Wearable technologies, performance analytics, and athlete monitoring systems in beach volleyball: a systematic review

Abstract

This review by a systematic method was intended to integrate the present knowledge about wearable gadgets, tracking systems, and analytical methods used for the purpose of athlete performance and monitoring assessment in beach volleyball. The review was run in line with the PRISMA 2020 criteria. Based on its wide interdisciplinary coverage of sport science, biomechanics, engineering, computer science, and sports technology research areas, Scopus was chosen as the main database. Studies that included beach volleyball players or events and referred to wearable, sensor-based, tracking, physiological, or computational monitoring technologies were accepted. Study screening and data extraction were performed independently by two reviewers with a very good level of inter-rater agreement (Cohen's κ = 0.87). Out of 128 published studies between 1998 and 2026, 112 were included in the qualitative synthesis. Thematic analysis mapped four main research areas: wearable sensor validation and load monitoring, physiological and biochemical monitoring, computer-vision tracking systems, and machine-learning-based performance analytics. Concerning validity, Inertial Measurement Units (IMUs) were highly reliable for jump detection and external-load monitoring, while beach volleyball environment positional accuracy of Ultra-Wideband (UWB) systems topped that of GPS technologies. Machine-learning algorithms reached very high accuracy for action recognition, frequently above 95%, although small datasets were characteristic of most research. The data presented also make a strong case for wearable and analytical technologies integration as the base of evidence-based athlete monitoring, training program optimization, tactical player analysis, and performance management in beach volleyball. Investigations aiming at longitudinal monitoring, females and youth as athlete groups, and physiological, environmental, and artificial intelligent monitoring systems integration seem to be the most promising directions for future research.