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

Long-term time series forecasting is a vital task and has a wide range ofreal applications. Recent methods focus on capturing the underlying patternsfrom one single domain (e.g. the time domain or the frequency domain), and havenot taken a holistic view to process long-term time series from thetime-frequency domains. In this paper, we propose a Time-Frequency EnhancedDecomposed Network (TFDNet) to capture both the long-term underlying patternsand temporal periodicity from the time-frequency domain. In TFDNet, we devise amulti-scale time-frequency enhanced encoder backbone and develop two separatetrend and seasonal time-frequency blocks to capture the distinct patternswithin the decomposed trend and seasonal components in multi-resolutions.Diverse kernel learning strategies of the kernel operations in time-frequencyblocks have been explored, by investigating and incorporating the potentialdifferent channel-wise correlation patterns of multivariate time series.Experimental evaluation of eight datasets from five benchmark domainsdemonstrated that TFDNet is superior to state-of-the-art approaches in botheffectiveness and efficiency.

TFDNet: Time-Frequency Enhanced Decomposed Network for Long-term Time Series Forecasting