Menu

HomeHow it worksContact UsContact Us

Conductive Composite-Based Wearable Sensors for Sports Science: Intelligent Data Analysis and Emerging Applications.

Wang Y, Ji C, Shi H, Wang W, Qi Q, Li Y et al. ยท ACS applied materials & interfaces ยท 2026

This review explores how wearable sensors made from advanced conductive materials can continuously monitor athletes' physiological, biochemical, and movement data during exercise, with artificial intelligence helping analyze this complex information for performance assessment and injury prevention. The integration of flexible composite materials with AI algorithms enables more reliable signal capture during movement and smarter interpretation of multimodal data to support training, fatigue monitoring, injury identification, and rehabilitation.
Takeaway: Use wearable sensors with AI analysis to get real-time feedback on your exercise form, fatigue state, and injury risk rather than relying on subjective feel alone.
Abstract (source)

Wearable sensors enable continuous acquisition of physiological, biochemical, and biomechanical signals during exercise, providing data to support sports performance assessment, training regulation, fatigue monitoring, and rehabilitation interventions. However, signal reliability and multidimensional data analysis under complex motion conditions remain constrained by device functionality. Conductive composites can improve sensor flexibility, interfacial conformability, and signal acquisition performance, while artificial intelligence (AI) enables movement pattern recognition, state assessment, and outcome prediction from complex data. Their integration is advancing wearable systems toward multimodal sensing and intelligent analysis. Guided by application needs in sports, this review summarizes emerging applications of wearable sensing technologies enabled by conductive composites and AI. First, the relevance to sports science and the data characteristics of physiological, biochemical, and biomechanical signals are introduced. The functional characteristics, representative applications, and major limitations of conductive polymer, carbon-based, MXene, and hydrogel composites are then summarized. Regarding algorithms, the fundamental principles of supervised learning, unsupervised learning, deep learning (DL), and large language models (LLMs) are discussed, with comparisons of their capabilities in feature extraction, temporal modeling, and multisource data analysis, as well as their input data requirements. On this basis, advances in the application of these systems to sports performance and sport-specific movement monitoring, exercise-induced fatigue monitoring and assessment, sports injury identification and evaluation, and intelligent monitoring of sports rehabilitation are reviewed followed by a

Discussion: of current challenges and future directions. Through the coordinated integration of material

Design: , signal acquisition, and intelligent analysis, wearable systems are expected to enable continuous, reliable, and individualized assessment of exercise-related states, with further applications in real-time feedback, risk alerts, and training decision support, providing a technological foundation for scientifically informed training, sports rehabilitation, and individual health management.

Read the original โ†’