Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling
Core strength training plays an essential role in maximizing performance for badminton athletes. The core muscles in the abdominal, back, and hip regions provide stability, enable efficient power transfer between the upper and lower body, and allow for rapid changes in direction - all crucial compon...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/113725/ http://psasir.upm.edu.my/id/eprint/113725/1/113725.pdf |
| _version_ | 1848866304525598720 |
|---|---|
| author | Ma, Shuzhen Geok Soh, Kim Japar, Salimah Xu, Simao Zhicheng, Guo |
| author_facet | Ma, Shuzhen Geok Soh, Kim Japar, Salimah Xu, Simao Zhicheng, Guo |
| author_sort | Ma, Shuzhen |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Core strength training plays an essential role in maximizing performance for badminton athletes. The core muscles in the abdominal, back, and hip regions provide stability, enable efficient power transfer between the upper and lower body, and allow for rapid changes in direction - all crucial components for success in badminton. However, optimizing core training requires an understanding of its impact on sport-specific skills. A variety of exercises targeting the abdominal, back, and hip muscles are discussed. Incorporating core strength training into regular regimens can improve athletes' overall strength, endurance, balance, control, and prevent injuries. This study investigates the effects of various core exercises on stability, agility, and power in badminton players. A comprehensive literature review was conducted to explore the biomechanical demands of badminton and how core musculature contributes to movements like serving, smashing, and lunging. Studies assessing the effects of core training programs in related racquet sports were also examined. The results indicate that targeted core exercises significantly improve athletes' stability, agility, and power output. Exercises targeting the abdominal, back, and hip muscles enhance performance capabilities while reducing injury risk. Machine learning (ML) techniques are then applied to further analyze the relationship between core training and athletic performance. An Artificial Neural Network (ANN) is developed using a dataset of athletes' training histories, metrics, and injury profiles. The model predicts enhancements to stability, agility, and strength from optimized core strengthening routines. Validation confirms the network accurately captures the complex interactions between training variables and physical attributes. This integrated approach provides evidence-based guidelines for tailoring individualized training regimens to unleash players' full abilities. ANNs hold promise for analyzing large datasets on athletes' performance metrics, training variables, and injury histories to design personalized training programs. Linear regression analysis confirmed the ANN's accurate predictions. The findings emphasize integrating data-driven core strength training tailored for badminton into comprehensive programs can help optimize physical abilities and elevate performance levels. © 2024 The Authors |
| first_indexed | 2025-11-15T14:18:29Z |
| format | Article |
| id | upm-113725 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:18:29Z |
| publishDate | 2024 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1137252025-01-17T02:15:57Z http://psasir.upm.edu.my/id/eprint/113725/ Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling Ma, Shuzhen Geok Soh, Kim Japar, Salimah Xu, Simao Zhicheng, Guo Core strength training plays an essential role in maximizing performance for badminton athletes. The core muscles in the abdominal, back, and hip regions provide stability, enable efficient power transfer between the upper and lower body, and allow for rapid changes in direction - all crucial components for success in badminton. However, optimizing core training requires an understanding of its impact on sport-specific skills. A variety of exercises targeting the abdominal, back, and hip muscles are discussed. Incorporating core strength training into regular regimens can improve athletes' overall strength, endurance, balance, control, and prevent injuries. This study investigates the effects of various core exercises on stability, agility, and power in badminton players. A comprehensive literature review was conducted to explore the biomechanical demands of badminton and how core musculature contributes to movements like serving, smashing, and lunging. Studies assessing the effects of core training programs in related racquet sports were also examined. The results indicate that targeted core exercises significantly improve athletes' stability, agility, and power output. Exercises targeting the abdominal, back, and hip muscles enhance performance capabilities while reducing injury risk. Machine learning (ML) techniques are then applied to further analyze the relationship between core training and athletic performance. An Artificial Neural Network (ANN) is developed using a dataset of athletes' training histories, metrics, and injury profiles. The model predicts enhancements to stability, agility, and strength from optimized core strengthening routines. Validation confirms the network accurately captures the complex interactions between training variables and physical attributes. This integrated approach provides evidence-based guidelines for tailoring individualized training regimens to unleash players' full abilities. ANNs hold promise for analyzing large datasets on athletes' performance metrics, training variables, and injury histories to design personalized training programs. Linear regression analysis confirmed the ANN's accurate predictions. The findings emphasize integrating data-driven core strength training tailored for badminton into comprehensive programs can help optimize physical abilities and elevate performance levels. © 2024 The Authors Elsevier 2024 Article PeerReviewed text en cc_by_nc_4 http://psasir.upm.edu.my/id/eprint/113725/1/113725.pdf Ma, Shuzhen and Geok Soh, Kim and Japar, Salimah and Xu, Simao and Zhicheng, Guo (2024) Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling. Heliyon, 10 (15). art. no. e35145. pp. 1-16. ISSN 2405-8440; eISSN: 2405-8440 https://linkinghub.elsevier.com/retrieve/pii/S2405844024111760 10.1016/j.heliyon.2024.e35145 |
| spellingShingle | Ma, Shuzhen Geok Soh, Kim Japar, Salimah Xu, Simao Zhicheng, Guo Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title | Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title_full | Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title_fullStr | Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title_full_unstemmed | Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title_short | Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling |
| title_sort | maximizing the performance of badminton athletes through core strength training: unlocking their full potential using machine learning (ml) modeling |
| url | http://psasir.upm.edu.my/id/eprint/113725/ http://psasir.upm.edu.my/id/eprint/113725/ http://psasir.upm.edu.my/id/eprint/113725/ http://psasir.upm.edu.my/id/eprint/113725/1/113725.pdf |