PROJECT TITLE :

HARKE: Human Activity Recognition from Kinetic Energy Harvesting Data in Wearable Devices - 2018

ABSTRACT:

Kinetic energy harvesting (KEH) may facilitate combat battery problems in wearable devices. Whereas the primary objective of KEH is to come up with energy from human activities, the harvested energy itself contains info about human activities that the majority wearable devices try to detect using motion sensors. In principle, it is therefore doable to use KEH both as an influence generator and a sensor for human activity recognition (HAR), saving sensor-related power consumption. Our aim is to quantify the potential of human activity recognition from kinetic energy harvesting (HARKE). We evaluate the performance of HARKE using 2 independent datasets: (i) a public accelerometer dataset converted into KEH knowledge through theoretical modeling; and (ii) a true KEH dataset collected from volunteers performing activities of daily living whereas carrying a data-logger that we tend to engineered of a piezoelectric energy harvester. Our results show that HARKE achieves an accuracy of eighty to ninety five %, relying on the dataset and the placement of the device on the human body. We conduct detailed power consumption measurements to understand and quantify the ability saving chance of HARKE. The results demonstrate that HARKE can save seventy nine percent of the system power consumption of conventional accelerometer-primarily based HAR.