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

In this paper we propose a data augmentation method for time series withirregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN).Our approach is based on Conditional Generative Adversarial Networks (CGAN),where the generative step is implemented by a deconvolutional NN and thediscriminative step by a convolutional NN. Both the generator and thediscriminator are conditioned on the sampling timestamps, to learn the hiddenrelationship between data and timestamps, and consequently to generate new timeseries. We evaluate our model with synthetic and real-world datasets. For thesynthetic data, we compare the performance of a classifier trained withT-CGAN-generated data, against the performance of the same classifier trainedon the original data. Results show that classifiers trained on T-CGAN-generateddata perform the same as classifiers trained on real data, even with very shorttime series and small training sets. For the real world datasets, we compareour method with other techniques of data augmentation for time series, such astime slicing and time warping, over a classification problem with unbalanceddatasets. Results show that our method always outperforms the other approaches,both in case of regularly sampled and irregularly sampled time series. Weachieve particularly good performance in case with a small training set andshort, noisy, irregularly-sampled time series.

T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling