FPGA implementation of Bayesian neural networks for a stand-alone predictor of pollutants concentration in the air

We exploit the potentials of Bayesian neural networks combined with the advantages of a VLSI implementation in order to design a stand-alone predictor system of air pollutants time series. The area under study is Villa San Giovanni, a small town located in front of the Messina Strait (Italy), whose harbor represents the main link to reach Sicily island by cars and trucks. Neural networks are powerful tools to predict air pollutants time series, but almost always they run by software programs on PC or workstations, which make difficult their use when are present constraints such as portability, low power dissipation, limited physical size. In this cases, SRAM based field programmable gate arrays (FPGAs) represent a suitable platform to realize these models, since their reprogrammability offers the possibility to rapidly change the parameters of the network if a new training is needed. The achieved results have highlighted the efficient design of the hardware network, obtained also using a new circuit to compute the activation function of the neurons.