The Impact of a Specialized Training Program on the Balance of Goalball Players with Emphasis on Body Type and Musculoskeletal Posture, with and without Artificial Intelligence
Poster Presentation
Paper ID : 1488-SSRC
Authors
1دانشجوی بیومکانیک ورزشی، گروه بیومکانیک و آسیب شناسی ورزشی، دانشکده تربیت بدنی و علوم ورزشی دانشگاه خوارزمی، تهران، ایران
2استاد گروه بیومکانیک و آسیب شناسی ورزشی، دانشکده تربیت بدنی و علوم ورزشی دانشگاه خوارزمی، تهران، ایران
Abstract
Background: Maintaining stability and optimal performance in Goalball, a sport
characterized by constant changes between attack and defense, is a significant concern
for both trainers and athletes. The role of balance in achieving these goals is crucial.
Objective: The aim of this study is to assess the impact of a specialized training course on
the balance of Goalball players, with a particular focus on body type and musculoskeletal
stature, both with and without the integration of artificial intelligence.
Methods30 semi-professional goalball players were randomly divided into two
experimental and control groups. Field balance test (static, semi-dynamic and dynamic)
was performed before and after an eight-week training course to assess balance. The
experimental group underwent special balance exercises for eight weeks (two sessions of
30 minutes per week), while the control group performed the usual goalball exercises.
Random Forest Neural Intelligence Network was used to predict post-test results based
on pre-test data. SPSS version 27 software was used for the statistical analysis at a
significance level of p>0.05, and the ANOVA test with repeated measurements between
groups was used for inferential statistics and the mean and standard deviation were used
for descriptive statistics.
Results: The statistical analysis revealed a significant improvement in balance due to the
exercise, with the most notable impact observed in static balance. Furthermore, the post-
test results were predicted with 89% accuracy using the Random Forest algorithm.
Conclusion: The findings suggest that incorporating special balance exercises alongside
routine Goalball exercises is recommended to enhance the performance of players. While
the Random Forest Artificial Intelligence (AI) system demonstrated accurate predictions,
it is noted that more input data is required for achieving higher accuracy results.
characterized by constant changes between attack and defense, is a significant concern
for both trainers and athletes. The role of balance in achieving these goals is crucial.
Objective: The aim of this study is to assess the impact of a specialized training course on
the balance of Goalball players, with a particular focus on body type and musculoskeletal
stature, both with and without the integration of artificial intelligence.
Methods30 semi-professional goalball players were randomly divided into two
experimental and control groups. Field balance test (static, semi-dynamic and dynamic)
was performed before and after an eight-week training course to assess balance. The
experimental group underwent special balance exercises for eight weeks (two sessions of
30 minutes per week), while the control group performed the usual goalball exercises.
Random Forest Neural Intelligence Network was used to predict post-test results based
on pre-test data. SPSS version 27 software was used for the statistical analysis at a
significance level of p>0.05, and the ANOVA test with repeated measurements between
groups was used for inferential statistics and the mean and standard deviation were used
for descriptive statistics.
Results: The statistical analysis revealed a significant improvement in balance due to the
exercise, with the most notable impact observed in static balance. Furthermore, the post-
test results were predicted with 89% accuracy using the Random Forest algorithm.
Conclusion: The findings suggest that incorporating special balance exercises alongside
routine Goalball exercises is recommended to enhance the performance of players. While
the Random Forest Artificial Intelligence (AI) system demonstrated accurate predictions,
it is noted that more input data is required for achieving higher accuracy results.
Keywords