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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Activity recognition, as an important component of behavioral monitoring andintervention, has attracted enormous attention, especially in Mobile CloudComputing (MCC) and Remote Health Monitoring (RHM) paradigms. While recentlyresource constrained wearable devices have been gaining popularity, theirbattery life is limited and constrained by the frequent wireless transmissionof data to more computationally powerful back-ends. This paper proposes anultra-low power activity recognition system using a novel adaptive compressedsensing technique that aims to minimize transmission costs. Coarse-grainedon-body sensor localization and unsupervised clustering modules are devised toautonomously reconfigure the compressed sensing module for further powersaving. We perform a thorough heuristic optimization using GrammaticalEvolution (GE) to ensure minimal computation overhead of the proposedmethodology. Our evaluation on a real-world dataset and a low power wearablesensing node demonstrates that our approach can reduce the energy consumptionof the wireless data transmission up to $81.2\%$ and $61.5\%$, with up to$60.6\%$ and $35.0\%$ overall power savings in comparison with baseline and anaive state-of-the-art approaches, respectively. These solutions lead to anaverage activity recognition accuracy of $89.0\%$ -- only $4.8\%$ less than thebaseline accuracy -- while having a negligible energy overhead of on-nodecomputation.

Toward Ultra-Low-Power Remote Health Monitoring: An Optimal and Adaptive Compressed Sensing Framework for Activity Recognition