Spectral analysis of signals by time-domain statistical characterization and neural network processing: Application to correction of spectral amplitude alterations in pulse-like waveforms

TL;DR

This paper introduces a fast time-domain method utilizing statistical features and neural networks to detect and correct spectral amplitude distortions in pulse-like signals, suitable for real-time embedded applications.

Contribution

The paper presents a novel, computationally efficient approach combining statistical waveform analysis and neural networks for spectral correction in pulse signals.

Findings

Effective correction of spectral amplitude attenuation demonstrated

Algorithm operates with low computational cost

Suitable for real-time embedded systems

Abstract

We present a time-domain method to detect and correct spectral alterations of signals by employing statistical characterization of waveforms and a pattern-recognition procedure using simple Artificial Neural Networks. The proposed strategy implements very-fast routines with a computational cost proportional to the number of signal samples, being convenient for applications in embedded environments with limited computational capabilities or fast real-time control tasks. We use the proposed algorithms to correct spectral amplitude attenuations in a pulse-like waveform with a sinc profile as an application example.