Lightweight Machine Learning System Embedded in Smart Wearable Devices for Personalized Sport Guidance

Ming Mo, Wenfeng Shi, Jun Wang, Ye Yang, Xuyin Xu

Article
2025 / Volume 8 / Pages 1210-1230
Received 15 August 2025; Accepted 24 September 2025; Published 31 December 2025
https://doi.org/10.31881/TLR.2025.1210

Abstract
The convergence of the textile industry and electronics presents new frontiers in functional apparel. This research details a system for personalized athletic guidance, rooted in advanced textile processing and materials science. The foundation is a smart garment fabricated from a blend of synthetic fibers using industrial knitting techniques. These methods are also applicable to natural fibers such as cotton or wool for enhanced comfort. The core innovation is a novel piezoresistive yarn, developed by dip-coating a base polyester yarn with poly (3,4-ethylenedioxythiophene):polystyrene sulfonate (PEDOT:PSS), a conductive polymer. This process transforms conventional fiber into a motion-sensing element. A lightweight machine learning model is embedded within the garment’s microcontroller, enabling on-device analysis of data from the yarn sensors. This approach avoids energy-intensive cloud computing and represents a step toward sustainable development in electronic textiles by minimizing the system’s overall energy footprint. The system accurately interprets complex movements, providing real-time feedback. This work demonstrates the integration of computational intelligence directly into fiber products, showcasing a scalable manufacturing pathway for a new generation of interactive textiles and moving beyond traditional applications of materials such as leather for wearable enclosures.

Keywords
smart textiles, piezoresistive yarn, textile processing, sustainable development, fiber products