This study presents a novel approach for golf swing biomechanics through deep learning-assisted to enhance the sensing, processing, interpretation, and assessment of swing quality. The proposed methodology introduces a Smart Golf Glove (SGG) system, incorporating a deep neural network and the Internet of Things (IoT) capabilities. The key contributions of this study include (1) a comprehensive design framework encompassing both hardware and software aspects of the SGG system, as well as (2) an algorithm of phase and events to segment swing signals as inputs for deep learning models. Moreover, (3) an Unsupervised Learning Model (ULM) architecture is introduced to address the challenges of dataset limitation and effort for data labeling. Additionally, (4) an IoT-assisted SGG platform is proposed, enabling remote monitoring and management. Experimental results indicate that the trained ULM model achieved an average accuracy of 92.4%. The findings highlight the effectiveness of the proposed SGG system in accurately detecting abnormal motion from beginner players. The integration of artificial intelligence (AI) and IoT-based platforms with targeted videos-based self-coaching capabilities represents a significant advancement in golf swing biomechanics analysis.
30 December 2024 in IEEE Journal of Biomedical and Health Informatics
Leg workout-based monitoring provides valuable insights into physical and neurological health, supporting healthcare professionals and facilitating in-depth analysis. However, current single sensing modalities technologies are limited by size constraints, environmental sensitivity, and accuracy issues. Furthermore, despite the widespread use of deep learning (DL) methods for sensor-based gesture recognition methods, they still encounter challenges in feature extraction. To address the limitations, this study (1) presents the development of a multi-modal wearable device for leg workout monitoring with real-time gait analysis capabilities, (2) introduces a novel Transformer-powered Two-Stream Fusion, namely TTSF, for efficient and accurate extraction of temporal and spatial features. The experimental results on our leg workout dataset demonstrate the superior performance of the proposed TTSF model with Precision, Recall, and F1-Score values of 90.7%, 90.6%, and 89.1%, respectively. Overall, this research contributes to the advancement of using multi-sensor fusion with DL and Medical Internet of Things (MIoT) techniques for advanced gait monitoring and analysis. These techniques have potential applications in personalized training programs and enhanced rehabilitation assessment.
17 January 2026 in Computers in Biology and Medicine
The accelerating demand for wearable electronics requires next-generation strain sensors combining high stretchability, sensitivity, robustness, and minimal hysteresis. Here, we present a multifunctional ionically conductive hydrogel constructed from a dual network of polyacrylamide (PAAm) and sodium carboxymethyl cellulose (CMC), reinforced with calcium chloride serving as both ionic conductor and dynamic crosslinker. The hydrogel achieves 1251.5% stretchability, 94.6% transparency, 29.8 kPa adhesion, and 1.44 S/m ionic conductivity, together with low mechanical hysteresis of 8.7% and electrical hysteresis of 0.34%. These properties originate from reversible Ca2+ coordination with carboxylate groups in CMC, enabling dynamic network reconstruction, while the interpenetrating framework promotes homogeneous stress distribution. The material exhibits a gauge factor of 2.05, allowing reliable strain detection across diverse human motions. Integrated into a wireless wearable platform with an AI-assisted analyzer, the sensor enables real time motion recognition and precise differentiation of strain patterns, including robotic hand control through gesture translation. Owing to its high water content and ionic mobility, the hydrogel provides passive thermoregulation via enhanced heat dissipation, improving long term wearing comfort. In addition, it operates as a hydrovoltaic generator by harvesting salinity gradients to produce stable electrical output. This work establishes a scalable soft material for intelligent sensing and energy harvesting.