2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes
| Format: | General Document |
|---|
| _version_ | 1860798141459070976 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| date | 2019-12-08 |
| format | General Document |
| id | 16139 |
| institution | UniSZA |
| originalfilename | UNSUPERVISED MODELING ON ANTHROPOMETRIC AND FITNESS COMPONENT'S RELATIVE AGE OF BOYS FOR TALENT IDENTIFICATION OF ATHLETES (PHD_2019).pdf |
| person | Siti Musliha binti Mat Rasid |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16139 |
| sourcemedia | Server storage Scanned document |
| spelling | 16139 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16139 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Applied Social Sciences English application/pdf 1.5 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access Universiti Sultan Zainal Abidin SAMBox 2.4.24; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) Copyright©PWB2025 Physical fitness 2019-12-08 210 UNSUPERVISED MODELING ON ANTHROPOMETRIC AND FITNESS COMPONENT'S RELATIVE AGE OF BOYS FOR TALENT IDENTIFICATION OF ATHLETES (PHD_2019).pdf Siti Musliha binti Mat Rasid Talent identification Unsupervised learning 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes Identifying individuals with the greatest potential to excel in sports currently presents a significant challenge. As various factors contribute to producing successful athletes, research on multidimensional talent identification is vital, in addition to addressing the dropout of potential athletes due to the relative age effect. A total of 43,003 male participants in the Malaysian National Talent Identification Program, with a mean age of 7.32 years and a standard deviation of 0.29 years, were involved in this study. They underwent anthropometric measurements (body weight and standing height) and fitness tests (standing broad jump test, sit-and-reach test, hand wall toss test, and 20-meter sprint test). The first objective of this study was to develop an unsupervised talent model in sports. The second objective aimed to determine multiple indexes of the talent model relative to the birth-month quarter: January-March (Q1), April-June (Q2), July-September (Q3), and October-December (Q4). The third objective was to validate the accuracy of the classification assigned by the proposed multiple indexes. The fourth objective aimed to explore the talent characteristics relative to the birth-month quarter. Finally, the fifth objective sought to introduce an online system named eMyTID for future screening of talented participants. The proposed talent model was developed using Principal Component Analysis (PCA), and k-means clustering (k-MC) was used to determine the multiple indexes for the talent model. Discriminant Analysis (DA) was used to validate the proposed multiple indexes, and Multiple Analysis of Variance (MANOVA) was used to explore talent characteristics relative to the birth-month quarter. Finally, eMyTID was developed as a practical tool for practitioners. The findings revealed that three domain factors with a total explained variance of 70.57% were extracted from the original variables. The first factor showed high factor loading on body weight (0.91) and standing height (0.89). The second factor revealed high factor loading on the standing broad jump (0.74) and 20-meter sprint (0.73). The third factor consisted of a high factor loading on the sit-and-reach test (0.97). These four factors were used to obtain the talent score formula, which explained a total variance of 27.42%, 26.04%, and 17.12%, respectively. The multiple indexes consisted of five categories: excellent, very good, good, fair, and poor, and were obtained separately for each birth-month quarter. DA confirmed the accuracy of classification, with a high percentage of discrimination greater than 90.00%, using standard, forward stepwise, and backward stepwise modes. The talent model formulas are used as input in the eMyTID online system programming. eMyTID serves as a tool for identifying talented participants in the future. In conclusion, body physique and fitness performance are essential indicators for identifying talented individuals in sports. This study has successfully developed a multidimensional talent model with proposed multiple indexes relative to birth-month quarters to identify talented individuals in sports and address the problem of potential athlete dropout. In the long run, it may reduce costs and increase the effectiveness of talent identification programs. Dissertations, Academic Anthropometric And Fitness Componet Relative Age Of Boys Talent Identification Of Athlete Athlete Development Thesis |
| spellingShingle | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| state | Terengganu |
| subject | Physical fitness Talent identification Unsupervised learning Dissertations, Academic |
| summary | Identifying individuals with the greatest potential to excel in sports currently presents a significant challenge. As various factors contribute to producing successful athletes, research on multidimensional talent identification is vital, in addition to addressing the dropout of potential athletes due to the relative age effect. A total of 43,003 male participants in the Malaysian National Talent Identification Program, with a mean age of 7.32 years and a standard deviation of 0.29 years, were involved in this study. They underwent anthropometric measurements (body weight and standing height) and fitness tests (standing broad jump test, sit-and-reach test, hand wall toss test, and 20-meter sprint test). The first objective of this study was to develop an unsupervised talent model in sports. The second objective aimed to determine multiple indexes of the talent model relative to the birth-month quarter: January-March (Q1), April-June (Q2), July-September (Q3), and October-December (Q4). The third objective was to validate the accuracy of the classification assigned by the proposed multiple indexes. The fourth objective aimed to explore the talent characteristics relative to the birth-month quarter. Finally, the fifth objective sought to introduce an online system named eMyTID for future screening of talented participants. The proposed talent model was developed using Principal Component Analysis (PCA), and k-means clustering (k-MC) was used to determine the multiple indexes for the talent model. Discriminant Analysis (DA) was used to validate the proposed multiple indexes, and Multiple Analysis of Variance (MANOVA) was used to explore talent characteristics relative to the birth-month quarter. Finally, eMyTID was developed as a practical tool for practitioners. The findings revealed that three domain factors with a total explained variance of 70.57% were extracted from the original variables. The first factor showed high factor loading on body weight (0.91) and standing height (0.89). The second factor revealed high factor loading on the standing broad jump (0.74) and 20-meter sprint (0.73). The third factor consisted of a high factor loading on the sit-and-reach test (0.97). These four factors were used to obtain the talent score formula, which explained a total variance of 27.42%, 26.04%, and 17.12%, respectively. The multiple indexes consisted of five categories: excellent, very good, good, fair, and poor, and were obtained separately for each birth-month quarter. DA confirmed the accuracy of classification, with a high percentage of discrimination greater than 90.00%, using standard, forward stepwise, and backward stepwise modes. The talent model formulas are used as input in the eMyTID online system programming. eMyTID serves as a tool for identifying talented participants in the future. In conclusion, body physique and fitness performance are essential indicators for identifying talented individuals in sports. This study has successfully developed a multidimensional talent model with proposed multiple indexes relative to birth-month quarters to identify talented individuals in sports and address the problem of potential athlete dropout. In the long run, it may reduce costs and increase the effectiveness of talent identification programs. |
| title | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| title_full | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| title_fullStr | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| title_full_unstemmed | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| title_short | 2019_Unsupervised Modeling on Anthropometric and Fitness Component's Relative Age of Boys For Talent Identification of Athletes |
| title_sort | 2019_unsupervised modeling on anthropometric and fitness component's relative age of boys for talent identification of athletes |