Machine learning facilitated gesture recognition using structural optimized wearable yarn-based strain sensor

The advancement of wearable sensing technologies demands multifunctional materials that integrate high sensitivity, environmental resilience, and intelligent signal processing. In this work, a flexible hydrophobic conductive yarn (FCB@SY) featuring a controllable microcrack structure is developed via a synergistic approach combining ultrasonic swelling and non-solvent induced phase separation (NIPS). By embedding a robust conductive network and engineering microcrack morphology, the resulting sensor achieves an ultrahigh gauge factor (GF ≈ 12,670), an ultrabroad working range (0%–547%), a low detection limit (0.5%), rapid response/recovery time (140 ms/140 ms), and outstanding durability over 10,000 cycles. Furthermore, the hydrophobic surface endowed by conductive coatings imparts exceptional chemical stability against acidic and alkaline environments, as well as reliable waterproof performance. This enables consistent functionality under harsh conditions, including underwater operation. Integrated with machine learning algorithms, the FCB@SY-based intelligent sensing system demonstrates dual-mode capabilities in human motion tracking and gesture recognition, offering significant potential for applications in wearable electronics, human–machine interfaces, and soft robotics.