IRCNN$^{+}$: An Enhanced Iterative Residual Convolutional Neural Network for Non-stationary Signal Decomposition

TL;DR

This paper introduces an enhanced version of IRCNN, a deep learning-based method for decomposing non-stationary signals, improving stability and efficiency in time-frequency analysis compared to traditional approaches.

Contribution

The paper presents an improved IRCNN model incorporating advanced deep learning techniques to better handle non-stationary signals and address previous limitations.

Findings

Achieves more stable signal decomposition

Handles large-scale signals with low computational cost

Improves time-frequency analysis accuracy

Abstract

Time-frequency analysis is an important and challenging task in many applications. Fourier and wavelet analysis are two classic methods that have achieved remarkable success in many fields. However, they also exhibit limitations when applied to nonlinear and non-stationary signals. To address this challenge, a series of nonlinear and adaptive methods, pioneered by the empirical mode decomposition method, have been proposed. The goal of these methods is to decompose a non-stationary signal into quasi-stationary components that enhance the clarity of features during time-frequency analysis. Recently, inspired by deep learning, we proposed a novel method called iterative residual convolutional neural network (IRCNN). IRCNN not only achieves more stable decomposition than existing methods but also handles batch processing of large-scale signals with low computational cost. Moreover, deep learning provides a unique perspective for non-stationary signal decomposition. In this study, we aim to further improve IRCNN with the help of several nimble techniques from deep learning and optimization to ameliorate the method and overcome some of the limitations of this technique.