Department of Physical Education, Chengdu University of Information Technology, Chengdu 610000, Sichuan, China
Received: May 29, 2026
Accepted: August 17, 2026
Publication Date: September 25, 2026
CNN Architecture
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
Download Citation: BibTeX | http://dx.doi.org/10.6180/jase.202612_35.058
University-level volleyball training often depends on subjective coach evaluations, which can lead to inconsistent, time-consuming, and less scalable instruction. With the growing use of artificial intelligence (AI) in sports analytics, this study develops a Convolutional Neural Network (CNN)-based motion recognition system for classifying volleyball actions, including serving, passing, blocking, and spiking. The model was trained using the Hyper AI volleyball motion dataset containing 4,830 annotated frames from collegiate match footage. The preprocessing pipeline included normalization, denoising, frame extraction, and data augmentation. A retrospective simulation case study was designed to replicate a university training environment and evaluate the system’s practical applicability. Experimental results showed a recognition accuracy of 97.36% and a micro-average AUC score of 0.995, with particularly strong performance in identifying spike and block actions. Compared with traditional coaching approaches, the AI-based framework provided more consistent evaluations, reduced misclassification errors, and accelerated error detection. The findings demonstrate the potential of AI-driven systems to support personalized feedback, objective performance assessment, and scalable coaching in university sports education. The framework also offers opportunities for adaptation to other sports and future pedagogical innovations.
Keywords: Volleyball training, Motion recognition, Convolutional Neural Network (CNN), Artificial intelligence, Sports analytics, Player performance evaluation, Deep learning
- [1] X. Kang, Q. Meng, and C.-H. Su, (2024) “School-Based Team Sports as Catalysts for Holistic Student Wellness: A Narrative Review” Behavioral Sciences 14(7): 528. DOI: https://doi.org/10.3390/bs14070528.
- [2] A. Chatterjee, M. Gerdes, A. Prinz, and S. Martinez, (2021) “Human Coaching Methodologies for Automatic Electronic Coaching (eCoaching) as Behavioral Interventions With Information and Communication Technology: Systematic Review” Journal of Medical Internet Research 23(3): e23533. DOI: https://doi.org/10.2196/23533.
- [3] G. M. Migliaccio, J. Padulo, and L. Russo, (2024) “The Impact of Wearable Technologies on Marginal Gains in Sports Performance: An Integrative Overview on Advances in Sports, Exercise, and Health” Applied Sciences 14(15): 6649. DOI: https://doi.org/10.3390/app14156649.
- [4] A. M. Cojocaru, R. Bucea-Manea-Tonis, A. Jianu, M. A. Dumangiu, L. U. Alexandrescu, and M. Cojocaru, (2022) “The Role of Physical Education and Sports in Modern Society Supported by IoT-A Student Perspective” Sustainability 14(9): 5624. DOI: https://doi.org/10.3390/su14095624.
- [5] P. Seemann, Z. Štofková, A. Poliaková, V. Biňasová, and E. Loučanová, (2024) “Coaching Approach as a Sustainable Means of Improving the Skills of Management Students” Administrative Sciences 14(6): 114. DOI: https://doi.org/10.3390/admsci14060114.
- [6] Z. Meng et al., (2020) “Recent Progress in Sensing and Computing Techniques for Human Activity Recognition and Motion Analysis” Electronics 9(9): 1357. DOI: https://doi.org/10.3390/electronics9091357.
- [7] M.-C. Shin, D.-H. Lee, A. Chung, and Y.-W. Kang, (2024) “When Taekwondo Meets Artificial Intelligence: The Development of Taekwondo” Applied Sciences 14(7): 3093. DOI: https://doi.org/10.3390/app14073093.
- [8] A. C. Sousa, D. L. Marques, D. A. Marinho, H. P. Neiva, and M. C. Marques, (2023) “Assessing and Monitoring Physical Performance Using Wearable Technologies in Volleyball Players: A Systematic Review” Applied Sciences 13(7): 4102. DOI: https://doi.org/10.3390/app13074102.
- [9] C. Serôdio, J. Cunha, G. Candela, S. Rodriguez, X. R. Sousa, and F. Branco, (2023) “The 6G Ecosystem as Support for IoE and Private Networks: Vision, Requirements, and Challenges” Future Internet 15(11): 348. DOI: https://doi.org/10.3390/fi15110348.
- [10] N. Mateus, E. Abade, D. Coutinho, M.-Á. Gómez, C. L. Peñas, and J. Sampaio, (2025) “Empowering the Sports Scientist with Artificial Intelligence in Training, Performance, and Health Management” Sensors 25(1): 139. DOI: https://doi.org/10.3390/s25010139.
- [11] Z. Hu, Z. Liu, and Y. Su, (2024) “AI-Driven Smart Transformation in Physical Education: Current Trends and Future Research Directions” Applied Sciences 14(22): 10616. DOI: https://doi.org/10.3390/app142210616.
- [12] J. Lutz, D. Memmert, D. Raabe, R. Dornberger, and L. Donath, (2020) “Wearables for Integrative Performance and Tactic Analyses: Opportunities, Challenges, and Future Directions” International Journal of Environmental Research and Public Health 17(1): 59. DOI: https://doi.org/10.3390/ijerph17010059.
- [13] M. A. Gul, M. H. Yousaf, S. Nawaz, Z. Ur Rehman, and H. Kim, (2020) “Patient Monitoring by Abnormal Human Activity Recognition Based on CNN Architecture” Electronics 9(12): 1993. DOI: https://doi.org/10.3390/electronics9121993.
- [14] R. Vrskova, P. Kamencay, R. Hudec, and P. Sykora, (2023) “A New Deep-Learning Method for Human Activity Recognition” Sensors 23(5): 2816. DOI: https://doi.org/10.3390/s23052816.
- [15] B. Ćwikliński, A. Giełczyk, and M. Choraś, (2021) “Who Will Score? A Machine Learning Approach to Supporting Football Team Building and Transfers” Entropy 23(1): 90. DOI: https://doi.org/10.3390/e23010090.