English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The decomposition of non-stationary signals is an important and challengingtask in the field of signal time-frequency analysis. In the recent two decades,many signal decomposition methods led by the empirical mode decomposition,which was pioneered by Huang et al. in 1998, have been proposed by differentresearch groups. However, they still have some limitations. For example, theyare generally prone to boundary and mode mixing effects and are not very robustto noise. Inspired by the successful applications of deep learning in fieldslike image processing and natural language processing, and given the lack inthe literature of works in which deep learning techniques are used directly todecompose non-stationary signals into simple oscillatory components, we use theconvolutional neural network, residual structure and nonlinear activationfunction to compute in an innovative way the local average of the signal, andstudy a new non-stationary signal decomposition method under the framework ofdeep learning. We discuss the training process of the proposed model and studythe convergence analysis of the learning algorithm. In the experiments, weevaluate the performance of the proposed model from two points of view: thecalculation of the local average and the signal decomposition. Furthermore, westudy the mode mixing, noise interference, and orthogonality properties of thedecomposed components produced by the proposed method. All results show thatthe proposed model allows for better handling boundary effect, mode mixingeffect, robustness, and the orthogonality of the decomposed components thanexisting methods.

RRCNN: A novel signal decomposition approach based on recurrent residue convolutional neural network