This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Yanshit Tanwar,
- Student, Department of Computer Science & Engineering, Greater Noida Institute of Technology, Uttar Pradesh, India
Abstract
The rapid advancement of Artificial Intelligence (AI) has profoundly transformed sports analytics, enabling deeper insights, real-time data analysis, and enhanced performance predictions. Noticeable results have been seen by enabling automated analysis of complex gameplay patterns along with athlete performance. Volleyball is a dynamic and strategic sport, which requires continuous tactical adjustments and constant monitoring of the player’s performance. This paper presents VolleyNexis AI, which is a multimodal artificial intelligence framework that is designed in order to enhance the volleyball analysis and its coaching with the use of advanced AI and machine learning techniques. The proposed system integrates computer vision, deep learning, and predictive analytics that can analyze match footage, evaluate player movement data, and assess the biomechanical performance indicators. Computer vision techniques are used in order to extract the key visual features like player positions, ball movement, court zones. Convolutional Neural Networks (CNNs) are applied so that it accurately classifies the sports actions. Additionally, sequential gameplay patterns are analyzed by the use of Long Short-Term Memory (LSTM) networks, which effectively model temporal relationships in the sequential data like player movements and transitions between plays. These models enable the detection of tactical elements including attack patterns, setter distribution, blocking formations, serve-receive structures, and defensive positioning. Additionally, Markov-based strategy transition analysis and probabilistic modeling are used to predict opponent strategies during gameplay. Based on these predictions, the system generates data-driven counter-strategies that assist coaches in real- time tactical decision making. VolleyNexis AI also functions as an AI-assisted coaching system by analyzing athlete performance metrics such as jump load, movement efficiency, fatigue levels, and training intensity to create personalized training programs, nutrition guidance, workload management plans, and injury prevention strategies, thereby providing a comprehensive data-driven volleyball coaching solution.
Keywords: Artificial Intelligence in Sports, Computer Vision, Volleyball Analytics, Strategy Prediction, Deep Learning (CNN–LSTM), Athlete Performance Optimization
References
- Gudmundsson J, Horton M. Spatio-temporal analysis of team sports. ACM Computing Surveys (CSUR). 2017 Apr 11;50(2):1-34.
- Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 779-788).
- Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the ACM. 2017 May 24;60(6):84-90.
- LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436-44.
- Bunker RP, Thabtah F. A machine learning framework for sport result prediction. Applied computing and informatics. 2019 Jan 1;15(1):27-33.
- Lu WL, Ting JA, Little JJ, Murphy KP. Learning to track and identify players from broadcast sports videos. IEEE transactions on pattern analysis and machine intelligence. 2013 May 16;35(7):1704-16.
- Ibrahim MS, Muralidharan S, Deng Z, Vahdat A, Mori G. A hierarchical deep temporal model for group activity recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 1971-1980).
- Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997 Nov 15;9(8):1735-80.
- Graves A. Supervised sequence labelling. InSupervised sequence labelling with recurrent neural networks 2012 Feb 6 (pp. 5-13). Berlin, Heidelberg: Springer Berlin Heidelberg.
- Wang Z, Yan W, Oates T. Time series classification from scratch with deep neural networks: A strong baseline. In2017 International joint conference on neural networks (IJCNN) 2017 May 14 (pp. 1578-1585). IEEE.
- Rabiner LR. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE. 1989 Feb 28;77(2):257-86.
- Cao Z, Simon T, Wei SE, Sheikh Y. Realtime multi-person 2d pose estimation using part affinity fields. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 7291-7299).
- Cioppa A, Deliege A, Giancola S, Ghanem B, Droogenbroeck MV, Gade R, Moeslund TB. A context-aware loss function for action spotting in soccer videos. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition 2020 (pp. 13126-13136).
- Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5-32.
- Carr P, Sheikh Y, Matthews I. Monocular object detection using 3d geometric primitives. InEuropean conference on computer vision 2012 Oct 7 (pp. 864-878). Berlin, Heidelberg: Springer Berlin Heidelberg.
Journal of Artificial Intelligence Research & Advances
| Volume | 13 | |
| 02 | ||
| Received | 24/06/2026 | |
| Accepted | 03/07/2026 | |
| Published | 10/07/2026 | |
| Publication Time | 16 Days |