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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Time series forecasting is widely used in the fields of equipment life cycleforecasting, weather forecasting, traffic flow forecasting, and other fields.Recently, some scholars have tried to apply Transformer to time seriesforecasting because of its powerful parallel training ability. However, theexisting Transformer methods do not pay enough attention to the small timesegments that play a decisive role in prediction, making it insensitive tosmall changes that affect the trend of time series, and it is difficult toeffectively learn continuous time-dependent features. To solve this problem, wepropose a differential attention fusion model based on Transformer, whichdesigns the differential layer, neighbor attention, sliding fusion mechanism,and residual layer on the basis of classical Transformer architecture.Specifically, the differences of adjacent time points are extracted and focusedby difference and neighbor attention. The sliding fusion mechanism fusesvarious features of each time point so that the data can participate inencoding and decoding without losing important information. The residual layerincluding convolution and LSTM further learns the dependence between timepoints and enables our model to carry out deeper training. A large number ofexperiments on three datasets show that the prediction results produced by ourmethod are favorably comparable to the state-of-the-art.

A Differential Attention Fusion Model Based on Transformer for Time Series Forecasting