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

Neural networks have become a powerful tool in pattern recognition and partof their success is due to generalization from using large datasets. However,unlike other domains, time series classification datasets are often small. Inorder to address this problem, we propose a novel time series data augmentationcalled guided warping. While many data augmentation methods are based on randomtransformations, guided warping exploits the element alignment properties ofDynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shapedescriptors, to deterministically warp sample patterns. In this way, the timeseries are mixed by warping the features of a sample pattern to match the timesteps of a reference pattern. Furthermore, we introduce a discriminativeteacher in order to serve as a directed reference for the guided warping. Weevaluate the method on all 85 datasets in the 2015 UCR Time Series Archive witha deep convolutional neural network (CNN) and a recurrent neural network (RNN).The code with an easy to use implementation can be found athttps://github.com/uchidalab/time_series_augmentation .

Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher