FPGA implementation of neural network as processing element in ice detector

Abstract

In this paper we propose usage of neural networks in the field of meteorology especially to detect ice formation on roads. Used algorithm for building and training network is based on the road and air conditions which define ice formation on road's surface. The ability of self and supervised learning are both used to solve this problem. We used VHDL to build proposed neural network as a part of the ice detector. FPGA implementation of the neural network is done using Xilinx Spartan-3 device.