Abstract
This study examines the use of the Teachable Machine program to facilitate the development of volleyball skills, with particular attention to assessing both the improvement of the skill and the satisfaction of the participants. Specifically, the Teachable Machine, an AI-powered platform, was integrated into volleyball training sessions to enhance serve, pass, and spike skills. Using 30 participants we performed pre- and post-test evaluations of the participants, using a 1 to 10 skill level rating to score for accuracy, technique, and consistency. Statistical analysis of the data was performed using means, standard deviation, and the t-test for independent samples. The results show that pretest scores for serving, passing, and spiking were, on average, 4.33, 3.70, and 3.93, respectively, which means they were intermediate. However, there was a significant increase in overall performance in the post-test scores immediately after they learned to use the Teachable Machine, which increased the performance score to 6.87 for the serve, 6.83 for the pass, and 0.73 for the spike. Furthermore, participant satisfaction was based on a 1-5 Likert scale, with an average satisfaction score of 4.68 on this scale, representing very high satisfaction with the program. The Teachable Machine program also helps improve technical performance and promotes the continuity of practice, as shown by the participants' engagement when handling the game environment. Studies have been conducted on how technology can enhance traditional coaching methods to design training programs better, and this study is supposed to add to that body of knowledge.
Author Information
Amnaj Sookjam, Rajamangala University of Technology Suvarnabhumi, Thailand
Anek Putthidech, Rajamangala University of Technology Suvarnabhumi, Thailand
Sangtong Boonying, Rajamangala University of Technology Suvarnabhumi, Thailand
Parinya Natho, Rajamangala University of Technology Suvarnabhumi, Thailand
Paper Information
Conference: ACE2024
Stream: Learning Experiences
This paper is part of the ACE2024 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
Comments
Powered by WP LinkPress