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

Sensor data streams from wearable devices and smart environments are widelystudied in areas like human activity recognition (HAR), person identification,or health monitoring. However, most of the previous works in activity andsensor stream analysis have been focusing on one aspect of the data, e.g. onlyrecognizing the type of the activity or only identifying the person whoperformed the activity. We instead propose an approach that uses a weaklysupervised multi-output siamese network that learns to map the data intomultiple representation spaces, where each representation space focuses on oneaspect of the data. The representation vectors of the data samples arepositioned in the space such that the data with the same semantic meaning inthat aspect are closely located to each other. Therefore, as demonstrated witha set of experiments, the trained model can provide metrics for clustering databased on multiple aspects, allowing it to address multiple tasks simultaneouslyand even to outperform single task supervised methods in many situations. Inaddition, further experiments are presented that in more detail analyze theeffect of the architecture and of using multiple tasks within this framework,that investigate the scalability of the model to include additional tasks, andthat demonstrate the ability of the framework to combine data for which onlypartial relationship information with respect to the target tasks is available.

Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables