E-Thesis 119 views 117 downloads
Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data / MARK WHITE
Swansea University Author: MARK WHITE
PDF | E-Thesis – open access
Copyright: The author, Mark George Eric White, 2021.Download (9.82MB)
DOI (Published version): 10.23889/SUthesis.58286
Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternati...
|Supervisor:||Bezodis, Neil ; Neville, Jonathon ; Rees, Paul|
No Tags, Be the first to tag this record!
Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternatives include predicting peak power from jump flight times, or using Newtonian methods based on body-worn inertial sensor data, but so far neither has yielded sufficiently accurate estimates. This thesis aims to develop a generalisable model for predicting peak power based on Functional Principal Component Analysis applied to body-worn accelerometer data. Data was collected from 69 male and female adults, engaged in sports at recreational, club or national levels. They performed up to 16 countermovement jumps each, with and without arm swing, 696 jumps in total. Peak power criterion measures were obtained from force platforms, and characteristic features from accelerometer data were extracted from four sensors attached to the lower back, upper back and both shanks. The best machine learning algorithm, jump type and sensor anatomical location were determined in this context. The investigation considered signal representation (resultant, triaxial or a suitable transform), preprocessing (smoothing, time window and curve registration), feature selection and data augmentation (signal rotations and SMOTER). A novel procedure optimised the model parameters based on Particle Swarm applied to a surrogate Gaussian Process model. Model selection and evaluation were based on nested cross validation (Monte Carlo design). The final optimal model had an RMSE of 2.5 W·kg-1, which compares favourably to earlier research (4.9 ± 1.7 W·kg-1 for flight-time formulae and 10.7 ± 6.3 W·kg-1 for Newtonian sensor-based methods). Whilst this is not yet sufficiently accurate for applied practice, this thesis has developed and comprehensively evaluated new techniques, which will be valuable to future biomechanical applications.
ORCiD identifier https://orcid.org/0000-0001-5404-9289
Countermovement jump, peak power, machine learning, functional principal component analysis, nested cross validation, optimisation
Faculty of Science and Engineering