• • 1D-CNN achieves 99.6% classification accuracy on human motion datasets after 16 training epochs with loss convergence, enabling reliable real-time motion recognition for immersive capture and intelligent feedback systems.
• • Under Gaussian noise with standard deviations of 150 and 200, the CNN model maintains 97.3% and 93.8% accuracy, respectively, demonstrating robust feature extraction and noise suppression critical for deployment in uncontrolled environments.
• • Spraying 0.1 mL water on sensor surfaces yields 98.6% accuracy, confirming resilience to sweat and humidity—a key requirement for wearable health monitoring where perspiration is inevitable.
• • The all-textile sensor eliminates metallic electrodes and petroleum-based polymers, using conductivity-modulable polypyrrole on cotton fabrics, which ensures biocompatibility, biodegradability, and breathability while maintaining high sensitivity and wide detection range.