Wavelets and Elman neural networks for monitoring environmental variables

Abstract
An application in cultural heritage is introduced. Wavelet decomposition and Neural Networks like virtual sensors are jointly used to simulate physical and chemical measurements in specific locations of a monument. Virtual sensors, suitably trained and tested, can substitute real sensors in monitoring the monument surface quality, while the real ones should be installed for a long time and at high costs. The application of the wavelet decomposition to the environmental data series allows getting the treatment of underlying temporal structure at low frequencies. Consequently a separate training of suitable Elman Neural Networks for high/low components can be performed, thus improving the networks convergence in learning time and measurement accuracy in working time.
Anno
2007
Tipo pubblicazione
Altri Autori
Ciarlini P., Maniscalco U.
Editore
Koninklijke Vlaamse Ingenieursvereniging
Rivista
Journal of computational and applied mathematics