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

Efficient prediction of internet traffic is essential for ensuring proactivemanagement of computer networks. Nowadays, machine learning approaches showpromising performance in modeling real-world complex traffic. However, mostexisting works assumed that model training and evaluation data came fromidentical distribution. But in practice, there is a high probability that themodel will deal with data from a slightly or entirely unknown distribution inthe deployment phase. This paper investigated and evaluated machine learningperformances using eXtreme Gradient Boosting, Light Gradient Boosting Machine,Stochastic Gradient Descent, Gradient Boosting Regressor, CatBoost Regressor,and their stacked ensemble model using data from both identical and out-ofdistribution. Also, we proposed a hybrid machine learning model integratingwavelet decomposition for improving out-of-distribution prediction asstandalone models were unable to generalize very well. Our experimental resultsshow the best performance of the standalone ensemble model with an accuracy of96.4%, while the hybrid ensemble model improved it by 1% for in-distributiondata. But its performance dropped significantly when tested with threedifferent datasets having a distribution shift than the training set. However,our proposed hybrid model considerably reduces the performance gap betweenidentical and out-of-distribution evaluation compared with the standalonemodel, indicating the decomposition technique's effectiveness in the case ofout-of-distribution generalization.

Wavelet-Based Hybrid Machine Learning Model for Out-of-distribution Internet Traffic Prediction