Embedded AI-Enabled Wearable Piezoelectric Sensing Cluster for Real-Time Multijoint Motion Recognition

Abstract

Wearable motion recognition holds significant promise in rehabilitation medicine and human–machine interaction. However, they face challenges like signal susceptibility to interference and limited back-end processing capabilities. This work reports a novel embedded artificial intelligence-enabled sensor cluster featuring high assembly flexibility, good anti-interference ability, and sensor nodes that autonomously process data, enabling real-time recognition of multiple joint movements. Polyvinylidene fluoride-based membranes for piezoelectric sensors exhibit high piezoelectric properties due to interface enhancement mechanisms resulting from hot-pressing and rapid annealing. The well-designed differential structure enhances the signal-to-noise ratio of the piezoelectric sensor to 72.5 dB, outperforming other reported polymer-based flexible piezoelectric sensors (31 dB). The single-joint recognition system used to build the cluster is equipped with a 12-channel sensor array and a miniaturized signal-conditioning circuit, which can real-time recognize 20 different joint movements via a lightweight convolutional neural network model deployed on a microcontroller. Finally, the distributed multijoint motion recognition cluster adopted a one-master-multiple-slaves architecture and multipoint wireless collaboration to synchronously recognize motions of the wrist, elbow, and shoulder. This work provides guidance for constructing motion recognition systems based on piezoresistive, piezoelectric, capacitive, and triboelectric principles.

Keywords

embedded AI / motion recognition / piezoelectric composite membrane / sensing array / wearable sensor cluster

References

[1] N. E. Groce, “Global Disability: An Emerging Issue,” Lancet Global Health 6 (2018): e724–e725.

[2] B. X. B. Yu, Y. Liu, K. C. C. Chan, and C. W. Chen, “EGCN++: A New Fusion Strategy for Ensemble Learning in Skeleton-Based Rehabilitation Exercise Assessment,” IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (2024): 6471–6485.

[3] Z.-Q. Yang, M.-F. Wei, L. Chen, and J.-N. Xi, “Research Progress in the Application of Motor-Cognitive Dual-Task Training in Rehabilitation of Walking Function in Stroke Patients,” Journal of Neurorestoratology 11 (2023): 100028.

[4] M. Elias Kevin, E. Brindle Mary, and G. Nelson, “Enhanced Recovery After Surgery—Evidence and Practice,” NEJM Evidence 4 (2025): EVIDra2400012.

[5] A. Abedi, T. J. F. Colella, M. Pakosh, and S. S. Khan, “Artificial Intelligence-Driven Virtual Rehabilitation for People Living in the Community: A Scoping Review,” NPJ Digital Medicine 7 (2024): 25.

[6] S. A. Jessep, N. E. Walsh, J. Ratcliffe, and M. V. Hurley, “Long-Term Clinical Benefits and Costs of an Integrated Rehabilitation Programme Compared With Outpatient Physiotherapy for Chronic Knee Pain,” Physiotherapy 95 (2009): 94–102.

[7] K. K. P. de Menezes, L. Ada, L. F. Teixeira-Salmela, et al., “Home-Based Interventions May Increase Recruitment, Adherence, and Measurement of Outcomes in Clinical Trials of Stroke Rehabilitation,” Journal of Stroke and Cerebrovascular Diseases 30 (2021): 106022.

[8] P. Li, Y. Wang, X. He, et al., “Wearable and Interactive Multicolored Photochromic Fiber Display,” Light, Science & Applications 13 (2024): 48.

[9] M. Chen, J. Ouyang, A. Jian, et al., “Imperceptible, Designable, and Scalable Braided Electronic Cord,” Nature Communications 13 (2022): 7097.

[10] J. Ouyang, P. Li, Y. Zou, et al., “A Scalable, Hyperstable Intelligent Fibre Velocimeter for Dynamic Digitisation of Resistance Training,” National Science Review 13 (2025): nwaf560.

[11] J. Xiong, L. Wang, F. Liang, et al., “Flexible Piezoelectric Sensor Based on Two-Dimensional Topological Network of PVDF/DA Composite Nanofiber Membrane,” Advanced Fiber Materials 6 (2024): 1212–1228.

[12] K. Kim, D. Choi, S. Ji, et al., “Highly Transparent and Flexible All-Nanofiber-Based Piezocomposite Containing BaTiO₃-embedded P(VDF-TrFE) Nanofibers for Harvesting and Monitoring Human Kinetic Movements,” Advanced Fiber Materials 6 (2024): 1369–1386.

[13] T. He, J. Chen, B.-G. He, W. Wang, Z.-L. Zhu, and Z. Lv, “Toward Wearable Sensors: Advances, Trends, and Challenges,” ACM Computing Surveys 55 (2023): 1–35.

[14] B. Chen, Z. Feng, F.-Z. Yao, et al., “Flexible Piezoelectrics: Integration of Sensing, Actuating and Energy Harvesting,” NPJ Flexible Electronics 9 (2025): 58.

[15] Q. Zhang, J. Li, G. Li, et al., “Hierarchically Structured Hollow PVDF Nanofibers for Flexible Piezoelectric Sensor,” Chemical Engineering Journal 498 (2024): 155661.

[16] Y. Huang, S. Chen, Y. Li, Q. Lin, Y. Wu, and Q. Shi, “Flexible Piezoelectric Sensor Based on PAN/MXene/PDA@ZnO Composite Film for Human Health and Motion Detection With Fast Response and Highly Sensitive,” Chemical Engineering Journal 488 (2024): 150997.

[17] J. Li, J. Yin, M. G. V. Wee, A. Chinnappan, and S. Ramakrishna, “A Self-Powered Piezoelectric Nanofibrous Membrane as Wearable Tactile Sensor for Human Body Motion Monitoring and Recognition,” Advanced Fiber Materials 5 (2023): 1417–1430.

[18] J. Shen, Y. Zeng, Q. Li, J. Zhou, and W. Chen, “Convenient Folding-Hot-Pressing Fabrication and Enhanced Piezoelectric Properties of High β-Phase-Content Poly(Vinylidene Fluoride) Films,” Interdisciplinary Materials 3 (2024): 715–725.

[19] J. Chang, J. Li, J. Ye, et al., “AI-Enabled Piezoelectric Wearable for Joint Torque Monitoring,” Nano-Micro Letters 17 (2025): 247.

[20] L. Sohail, S. Drakopoulou, T. L. Costa, and G. D. Spyropoulos, “Piezoelectric Ion Gated Organic Electrochemical Transistors for Efficient Vibration Sensing and On-Site Amplification,” NPJ Flexible Electronics 9 (2025): 39.

[21] Y. Z. Huang, Z. Liu, L. W. Li, et al., “Giant Piezoelectric Coefficient of Polyvinylidene Fluoride With Rationally Engineered Ultrafine Domains Achieved by Rapid Freezing Processing,” Advanced Materials 37 (2024): 2412344.

[22] H. Zhou, Y. Zhang, Y. Qiu, et al., “Stretchable Piezoelectric Energy Harvesters and Self-Powered Sensors for Wearable and Implantable Devices,” Biosensors and Bioelectronics 168 (2020): 112569.

[23] J. Yu, L. Chen, X. Hou, et al., “Stretchable and Skin-Conformal Piezo-Triboelectric Pressure Sensor for Human Joint Bending Motion Monitoring,” Journal of Materiomics 8 (2022): 247–256.

[24] S. Shajari, K. Kuruvinashetti, A. Komeili, and U. Sundararaj, “The Emergence of AI-Based Wearable Sensors for Digital Health Technology: A Review,” Sensors 23 (2023): 9498.

[25] T. Sun, B. Feng, J. Huo, et al., “Artificial Intelligence Meets Flexible Sensors: Emerging Smart Flexible Sensing Systems Driven by Machine Learning and Artificial Synapses,” Nano-Micro Letters 16 (2023): 14.

[26] J. Suo, Y. Liu, J. Wang, et al., “AI-Enabled Soft Sensing Array for Simultaneous Detection of Muscle Deformation and Mechanomyography for Metaverse Somatosensory Interaction,” Advanced Science 11 (2024): 2305025.

[27] H. Zhou, Y. Gui, G. Gu, et al., “A Plantar Pressure Detection and Gait Analysis System Based on Flexible Triboelectric Pressure Sensor Array and Deep Learning,” Small 21 (2024): 2405064.

[28] Y. Wang, C. Sun, and D. Ahmed, “A Smart Acoustic Textile for Health Monitoring,” Nature Electronics 8 (2025): 485–495.

[29] Y.-G. Kim, J.-H. Song, S. Hong, and S.-H. Ahn, “Piezoelectric Strain Sensor With High Sensitivity and High Stretchability Based on Kirigami Design Cutting,” NPJ Flexible Electronics 6 (2022): 52.

