Identification of high-performance volleyball players from anthropometric variables and psychological readiness: A machine-learning approach

Rabiu Muazu Musa, Anwar P.P. Abdul Majeed*, Muhammad Zuhaili Suhaimi, Mohamad Razali Abdullah, Mohd Azraai Mohd Razman, Deboucha Abdelhakim, Noor Azuan Abu Osman

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

Modern indoor volleyball has evolved into a high-level strength sport and is seen as one of the most popular open-skilled team sports. The nature of the sport as an open-based skill requires players to have a high degree of both psychological skill and physical ability to cope with the sport’s externally and internally induced pace. The purposes of this study were to examine the essential basic anthropometric variables, as well as competition and practice psychological readiness, that could provide a performance edge and identify high and low-performance players based on the parameters. The anthropometric variables of height, weight, and age were assessed, while the test for performance strategies instrument was used to evaluate competition and practice psychological readiness skills of the players. The players’ performances were analyzed in real-time during a volleyball tournament. The Louvain clustering algorithm was used to determine the performance class of the players with reference to the variables evaluated. A total of 45 players were ascertained as high-performance volleyball players (HVP), while 20 players were deemed as low-performance volleyball players (LVP) via the clustering analysis technique. The logistic regression classifier was used to classify the performance of the players. Nonetheless, owing to the skewed representation between the HVP and LVP during the training of the model, the Synthetic Minority Oversampling TEchnique (SMOTE) was employed to artificially increase the minority class dataset to avoid the overfitting notion upon classification. It was shown from the study that, through the machine learning pipeline developed, an excellent identification of the HVP and LVP could be attained. The findings could be invaluable to coaches and other relevant stakeholders in team preparation and the selection of high-performance players in volleyball.

Original languageEnglish
Pages (from-to)317-324
Number of pages8
JournalProceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology
Volume237
Issue number4
DOIs
Publication statusAccepted/In press - 2021
Externally publishedYes

Keywords

  • Anthropometric index
  • high-performance players
  • indoor volleyball
  • logistic regression
  • psychological readiness
  • SMOTE

Fingerprint

Dive into the research topics of 'Identification of high-performance volleyball players from anthropometric variables and psychological readiness: A machine-learning approach'. Together they form a unique fingerprint.

Cite this