Traditional biometric technologies, including fingerprint, iris, and facial recognition, have been widely deployed for identity verification but remain constrained by privacy risks and environmental sensitivities. In contrast, gait recognition has emerged as a promising behavioral biometric due to its non-intrusive nature and difficulty of being disguised. Herein, we proposed a gait recognition method based on multi-sensor fusion and multi-scale feature extraction. Plantar pressure distribution and limb acceleration data were synchronously acquired via a custom-developed smart pressure insole integrated with an inertial measurement unit (IMU), enabling an end-to-end recognition pipeline. A lightweight parallel dual-branch (LPDB) attention module was designed to reduce computational overhead, while a multi-scale feature fusion (MSFF) method effectively integrated heterogeneous sensor data, capturing structural invariants within gait cycles and enhancing cross-cycle consistency. The system achieved a recognition accuracy of 98.5%. Furthermore, the piezoresistive sensor fabricated for the smart insole incorporated disordered nanofibers to form a hierarchical micro-protrusion conductive network, yielding a high sensitivity of 45.4 kPa⁻¹ in low-pressure regimes, significantly surpassing conventional porous material-based sensors. In addition, the as-prepared sensor exhibited superior anti-counterfeiting properties to facial features or fingerprints. This work offered a robust, privacy-preserving identification solution with potential applications in medical rehabilitation, sports science, robotic control, and the artificial intelligence of things (AIoT).

With the rapid development of wearable electronics, flexible pressure sensors have attracted wide attention in human–computer interaction and intelligent machines. However, it is a challenge to achieve a sensor with high sensitivity, wide measurement range, and wearing comfortability. Here, we develop an oriented electrospinning thermoplastic polyurethane/polyacrylonitrile (TPU/PAN) nanofibers (OETPN) based piezoresistive pressure sensor (PONPS) in which the active layer and the electrode are assembled perpendicularly. The interdigital electrode is fabricated by spraying silver nanowires (AgNWs) on the OETPN through a mask plate. The active layer is composed of OETPN coated with MXene, encapsulated on the electrode by polyurethane (PU) film. The porous structure of nanofibers membrane broadens the measurement range of the sensor. Employing oriented nanofibers as active layer can improve the sensitivity in low pressure, because oriented nanofibers without interweaving nanofibers are more compressible than disordered nanofibers. Electrode prepared using the spraying method creates nanoscale microstructure and increases sensitivity. The perpendicular assembly has greater response between the active layer and the electrode than the parallel assembly to improve the sensitivity. The sensor exhibits high sensitivity (6.71 kPa⁻¹, 0.02–2 kPa) and wide measurement range (0.02–700 kPa). The sensor can detect weak signals such as radial artery. A pressure array constructed precisely represents the distribution of pressure. An intelligent throat is created by combining machine learning algorithms with the PONPS. It can detect and recognize subtle throat vibrations while speaking, achieving recognition accuracy up to 100% using support vector machine (SVM) for five words with different syllables. The fabricated sensor shows promising prospects in personal healthcare and intelligent robots.

Triboelectric nanogenerators (TENGs) have recently drawn much attention in the field of biomechanical energy harvesting and motion monitoring. However, the electrode stretchability and contact-separation model induced complicated packed structure remain a problem that heavily affects output performance during various human movements and requires to be urgently addressed. Here, a single-electrode piezo-triboelectric hybrid nanogenerator (SEP-TENG) integrated with stretchable liquid-metal metal electrodes is reported, which simultaneously achieves outstanding energy harvesting performance and skin-comfort human motion monitoring. A polarized piezoelectric BaTiO₃/silicon rubber (SR) composites film is served as the effective negative tribomaterial, benefiting from the improved dielectric constant and piezoelectric charge transfer, the optimized SEP-TENG generates a high peak power density of 5.7 W/m² while contacted with human skin. Besides, owing to the ultralow Young's modulus of the SR encapsulation layer and tribo-piezoelectric hybrid layer, the homogeneous integrated multilayer composite serves no break till a 745% elongation, promoting that the SEP-TENG could effectively harvest biomechanical energy and realize stable power supplying for wearable electronics even under large deformation state. Furthermore, the SEP-TENG could comfortably attach to the finger joints and collect bending energy. This work provides a novel design methodology for a single-electrode TENG to realize omnidirectional biomechanical energy harvesting and motion monitoring.