LPWAN and Embedded Machine Learning as Enablers for the Next Generation of Wearable Devices.

Ramon Sanchez-Iborra

doi:10.3390/s21155218

Abstract

The penetration of wearable devices in our daily lives is unstoppable. Although they are very popular, so far, these elements provide a limited range of services that are mostly focused on monitoring tasks such as fitness, activity, or health tracking. Besides, given their hardware and power constraints, wearable units are dependent on a master device, e.g., a smartphone, to make decisions or send the collected data to the cloud. However, a new wave of both communication and artificial intelligence (AI)-based technologies fuels the evolution of wearables to an upper level. Concretely, they are the low-power wide-area network (LPWAN) and tiny machine-learning (TinyML) technologies. This paper reviews and discusses these solutions, and explores the major implications and challenges of this technological transformation. Finally, the results of an experimental study are presented, analyzing (i) the long-range connectivity gained by a wearable device in a university campus scenario, thanks to the integration of LPWAN communications, and (ii) how complex the intelligence embedded in this wearable unit can be. This study shows the interesting characteristics brought by these state-of-the-art paradigms, concluding that a wide variety of novel services and applications will be supported by the next generation of wearables.

Highlights

The wearable industry has notably evolved during the last years
The focus was on the low-power wide-area network (LPWAN) and embedded machine learning (ML) paradigms
Regarding LPWANs, they enable long-range transmissions with limited energy consumption, which permits end-devices to directly connect to the network infrastructure without using another paired element as a relay, e.g., a smartphone

Summary

Introduction

The wearable industry has notably evolved during the last years. From the first devices, which could be worn as accessories, e.g., wristbands or glasses, or integrated within clothing, e.g., footwear sensors, currently novel solutions that are tattooed or implanted in the body are gaining momentum [1]. The Internet of Things (IoT) and AI paradigms have been a great revolution for the digitalization of many vertical industries Nowadays, they have evolved enough to be adopted by the wearable industry, aiming at producing truly autonomous and intelligent devices. The development of transmission technologies permitting long-distance communications with a highly limited energy consumption, has been one of the great achievements in the IoT ecosystem during the recent years [8]. This family of technologies, so-called LPWAN, is receiving great attention, given the almost omnipresence of connected devices in different scenarios, namely, urban, rural, aerial, etc., where a pre-existent communication infrastructure is not always present. These transmission distances are achieved with very low-power consumption, which is comparable to that of wireless sensor network (WSN) technologies, such as Zigbee or

Objectives

Findings

Discussion

Conclusion