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

It has been demonstrated that the amount of data is crucial in data-drivenmachine learning methods. Data is always valuable, but in some tasks, it isalmost like gold. This occurs in engineering areas where data is scarce or veryexpensive to obtain, such as predictive maintenance, where faults are rare. Inthis context, a mechanism to generate synthetic data can be very useful. Whilein fields such as Computer Vision or Natural Language Processing synthetic datageneration has been extensively explored with promising results, in otherdomains such as time series it has received less attention. This workspecifically focuses on studying and analyzing the use of different techniquesfor data augmentation in time series for classification and regressionproblems. The proposed approach involves the use of diffusion probabilisticmodels, which have recently achieved successful results in the field of ImageProcessing, for data augmentation in time series. Additionally, the use ofmeta-attributes to condition the data augmentation process is investigated. Theresults highlight the high utility of this methodology in creating syntheticdata to train classification and regression models. To assess the results, sixdifferent datasets from diverse domains were employed, showcasing versatilityin terms of input size and output types. Finally, an extensive ablation studyis conducted to further support the obtained outcomes.

D3A-TS: Denoising-Driven Data Augmentation in Time Series