2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model
| Format: | General Document |
|---|
| _version_ | 1860798138547175424 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2019-11-19 |
| format | General Document |
| id | 16126 |
| institution | UniSZA |
| originalfilename | THE APPLICATION OF ARTIFICIAL NEURAL NETWORK TECHNIQUE FOR DEVELOPING SEPAK TAKRAW YOUTH PERFORMANCE MODEL (PHD_2019).pdf |
| person | Norlaila Azura binti Kosni |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16126 |
| sourcemedia | Server storage Scanned document |
| spelling | 16126 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16126 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia 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) 261 Copyright©PWB2025 Technological innovations 2019-11-19 THE APPLICATION OF ARTIFICIAL NEURAL NETWORK TECHNIQUE FOR DEVELOPING SEPAK TAKRAW YOUTH PERFORMANCE MODEL (PHD_2019).pdf Norlaila Azura binti Kosni Sepak Takraw Artificial intelligence Data processing 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model Under the umbrella of positive youth athlete development, physical fitness and performance represent an essential area of research for youth elite athletes. The individual competency a young person possesses determines their capacity to effectively navigate the turbulence of performance from beginner to intermediate, and followed by elite performance. An increase in the knowledge of the important parameters to enhance athlete performance, therefore, assists in the development of an appropriate model and evaluation of the sepak takraw youth development model. This thesis aims to explore the current knowledge and practice by targeting the gaps in anthropometric attribution, physical fitness ability, psychological strategies, and maturation status, thus discovering the most essential parameters among sepak takraw youth athletes. Afterward, the selected parameters were used for developing a scientific model of performance prediction in the game of sepak takraw. A quantitative approach and ex post facto design were applied in this current study. A total number of 104 male sepak takraw athletes volunteered to participate in this study. The average age range of the participants is 13 to 17 years old (15.5 + 1.76 years old). Multivariate analysis was used to accomplish all of the objectives, which included principal component analysis (PCA), multiple linear regression (MLR), and artificial neural network (ANN). The specific requirements of the young athlete were investigated while outlining a proposed methodology for future needs analysis. The PCA revealed the important anthropometric attribution parameters, which were found to be significant: body weight (BW), standing height (SH), sitting height (SitH), leg length (LL), waist circumference (WC), hip circumference (HC), calf circumference (CC), triceps skinfold (TS), subscapular skinfold (SubS), and suprailiac skinfold (SupS). For physical fitness ability, the essential parameters revealed were standing broad jump (SBJ), vertical jump (VJ), stork balance test for the non-dominant foot (SBT-n-df), star excursion balance test for anterior (SEBT-ant), star excursion balance test for anteromedial (SEBT-antmed), star excursion balance test for medial (SEBT-med), star excursion balance test for posteromedial (SEBT-postmed), star excursion balance test for posterior (SEBT-post), star excursion balance test for posterolateral (SEBT-postlat), star excursion balance test for lateral (SEBT-lat), 5m-multiple shuttle test for peak distance (5m-MST-pd), and 5m-multiple shuttle test for total distance (5m-MST-d). Meanwhile, the most substantial parameters in psychological strategies are C-goal setting (C-GS), C-automaticity (C-Auto), P-emotional control (P-EC), P-imagery (P-I), P-activation (P-Activ), and P-self talk (P-ST). The parameters identified as high factor loading were used for further analysis with one additional parameter called maturity status. MLR with three methods was implemented to estimate relationships among the parameters: standard mode, forward stepwise, and backward stepwise. The significant parameters and growth and maturation status were treated as independent variables, whereas performance analysis represented the dependent variable. The given R² of the standard mode shows 86% of the variability of the dependent variable explained by 29 explanatory variables. Meanwhile, for forward stepwise and backward stepwise modes, 34% and 86% of the variability of the dependent variable were explained by 4 explanatory variables and 18 explanatory variables, respectively. The summary of multiple linear regressions indicates that the maturity scale is the most influential parameter toward sepak takraw youth athlete performance. The model was reconfirmed by the non-linear model using the artificial neural network (ANN). The validation technique chosen to run the analysis is a k-fold method with 5-fold validation. ANN was run starting with 29 significant variables, and the models respected 18 and 4 variables derived from MLR. A feedforward neural network was used (multilayer perceptron) with 29, 18, and 4 neurons with a single hidden layer. For 29 significant variables, the best architecture network was 29-9-1 (R²: 0.998, RMSE: 0.585). For 18 and 4 significant variables, ANNs produced the best architecture networks 18-5-1 (R²: 0.954, RMSE: 2.744) and 4-5-1 (R²: 0.671, RMSE: 7.690), respectively. This current study offers a scientific method to identify the most influential parameter in sepak takraw. Identifying the most essential parameter in a particular sport is a major step toward enhancing performance, and the performance of sepak takraw youth athletes could be well predicted if an appropriate scientific method is applied. The scientific method used a variety of mathematical analyses to obtain solid and objective findings. Therefore, these findings have provided valuable information regarding specific measurements of anthropometric attribution, physical fitness ability, psychological strategies, and maturation status for sepak takraw athlete performance. The application of both linear and non-linear models in predicting athlete performance provided solid and objective results. The benefit of using ANNs is that they outperform MLRs and have the advantage of accounting for non-linear relationships. Finally, the application of intelligent statistical methods may ease coaches and managers in selecting future potential sepak takraw youth athletes with less cost, energy, and time. Dissertations, Academic Youth Athlete Development Sepak Takraw Performance Anthropometric and Psychological Parameters Thesis |
| spellingShingle | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| state | Terengganu |
| subject | Technological innovations Artificial intelligence Data processing Dissertations, Academic |
| summary | Under the umbrella of positive youth athlete development, physical fitness and performance represent an essential area of research for youth elite athletes. The individual competency a young person possesses determines their capacity to effectively navigate the turbulence of performance from beginner to intermediate, and followed by elite performance. An increase in the knowledge of the important parameters to enhance athlete performance, therefore, assists in the development of an appropriate model and evaluation of the sepak takraw youth development model. This thesis aims to explore the current knowledge and practice by targeting the gaps in anthropometric attribution, physical fitness ability, psychological strategies, and maturation status, thus discovering the most essential parameters among sepak takraw youth athletes. Afterward, the selected parameters were used for developing a scientific model of performance prediction in the game of sepak takraw. A quantitative approach and ex post facto design were applied in this current study. A total number of 104 male sepak takraw athletes volunteered to participate in this study. The average age range of the participants is 13 to 17 years old (15.5 + 1.76 years old). Multivariate analysis was used to accomplish all of the objectives, which included principal component analysis (PCA), multiple linear regression (MLR), and artificial neural network (ANN). The specific requirements of the young athlete were investigated while outlining a proposed methodology for future needs analysis. The PCA revealed the important anthropometric attribution parameters, which were found to be significant: body weight (BW), standing height (SH), sitting height (SitH), leg length (LL), waist circumference (WC), hip circumference (HC), calf circumference (CC), triceps skinfold (TS), subscapular skinfold (SubS), and suprailiac skinfold (SupS). For physical fitness ability, the essential parameters revealed were standing broad jump (SBJ), vertical jump (VJ), stork balance test for the non-dominant foot (SBT-n-df), star excursion balance test for anterior (SEBT-ant), star excursion balance test for anteromedial (SEBT-antmed), star excursion balance test for medial (SEBT-med), star excursion balance test for posteromedial (SEBT-postmed), star excursion balance test for posterior (SEBT-post), star excursion balance test for posterolateral (SEBT-postlat), star excursion balance test for lateral (SEBT-lat), 5m-multiple shuttle test for peak distance (5m-MST-pd), and 5m-multiple shuttle test for total distance (5m-MST-d). Meanwhile, the most substantial parameters in psychological strategies are C-goal setting (C-GS), C-automaticity (C-Auto), P-emotional control (P-EC), P-imagery (P-I), P-activation (P-Activ), and P-self talk (P-ST). The parameters identified as high factor loading were used for further analysis with one additional parameter called maturity status. MLR with three methods was implemented to estimate relationships among the parameters: standard mode, forward stepwise, and backward stepwise. The significant parameters and growth and maturation status were treated as independent variables, whereas performance analysis represented the dependent variable. The given R² of the standard mode shows 86% of the variability of the dependent variable explained by 29 explanatory variables. Meanwhile, for forward stepwise and backward stepwise modes, 34% and 86% of the variability of the dependent variable were explained by 4 explanatory variables and 18 explanatory variables, respectively. The summary of multiple linear regressions indicates that the maturity scale is the most influential parameter toward sepak takraw youth athlete performance. The model was reconfirmed by the non-linear model using the artificial neural network (ANN). The validation technique chosen to run the analysis is a k-fold method with 5-fold validation. ANN was run starting with 29 significant variables, and the models respected 18 and 4 variables derived from MLR. A feedforward neural network was used (multilayer perceptron) with 29, 18, and 4 neurons with a single hidden layer. For 29 significant variables, the best architecture network was 29-9-1 (R²: 0.998, RMSE: 0.585). For 18 and 4 significant variables, ANNs produced the best architecture networks 18-5-1 (R²: 0.954, RMSE: 2.744) and 4-5-1 (R²: 0.671, RMSE: 7.690), respectively. This current study offers a scientific method to identify the most influential parameter in sepak takraw. Identifying the most essential parameter in a particular sport is a major step toward enhancing performance, and the performance of sepak takraw youth athletes could be well predicted if an appropriate scientific method is applied. The scientific method used a variety of mathematical analyses to obtain solid and objective findings. Therefore, these findings have provided valuable information regarding specific measurements of anthropometric attribution, physical fitness ability, psychological strategies, and maturation status for sepak takraw athlete performance. The application of both linear and non-linear models in predicting athlete performance provided solid and objective results. The benefit of using ANNs is that they outperform MLRs and have the advantage of accounting for non-linear relationships. Finally, the application of intelligent statistical methods may ease coaches and managers in selecting future potential sepak takraw youth athletes with less cost, energy, and time. |
| title | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| title_full | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| title_fullStr | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| title_full_unstemmed | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| title_short | 2019_The Application of Artificial Neural Network Technique for Developing Sepak Takraw Youth Performance Model |
| title_sort | 2019_the application of artificial neural network technique for developing sepak takraw youth performance model |