What question did this study set out to answer?

The aim is to develop an intelligent system for evaluating volleyball skills using advanced deep learning methods.

March 7, 2026SHILAP Revista de lepidopterología0 citationsOpen Access

Deep Learning-Driven Intelligent Volleyball Teaching System Design and Implementation

Design and Implementation of a Deep Learning-Driven Intelligent Volleyball Teaching System

View Full Paper

Ask AI

Bookmark

Authors

This research demonstrates an AI-driven teaching system that evaluates volleyball skills, suggesting improvements in assessment techniques.

The aim is to develop an intelligent system for evaluating volleyball skills using advanced deep learning methods.
Designed a volleyball teaching system leveraging deep learning for skill analysis.
Employed YOLOv8 for player detection and DeepSORT for tracking multiple players.
Utilized a hybrid CNN–LSTM architecture for classifying player actions.
Preprocessed the dataset through frame cleaning, normalization, and data augmentation.
High accuracy in player detection was achieved with YOLOv8.
Best performance metrics were noted for actions like l_winpoint and moving, while spiking and standing had lower scores indicating performance variances.
Indicated the importance of combining biomechanical metrics for comprehensive action evaluation.

Chen et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

March 7, 2026SHILAP Revista de lepidopterología0 citationsOpen Access

Design and Implementation of a Deep Learning-Driven Intelligent Volleyball Teaching System

View Full Paper

Ask AI

Bookmark

Authors

This research demonstrates an AI-driven teaching system that evaluates volleyball skills, suggesting improvements in assessment techniques.

The aim is to develop an intelligent system for evaluating volleyball skills using advanced deep learning methods.
Designed a volleyball teaching system leveraging deep learning for skill analysis.
Employed YOLOv8 for player detection and DeepSORT for tracking multiple players.
Utilized a hybrid CNN–LSTM architecture for classifying player actions.
Preprocessed the dataset through frame cleaning, normalization, and data augmentation.
High accuracy in player detection was achieved with YOLOv8.
Best performance metrics were noted for actions like l_winpoint and moving, while spiking and standing had lower scores indicating performance variances.
Indicated the importance of combining biomechanical metrics for comprehensive action evaluation.

Chen et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark