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

Area of Science:

• Wearable Technology
• Artificial Intelligence
• Wireless Communication

Background:

• Wearable devices are increasingly integrated into daily life, primarily for monitoring functions.
• Current wearables have hardware and power limitations, relying on master devices like smartphones for data processing and cloud connectivity.
• The evolution of wearables is driven by advancements in communication and AI technologies.

Purpose of the Study:

• To review and discuss the integration of Low-Power Wide-Area Network (LPWAN) and Tiny Machine Learning (TinyML) in wearable devices.
• To explore the implications and challenges of incorporating these advanced technologies into wearables.
• To experimentally analyze the long-range connectivity and embedded intelligence capabilities of LPWAN-enabled wearables.

Main Methods:

• Review of LPWAN and TinyML technologies for wearable applications.
• Experimental study on a wearable device integrated with LPWAN communication.
• Analysis of connectivity range in a university campus scenario.
• Evaluation of the complexity of embedded intelligence in wearable units.

Main Results:

• LPWAN integration significantly enhances the long-range connectivity of wearable devices.
• Wearables can embed sophisticated intelligence, moving beyond simple monitoring tasks.
• The experimental study demonstrated the feasibility and benefits of these advanced technologies in a real-world setting.

Conclusions:

• LPWAN and TinyML are transformative technologies for the next generation of wearables.
• These advancements enable a wider array of novel services and applications.
• Future wearables will offer greater independence and sophisticated functionalities.