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/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

We propose a novel way of solving the issue of classification ofout-of-vocabulary gestures using Artificial Neural Networks (ANNs) trained inthe Generative Adversarial Network (GAN) framework. A generative model augmentsthe data set in an online fashion with new samples and stochastic targetvectors, while a discriminative model determines the class of the samples. Theapproach was evaluated on the UC2017 SG and UC2018 DualMyo data sets. Thegenerative models performance was measured with a distance metric betweengenerated and real samples. The discriminative models were evaluated by theiraccuracy on trained and novel classes. In terms of sample generation quality,the GAN is significantly better than a random distribution (noise) in meandistance, for all classes. In the classification tests, the baseline neuralnetwork was not capable of identifying untrained gestures. When the proposedmethodology was implemented, we found that there is a trade-off between thedetection of trained and untrained gestures, with some trained samples beingmistaken as novelty. Nevertheless, a novelty detection accuracy of 95.4% or90.2% (depending on the data set) was achieved with just 5% loss of accuracy ontrained classes.

Improving novelty detection with generative adversarial networks on hand gesture data