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

Data augmentation in deep neural networks is the process of generatingartificial data in order to reduce the variance of the classifier with the goalto reduce the number of errors. This idea has been shown to improve deep neuralnetwork's generalization capabilities in many computer vision tasks such asimage recognition and object localization. Apart from these applications, deepConvolutional Neural Networks (CNNs) have also recently gained popularity inthe Time Series Classification (TSC) community. However, unlike in imagerecognition problems, data augmentation techniques have not yet beeninvestigated thoroughly for the TSC task. This is surprising as the accuracy ofdeep learning models for TSC could potentially be improved, especially forsmall datasets that exhibit overfitting, when a data augmentation method isadopted. In this paper, we fill this gap by investigating the application of arecently proposed data augmentation technique based on the Dynamic Time Warpingdistance, for a deep learning model for TSC. To evaluate the potential ofaugmenting the training set, we performed extensive experiments using the UCRTSC benchmark. Our preliminary experiments reveal that data augmentation candrastically increase deep CNN's accuracy on some datasets and significantlyimprove the deep model's accuracy when the method is used in an ensembleapproach.

Data augmentation using synthetic data for time series classification with deep residual networks