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

The use of supervised learning for Human Activity Recognition (HAR) on mobiledevices leads to strong classification performances. Such an approach, however,requires large amounts of labeled data, both for the initial training of themodels and for their customization on specific clients (whose data often differgreatly from the training data). This is actually impractical to obtain due tothe costs, intrusiveness, and time-consuming nature of data annotation.Moreover, even with the help of a significant amount of labeled data, modeldeployment on heterogeneous clients faces difficulties in generalizing well onunseen data. Other domains, like Computer Vision or Natural LanguageProcessing, have proposed the notion of pre-trained models, leveraging largecorpora, to reduce the need for annotated data and better manage heterogeneity.This promising approach has not been implemented in the HAR domain so farbecause of the lack of public datasets of sufficient size. In this paper, wepropose a novel strategy to combine publicly available datasets with the goalof learning a generalized HAR model that can be fine-tuned using a limitedamount of labeled data on an unseen target domain. Our experimental evaluation,which includes experimenting with different state-of-the-art neural networkarchitectures, shows that combining public datasets can significantly reducethe number of labeled samples required to achieve satisfactory performance onan unseen target domain.

Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity