Improvements to the Sliding Discrete Fourier Transform Algorithm

Abstract

This article presents two networks that improve upon the behavior and performance of previously published sliding discrete Fourier transform (SDFT) algorithms. The proposed networks are structurally simple, computationally efficient, guaranteed stable networks used for real-time sliding spectrum analysis. The first real-time network computes one spectral output sample, equal to a single-bin output of an N-point DFT, for each input signal sample. The second real-time network is frequency flexible, in that its analysis frequency can be any scalar value in the range of zero to one-half the input data sample rate measured in cycles per second.