[30] S. He, J. Dai, D. Wan, et al., “Biomimetic Bimodal Haptic Perception Using Triboelectric Effect,” Science Advances 10 (2024): eado6793.

[31] K. Mahato, T. Saha, S. Ding, S. S. Sandhu, A.-Y. Chang, and J. Wang, “Hybrid Multimodal Wearable Sensors for Comprehensive Health Monitoring,” Nature Electronics 7 (2024): 735–750.

[32] B. Hou, D. Yang, X. Ren, L. Yi, and X. Liu, “A Tactile Oral Pad Based on Carbon Nanotubes for Multimodal Haptic Interaction,” Nature Electronics 7 (2024): 777–787.

[33] M. Salama, A. Hamed, S. Noman, G. Magdy, N. Shehata, and I. Kandas, “Boosting Piezoelectric Properties of PVDF Nanofibers via Embedded Graphene Oxide Nanosheets,” Scientific Reports 14 (2024): 16484.

[34] Z. He, F. Rault, M. Lewandowski, E. Mohsenzadeh, and F. Salaün, “Electrospun PVDF Nanofibers for Piezoelectric Applications: A Review of the Influence of Electrospinning Parameters on the β Phase and Crystallinity Enhancement,” Polymers 13 (2021): 174.

[35] W. Fan, R. Lei, H. Dou, et al., “Sweat Permeable and Ultrahigh Strength 3D PVDF Piezoelectric Nanoyarn Fabric Strain Sensor,” Nature Communications 15 (2024): 3509.

[36] L. Zhang, S. Li, Z. Zhu, et al., “Recent Progress on Structure Manipulation of Poly(Vinylidene Fluoride)-Based Ferroelectric Polymers for Enhanced Piezoelectricity and Applications,” Advanced Functional Materials 33 (2023): 2301302.

[37] Y. Huang, G. Rui, Q. Li, et al., “Enhanced Piezoelectricity From Highly Polarizable Oriented Amorphous Fractions in Biaxially Oriented Poly(Vinylidene Fluoride) With Pure β Crystals,” Nature Communications 12 (2021): 675.

[38] Z.-W. Yang, L.-W. Zhang, and Y.-F. Huang, “Manipulation of the Oriented Amorphous Fraction of Poly(Vinylidene Fluoride-co-Trifluoroethylene) Films by Thermal Annealing for High Piezoelectricity,” Chemical Communications 61 (2025): 3399–3402.

[39] X. Huang, G. Dong, Y. Zhang, et al., “Decoding the Intrinsic Frequency Response Behaviors of Piezoelectric Output Current Toward Advanced Sensing and Monitoring Applications,” Nano Energy 134 (2025): 110544.

[40] D. Yu, Z. Zheng, J. Liu, H. Xiao, G. Huangfu, and Y. Guo, “Superflexible and Lead-Free Piezoelectric Nanogenerator as a Highly Sensitive Self-Powered Sensor for Human Motion Monitoring,” Nano-Micro Letters 13 (2021): 117.

[41] C. Cao, P. Zhou, W. Qin, et al., “Ultra-Sensitive Flexible Piezoelectric Sensor Based on P(VDF-TrFE) Films With Integrated Fillers Encased in Organic Conductive Shells,” Chemical Engineering Journal 509 (2025): 161521.

[42] J. Li, G. Zhou, Y. Hong, et al., “Highly Sensitive, Flexible and Wearable Piezoelectric Motion Sensor Based on PT Promoted β-Phase PVDF,” Sensors and Actuators, A: Physical 337 (2022): 113415.

[43] C. Zhang, L. Zhang, Y. Tian, Z. An, B. Li, and D. Li, “AI-Enabled Full-Body Dynamic Avatar Reconstruction Using Triboelectric Smart Clothing for Metaverse Applications,” eScience 5 (2025): 100373.

[44] J. Tang, B. Yang, T. Duanmu, Z. Mao, and J. Zhang, “Low Percolation Threshold Polyvinylidene Fluoride/Multi-Walled Carbon Nanotube Composites: A Perspective of Electrical Conductivity, Crystalline, Rheological and Mechanical Properties,” Polymer Composites 45 (2024): 8065–8075.

[45] J.-H. Zhang, Z. Li, J. Xu, et al., “Versatile Self-Assembled Electrospun Micropyramid Arrays for High-Performance On-Skin Devices With Minimal Sensory Interference,” Nature Communications 13 (2022): 5839.

