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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper analyzes the wavelet multiresolution theory, and adopts the energy information obtained from every decomposition layer of the wavelet as partial feature information of the original signals. According to design ideas and advantages of the traditional wavelet threshold function, a network stability monitoring model based on feature extraction of the improved wavelet function. The improved wavelet threshold function integrates advantages of the traditional threshold function and efficiently overcomes flaws of the traditional threshold function. At last, the network flow data are collected and the wavelet threshold function after optimization and improvement is adopted for feature extraction. The signal feature value thus obtained is used to train the BP network. After training, the BP network undergoes the network stability monitoring test. Results suggest that the improved wavelet function can not only efficiently remove signal noises, but also maintain the feature information of signals. Besides, through network stability monitoring test, the final network stability monitoring accuracy of feature extraction of signals based on the improved wavelet function is 8%~10% higher than the traditional threshold function.

Network Stability of Feature Extraction Based on Improved Wavelet Function