Extending the battery lifetime of wearable sensors with embedded machine learning

TLDR

Smart health home systems depend on energy‑constrained wearable sensors for data generation and wireless communication, yet frequent battery recharging burdens maintenance and limits cost‑effectiveness, especially for elderly or chronically ill users, while raw data is processed into knowledge by reasoning and machine learning algorithms. This paper investigates the benefits of embedding machine learning on the wearable sensor to extract knowledge locally instead of transmitting raw data over a low‑power network. The authors embed machine learning on the sensor to perform local knowledge extraction, reducing the need to transmit raw data. In a simple classification task with an accelerometer‑based wearable sensor, embedded machine learning cut radio and processor duty cycles by several orders of magnitude, substantially extending battery life.

Abstract

Smart health home systems and assisted living architectures rely on severely energy-constrained sensing devices, such as wearable sensors, for the generation of data and their reliable wireless communication to a central location. However, the need for recharging the battery regularly constitutes a maintenance burden that hinders the long-term cost-effectiveness of these systems, especially for health-oriented applications that target people in need, such as the elderly or the chronically ill. These sensing systems generate raw data that is processed into knowledge by reasoning and machine learning algorithms. This paper investigates the benefits of embedded machine learning, i.e. executing this knowledge extraction on the wearable sensor, instead of communicating abundant raw data over the low power network. Focusing on a simple classification task and using an accelerometer-based wearable sensor, we demonstrate that embedded machine learning has the potential to reduce the radio and processor duty cycle by several orders of magnitude; and, thus, substantially extend the battery lifetime of resource-constrained wearable sensors.