Computer-aided parameter selection for resistance exercise using machine vision-based capability profile estimation
Abstract
The penetration of mathematical modelling in sports science to date has been highly limited. In particular and in contrast to most other scientific disciplines, sports science research has been characterized by comparatively little effort investment in the development of phenomenological models. Practical applications of such models aimed at assisting trainees or sports professionals more generally remain nonexistent. The present paper aims at addressing this gap. We adopt a recently proposed mathematical model of neuromuscular engagement and adaptation, and develop around it an algorithmic framework which allows it to be employed in actual training program design and monitoring by resistance training practitioners (coaches or athletes). We first show how training performance characteristics can be extracted from video sequences, effortlessly and with minimal human input, using computer vision. The extracted characteristics are then used to fit the adopted model i.e. to estimate the values of its free parameters, from differential equations of motion in what is usually termed the inverse dynamics problem. A computer simulation of training bouts using the estimated (and hence athlete specific) model is used to predict the effected adaptation and with it the expected changes in future performance capabilities. Lastly we describe a proof-of-concept software tool we developed which allows the practitioner to manipulate training parameters and immediately see their effect on predicted adaptation (again, on an athlete specific basis). Thus, this work presents a holistic view of the monitoring–assessment–adjustment loop which lies at the centre of successful coaching. By bridging the gap between theoretical and applied aspects of sports science, the present contribution highlights the potential of mathematical and computational modelling in this field and serves to encourage further research focus in this direction.
Citation
Arandelovic , O 2017 , ' Computer-aided parameter selection for resistance exercise using machine vision-based capability profile estimation ' , Augmented Human Research , vol. 2 , 4 . https://doi.org/10.1007/s41133-017-0007-1
Publication
Augmented Human Research
Status
Peer reviewed
ISSN
2365-4317Type
Journal article
Rights
© The Author(s) 2017. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Related items
Showing items related by title, author, creator and subject.
-
Virtual Worlds and the 3D Web – time for convergence?
Bakri, Hussein; Allison, Colin; Miller, Alan Henry David; Oliver, Iain Angus (Springer, 2016) - Conference itemMulti-User Virtual Worlds (MUVW) such as Open Wonderland and OpenSim have proved to be fruitful platforms for innovative educational practice, supporting exploratory learning and generating true engagement. However, when ... -
The effect of visual and interactive representations on human performance and preference with scalar data fields
Han, Han L.; Nacenta, Miguel A. (Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine, 2020-05-28) - Conference item2D scalar data fields are often represented as heatmaps because color can help viewers perceive structure without having to interpret individual digits. Although heatmaps and color mapping have received much research ... -
LOC8 : A location model and extensible framework for programming with location
Stevenson, Graeme Turnbull; Ye, Juan; Dobson, Simon Andrew; Nixon, Paddy (2010) - Journal articleLocation is a core concept in most pervasive systems-and one that's surprisingly hard to deal with flexibly. Using a location model supporting a range of expressive representations for spaces, spatial relationships, and ...