Facilitating privacy-preserving activity recognition in age-friendly environments through low-power devices

Abstract

Advances in the Internet of Things (IoT) technologies are being applied in various industries, but lately, they are also finding applications in home-based healthcare systems. Such pervasive healthcare systems aim to enable older adults to receive better and more cost-effective care in their preferred home environment. Battery-powered IoT devices are essential for low-cost deployment, especially in rural areas. However, one of the main challenges for any battery-powered device is energy management so that the period between battery changes is prolonged. This paper proposes an energy-saving approach for a non-invasive passive infrared (PIR) sensor. The proposed method can put the device into a deep sleep to minimize the energy consumption and use hardware wake-up interrupts to make it functional again. The analyzed sensor kit allows the detection of persons, including recognition of their actions, while preserving the privacy of the person. This is very important for age-friendly environments where privacypreserving is essential.