Energy Harvesting Wearables for Activity-aware Services

Select |


Khalifa, Sara; Hassan, Mahbub; Seneviratne, Aruna; Das, Sajal


Journal Article

IEEE Internet Computing




Recent advancements in energy harvesting hardware have created an opportunity for realising battery-less wearables for continuous and pervasive human activity recognition (HAR). Unfortunately, power consumption of accelerometers used in conventional HAR is relatively high compared to the amount of power that can be practically harvested, which limits the usefulness of energy harvesting. In this paper, we propose and evaluate a novel energy harvesting wearable sensor architecture, called HARKE, for human activity recognition from kinetic energy without using any accelerometer. HARKE employs kinetic harvesting and infer human activity directly from the energy harvesting patterns without using any accelerometer. Using off-the-shelf products, we demonstrate that the voltage of a kinetic harvester exhibits distinguishable patterns to distinctly infer human activities. Our experimental results demonstrate that HARKE is as accurate as an accelerometer-based HAR, yet consuming only a small fraction of the limited harvested energy.

Data61; NICTA; wearable computing; energy harvesting; human activity recognition; internet of things.



Khalifa, Sara; Hassan, Mahbub; Seneviratne, Aruna; Das, Sajal. Energy Harvesting Wearables for Activity-aware Services. IEEE Internet Computing. 2015-09-17; 19(5):8-16. <a href="" target="_blank"></a>

Loading citation data...

Citation counts
(Requires subscription to view)