A neural network based identification system for VIRGO seismic noise

In this paper a Neural Network-based approach is presented for the real time seismic noise identification of GW laser interferometric antenna. The procedure allows the estimation of seismic events in a background noise. The recognition of such events is very important for the data quality of the interferometer output. The algorithm we propose is quite general and robust, taking into account that it does not requires a-priori informations on the data, nor precise model, and constitute a powerful tool for quality data analysis.