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

Despite the vast literature on Human Activity Recognition (HAR) with wearableinertial sensor data, it is perhaps surprising that there are few studiesinvestigating semisupervised learning for HAR, particularly in a challengingscenario with class imbalance problem. In this work, we present a newbenchmark, called A*HAR, towards semisupervised learning for class-imbalancedHAR. We evaluate state-of-the-art semi-supervised learning method on A*HAR, bycombining Mean Teacher and Convolutional Neural Network. Interestingly, we findthat Mean Teacher boosts the overall performance when training the classifierwith fewer labelled samples and a large amount of unlabeled samples, but theclassifier falls short in handling unbalanced activities. These findings leadto an interesting open problem, i.e., development of semi-supervised HARalgorithms that are class-imbalance aware without any prior knowledge on theclass distribution for unlabeled samples. The dataset and benchmark evaluationare released at https://github.com/I2RDL2/ASTAR-HAR for future research.

A*HAR: A New Benchmark towards Semi-supervised learning for Class-imbalanced Human Activity Recognition