[46] S. Shi, Y. Si, Y. Han, et al., “Recent Progress in Protective Membranes Fabricated via Electrospinning: Advanced Materials, Biomimetic Structures, and Functional Applications,” Advanced Materials 34 (2022): 2107938.

[47] P. Wu, J. Gu, X. Liu, et al., “A Robust Core–Shell Nanofabric With Personal Protection, Health Monitoring and Physical Comfort for Smart Sportswear,” Advanced Materials 36 (2024): 2411131.

[48] Y. Li, J. Long, Y. Chen, Y. Huang, and N. Zhao, “Crosstalk-Free, High-Resolution Pressure Sensor Arrays Enabled by High-Throughput Laser Manufacturing,” Advanced Materials 34 (2022): 2200517.

[49] H. Lee, S. Lee, J. Kim, et al., “Stretchable Array Electromyography Sensor With Graph Neural Network for Static and Dynamic Gestures Recognition System,” NPJ Flexible Electronics 7 (2023): 20.

[50] Y. Sun, J. Mao, L. Cao, et al., “Intelligent Cardiovascular Disease Diagnosis System Combined Piezoelectric Nanogenerator Based on 2D Bi₂O₂Se With Deep Learning Technique,” Nano Energy 128 (2024): 109878.

[51] Q. Zhang, Y. Wang, D. Li, et al., “Multifunctional and Wearable Patches Based on Flexible Piezoelectric Acoustics for Integrated Sensing, Localization, and Underwater Communication,” Advanced Functional Materials 33 (2022): 2209667.

[52] Z. Xiang, L. Li, Z. Lu, et al., “High-Performance Microcone-Array Flexible Piezoelectric Acoustic Sensor Based on Multicomponent Lead-Free Perovskite Rods,” Matter 6 (2023): 554–569.

[53] A. Rahaman, C. H. Park, and B. Kim, “Design and Characterization of a MEMS Piezoelectric Acoustic Sensor With the Enhanced Signal-to-Noise Ratio,” Sensors and Actuators, A: Physical 311 (2020): 112087.

[54] B. Jin, H. Cao, T. Sheng, et al., “Flexible Hair-Like Piezoelectric Acoustic Particle Velocity Sensor With Enhanced Sensitivity for Speaker Recognition,” Advanced Functional Materials 35 (2024): 2417164.

[55] Q. Hu, L. Zhou, X. Ma, and X. Zhang, “Biodegradable, Bifunctional Electro-Acoustic Transducers Based on Cellular Polylactic Acid Ferroelectrets for Sustainable Flexible Electronics,” ACS Applied Materials & Interfaces 16 (2024): 3876–3887.

[56] H. Hu, W. Li, X. Li, et al., “An Ultra-Sensitive Flexible Piezoelectric Nanogenerator Based on P(VDF-TrFE) Nanofibers,” International Journal of Extreme Manufacturing 7 (2025): 065503.

[57] N. Zhou, N. Wang, H. Wang, H. Xie, Y. Zhang, and H. Ao, “Optical 3D μ-Printing of PVDF-Based Flexible Microstructural Auxetic Metamaterials and 3D Microgrid Pyramid Arrays for Wearable Electronics,” Chemical Engineering Journal 516 (2025): 163956.

[58] X. Wang, L. Zhang, T. Lin, C. Zhao, K. Wang, and Z. Chen, “Solving Job Scheduling Problems in a Resource Preemption Environment With Multi-Agent Reinforcement Learning,” Robotics and Computer-Integrated Manufacturing 77 (2022): 102324.

[59] A. Soltoggio, E. Ben-Iwhiwhu, V. Braverman, et al., “A Collective AI via Lifelong Learning and Sharing at the Edge,” Nature Machine Intelligence 6 (2024): 251–264.

[60] L. Liu, J. Li, Z. Tian, et al., “Self-Powered Porous Polymer Sensors With High Sensitivity for Machine Learning-Assisted Motion and Rehabilitation Monitoring,” Nano Energy 128 (2024): 109817.

[61] Q. Jiang, X. Zhao, T. Zhao, et al., “A Machine-Learning–Powered Spectral-Dominant Multimodal Soft Wearable System for Long-Term and Early-Stage Diagnosis of Plant Stresses,” Science Advances 11 (2025): eadw7279.

RIGHTS & PERMISSIONS

2026 The Author(s). Interdisciplinary Materials published by Wuhan University of Technology and John Wiley & Sons Australia, Ltd.