Design and Analysis of FIR Filter using Neural Network

Abstract

This paper is intended to provide an alternative approach for comparison of FIR digital filter by using neural network. This proposed approach establishes relation between (I) order and main width lobe of filter and (II) order and cutoff frequency of filter. In this paper is used FDA tool to design digital FIR filters of different orders and neural network tool box to compare different filters. As the simulation results show, the proposed neural-based method is capable of archiving a better performance for filter design.