED ON RESAMPLING TECHNIQUES FOR NEURAL NETWORKS IN REGRESSION MODELS
2000
Let {Yt}, t=1,..., T be a time series generated according to the model: Yt=f(Xt)+et t=1, ..., T where f is a non linear continuous function, Xt = (X1t, X2t, ...,Xdt) is a vector of d non stochastic explanatory variables defined on a compact X belonging Rd , and {et} are zero mean random variables with constant variance. The function f in the previous model can be approximated with a feed-forward neural networks. Many authors (Hornik et al., 1989 inter alia) showed that, under general regularity conditions, a sufficiently complex single hidden layer feedforward network can approximate any member of a class of function to any degree of accuracy. Of course to consider them a statistical techni…