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

AI models have garnered significant research attention towards predictivetask automation. However, a stationary training environment is an underlyingassumption for most models and such models simply do not work on non-stationarydata since a stationary relationship is learned. The existing solutions proposemaking data stationary prior to model training and evaluation. This leads toloss of trend and seasonal patterns which are vital components for learningtemporal dependencies of the system under study. This research aims to addressthis limitation by proposing a method for enforcing stationary behaviour withinthe latent space while preserving trend and seasonal information. The methoddeploys techniques including Differencing, Time-series decomposition, andLatent Space Arithmetic (LSA), to learn information vital for efficientapproximation of trend and seasonal information which is then stored asembeddings within the latent space of a Variational Autoencoder (VAE). Theapproach's ability to preserve trend and seasonal information was evaluated ontwo time-series non-stationary datasets. For predictive performance evaluation,four deep learning models were trained on the latent vector representations ofthe datasets after application of the proposed method and all models producedcompetitive results in comparison with state-of-the-art techniques using RMSEas the performance metric.

Preserving Seasonal and Trend Information: A Variational Autoencoder-Latent Space Arithmetic Based Approach for Non-stationary Learning