2018_Multivariate Analysis of a Multicomponent Model of Archery Performance
| Format: | General Document |
|---|
| _version_ | 1860798105515982848 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2018-07-22 |
| format | General Document |
| id | 15940 |
| institution | UniSZA |
| originalfilename | MULTIVARIATE ANALYSIS OF A MULTICOMPONENT MODEL OF ARCHERY PERFORMANCE (PHD_2018).pdf |
| person | Rabiu Mu’azu Musa |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15940 |
| sourcemedia | Server storage Scanned document |
| spelling | 15940 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15940 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 17 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access Universiti Sultan Zainal Abidin SAMBox 2.3.4; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) Copyright©PWB2025 Multivariate analysis Multivariate Analysis 2018-07-22 MULTIVARIATE ANALYSIS OF A MULTICOMPONENT MODEL OF ARCHERY PERFORMANCE (PHD_2018).pdf Rabiu Mu’azu Musa Sports performance Performance analysis 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance Successful performance in the sport of archery is reliant upon a multitude of factors. For athletes to develop and excel in the sport, the interactions of several performance-related variables must be considered. A holistic approach in establishing a model that takes cognizance into all the possible related variables is needful. This study measured four major components of performance-related variables viz. fitness-motor skills, anthropometric, biomechanical-physiological and psychological-personality traits components. The objectives of the study were to examine and highlight the variables in each component, classify the archers under study as high-potential archers (HPA) or low potential archers (LPA) based on their performances from the variables and to eventually apply a machine -learning based technique in classifying the archers for developing a model. 50 youth archers with the mean age and standard deviation of (17.0 ± 0.56) drawn from various archery programmes completed a one-end archery shooting score test. Standard measurement of fitness and motor-ability, anthropometric, biomechanical-physiological and psychological-personality traits components were completed prior to the archers shooting tests. A multi-hierarchical agglomerative cluster analysis (HACA) was employed to cluster the archers in relation to their performance on the measured performance related variables while discriminant analysis (DA) of standard, backward stepwise and forward stepwise mode methods were applied on the clusters defined by HACA to view through variation of relative performance. The artificial neural network (ANN), k-nearest neighbour (k-NN) and a support vector machine (SVM) learning algorithms functions were trained to predict and classify the HPA and LPA. The HACA clustered the archers into HPA and LPA based on the measured performances variables. It was apparent from the HACA analysis that 38 archers were grouped as HPA while 12 archers were LPA. In the same vein, the standard, backward stepwise and forward stepwise mode methods for the DA demonstrated excellent precision and discrimination of 74.00%, 98.00% and 96.00% with 16, 7 and 3 modes respectively. Finally, the ANN, SVM and the k-NN learning algorithms used in the study for predicting the HPA revealed that the ANN and k-NN outperformed the SVM across all performance metrics. Nevertheless, it is worth to note that all the classification models exhibit reasonably accurate classification as their classification accuracies, as well as the precisions for all the evaluated parameters, are between the ranges of 0.9 to 1. Furthermore, a relatively strong sensitivity and specificity are observed between the classification and the selected performance variables for both models, suggesting the significance of the selected performance components in developing the model in the present study. The study has shown that the utilisation of multivariate analysis and machine learning techniques cannot be over-emphasised. The study has demonstrated that high potential archers could be accurately identify in the sport of archery by considering some sets of performance related variables which would, in the long run, reduce cost and energy during talent identification and development programmes. Dissertations, Academic Talent Identification Machine Learning Classification Archery Performance Thesis |
| spellingShingle | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| state | Terengganu |
| subject | Multivariate analysis Sports performance Performance analysis Dissertations, Academic |
| summary | Successful performance in the sport of archery is reliant upon a multitude of factors. For athletes to develop and excel in the sport, the interactions of several performance-related variables must be considered. A holistic approach in establishing a model that takes cognizance into all the possible related variables is needful. This study measured four major components of performance-related variables viz. fitness-motor skills, anthropometric, biomechanical-physiological and psychological-personality traits components. The objectives of the study were to examine and highlight the variables in each component, classify the archers under study as high-potential archers (HPA) or low potential archers (LPA) based on their performances from the variables and to eventually apply a machine -learning based technique in classifying the archers for developing a model. 50 youth archers with the mean age and standard deviation of (17.0 ± 0.56) drawn from various archery programmes completed a one-end archery shooting score test. Standard measurement of fitness and motor-ability, anthropometric, biomechanical-physiological and psychological-personality traits components were completed prior to the archers shooting tests. A multi-hierarchical agglomerative cluster analysis (HACA) was employed to cluster the archers in relation to their performance on the measured performance related variables while discriminant analysis (DA) of standard, backward stepwise and forward stepwise mode methods were applied on the clusters defined by HACA to view through variation of relative performance. The artificial neural network (ANN), k-nearest neighbour (k-NN) and a support vector machine (SVM) learning algorithms functions were trained to predict and classify the HPA and LPA. The HACA clustered the archers into HPA and LPA based on the measured performances variables. It was apparent from the HACA analysis that 38 archers were grouped as HPA while 12 archers were LPA. In the same vein, the standard, backward stepwise and forward stepwise mode methods for the DA demonstrated excellent precision and discrimination of 74.00%, 98.00% and 96.00% with 16, 7 and 3 modes respectively. Finally, the ANN, SVM and the k-NN learning algorithms used in the study for predicting the HPA revealed that the ANN and k-NN outperformed the SVM across all performance metrics. Nevertheless, it is worth to note that all the classification models exhibit reasonably accurate classification as their classification accuracies, as well as the precisions for all the evaluated parameters, are between the ranges of 0.9 to 1. Furthermore, a relatively strong sensitivity and specificity are observed between the classification and the selected performance variables for both models, suggesting the significance of the selected performance components in developing the model in the present study. The study has shown that the utilisation of multivariate analysis and machine learning techniques cannot be over-emphasised. The study has demonstrated that high potential archers could be accurately identify in the sport of archery by considering some sets of performance related variables which would, in the long run, reduce cost and energy during talent identification and development programmes. |
| title | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| title_full | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| title_fullStr | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| title_full_unstemmed | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| title_short | 2018_Multivariate Analysis of a Multicomponent Model of Archery Performance |
| title_sort | 2018_multivariate analysis of a multicomponent model of archery performance |