The employment of Support Vector Machine to classify high and low performance archers based on bio-physiological variables

International Conference on Innovative Technology, Engineering and Sciences 2018

工业技术;自然科学

Taha, Zahari^1 ; Musa, Rabiu Muazu^1,2 ; Abdul Majeed, Anwar P. P.^1 ; Abdullah, Mohamad Razali^2 ; Abdullah, Muhammad Amirul^1 ; Hassan, Mohd Hasnun Arif^1 ; Khalil, Zubair^1

Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing Engineering, Universiti Malaysia Pahang, Pekan, Pahang

26600, Malaysia^1

Faculty of Applied Social Sciences, Universiti Sultan Zainal Abidin, Terengganu Kuala Terengganu

21300, Malaysia^2

关键词: Classification accuracy;    Diastolic blood pressures;    K-means cluster analysis;    Kernel function;    Respiratory rate;    Resting heart rate;    Standard deviation;    Systolic blood pressure;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/342/1/012020/pdf
DOI  :  10.1088/1757-899X/342/1/012020

来源: IOP

【 摘 要 】

The present study employs a machine learning algorithm namely support vector machine (SVM) to classify high and low potential archers from a collection of bio-physiological variables trained on different SVMs. 50 youth archers with the average age and standard deviation of (17.0 .056) gathered from various archery programmes completed a one end shooting score test. The bio-physiological variables namely resting heart rate, resting respiratory rate, resting diastolic blood pressure, resting systolic blood pressure, as well as calories intake, were measured prior to their shooting tests. k-means cluster analysis was applied to cluster the archers based on their scores on variables assessed. SVM models i.e. linear, quadratic and cubic kernel functions, were trained on the aforementioned variables. The k-means clustered the archers into high (HPA) and low potential archers (LPA), respectively. It was demonstrated that the linear SVM exhibited good accuracy with a classification accuracy of 94% in comparison the other tested models. The findings of this investigation can be valuable to coaches and sports managers to recognise high potential athletes from the selected bio-physiological variables examined.