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

Many real-world applications involve multivariate, geo-tagged time seriesdata: at each location, multiple sensors record corresponding measurements. Forexample, air quality monitoring system records PM2.5, CO, etc. The resultingtime-series data often has missing values due to device outages orcommunication errors. In order to impute the missing values, state-of-the-artmethods are built on Recurrent Neural Networks (RNN), which process each timestamp sequentially, prohibiting the direct modeling of the relationship betweendistant time stamps. Recently, the self-attention mechanism has been proposedfor sequence modeling tasks such as machine translation, significantlyoutperforming RNN because the relationship between each two time stamps can bemodeled explicitly. In this paper, we are the first to adapt the self-attentionmechanism for multivariate, geo-tagged time series data. In order to jointlycapture the self-attention across multiple dimensions, including time, locationand the sensor measurements, while maintain low computational complexity, wepropose a novel approach called Cross-Dimensional Self-Attention (CDSA) toprocess each dimension sequentially, yet in an order-independent manner. Ourextensive experiments on four real-world datasets, including three standardbenchmarks and our newly collected NYC-traffic dataset, demonstrate that ourapproach outperforms the state-of-the-art imputation and forecasting methods. Adetailed systematic analysis confirms the effectiveness of our design choices.

CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation