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

Human activity recognition (HAR) is an important research field in ubiquitouscomputing where the acquisition of large-scale labeled sensor data is tedious,labor-intensive and time consuming. State-of-the-art unsupervised remediesinvestigated to alleviate the burdens of data annotations in HAR mainly exploretraining autoencoder frameworks. In this paper: we explore generativeadversarial network (GAN) paradigms to learn unsupervised featurerepresentations from wearable sensor data; and design a new GANframework-Geometrically-Guided GAN or Guided-GAN-for the task. To demonstratethe effectiveness of our formulation, we evaluate the features learned byGuided-GAN in an unsupervised manner on three downstream classificationbenchmarks. Our results demonstrate Guided-GAN to outperform existingunsupervised approaches whilst closely approaching the performance with fullysupervised learned representations. The proposed approach paves the way tobridge the gap between unsupervised and supervised human activity recognitionwhilst helping to reduce the cost of human data annotation tasks.

Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables