Application of the principal component waveform analysis to identify improvements in vertical jump performance

Floría, Pablo; Sánchez-Sixto, Alberto; Harrison, Andrew J.

doi:10.1080/02640414.2018.1504602

“…After study titles and abstracts were screened, a further 2172 studies were removed. Accordingly, full-text versions of 498 studies were screened, with 32 studies 28 , 29 , 30 , 42 , 43 , 44 , 45 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 considered eligible for meta-analysis. The included studies involved 442 participants in 37 experimental groups and 376 participants in 32 control groups.…”

Section: Resultsmentioning

confidence: 99%

The effects of plyometric jump training on physical fitness attributes in basketball players: A meta-analysis

Ramírez‐Campillo

¹

,

García-Hermoso²,

Moran

³

et al. 2022

Journal of Sport and Health Science

View full text Add to dashboard Cite

“…Indeed, Functional Principal Component Analysis (FPCA) has been applied to a diverse range of applications in biomechanics. Studies have reported strong associations between FPCs and various performance or injury risk measures in sports, including rowing, swimming, weightlifting, race walking and jumping [41,[43][44][45][46][47][48][49][50][51]. These applications analysed the FPC scores using descriptive statistics, t-tests, ANOVA, discriminant analysis or a simple regression model to address their research questions.…”

Section: Introductionmentioning

confidence: 99%

Determining jumping performance from a single body-worn accelerometer using machine learning

White

¹

,

Bezodis

²

,

Neville

³

et al. 2022

View full text Add to dashboard Cite

External peak power in the countermovement jump is frequently used to monitor athlete training. The gold standard method uses force platforms, but they are unsuitable for field-based testing. However, alternatives based on jump flight time or Newtonian methods applied to inertial sensor data have not been sufficiently accurate for athlete monitoring. Instead, we developed a machine learning model based on characteristic features (functional principal components) extracted from a single body-worn accelerometer. Data were collected from 69 male and female athletes at recreational, club or national levels, who performed 696 jumps in total. We considered vertical countermovement jumps (with and without arm swing), sensor anatomical locations, machine learning models and whether to use resultant or triaxial signals. Using a novel surrogate model optimisation procedure, we obtained the lowest errors with a support vector machine when using the resultant signal from a lower back sensor in jumps without arm swing. This model had a peak power RMSE of 2.3 W·kg-1 (5.1% of the mean), estimated using nested cross validation and supported by an independent holdout test (2.0 W·kg-1). This error is lower than in previous studies, although it is not yet sufficiently accurate for a field-based method. Our results demonstrate that functional data representations work well in machine learning by reducing model complexity in applications where signals are aligned in time. Our optimisation procedure also was shown to be robust can be used in wider applications with low-cost, noisy objective functions.

show abstract

“…Indeed, Functional Principal Component Analysis (FPCA) has been applied to a diverse range of applications in biomechanics. Studies have reported strong associations between FPCs and various performance or injury risk measures in sports, including rowing, swimming, weightlifting, race walking and jumping [37,[39][40][41][42][43][44][45][46][47]. These applications analysed the FPC scores using descriptive statistics, t-tests, ANOVA, discriminant analysis or a simple regression model to address their research questions.…”

Section: Introductionmentioning

confidence: 99%

Determining jumping performance from a single body-worn accelerometer using machine learning

White

¹

,

Bezodis

²

,

Neville

³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

External peak power in the countermovement jump is frequently used to monitor athlete training. The gold standard method uses force platforms, but they are unsuitable for field-based testing. However, alternatives based on jump flight time or Newtonian methods applied to inertial sensor data have not been sufficiently accurate for athlete monitoring. Instead, we developed a machine learning model based on characteristic features (functional principal components) extracted from a single body-worn accelerometer. Data were collected from 69 male and female athletes at recreational, club or national levels, who performed 696 jumps in total. We considered vertical countermovement jumps (with and without arm swing), sensor anatomical locations, machine learning models and whether to use resultant or triaxial signals. Using a novel surrogate model optimisation procedure, we obtained the lowest errors with a support vector machine when using the resultant signal from a lower back sensor in jumps without arm swing. This model had a peak power RMSE of 2.3 W·kg-1 (5.1% of the mean), estimated using nested cross validation and supported by an independent holdout test (2.0 W·kg-1). This error is lower than in previous studies, although it is not yet sufficiently accurate for a field-based method. Our results demonstrate that functional data representations work well in machine learning by reducing model complexity in applications where signals are aligned in time. Our optimisation procedure also was shown to be robust can be used in wider applications with low-cost, noisy objective functions.

show abstract

Application of the principal component waveform analysis to identify improvements in vertical jump performance

Cited by 13 publications

References 31 publications

The effects of plyometric jump training on physical fitness attributes in basketball players: A meta-analysis

The effects of plyometric jump training on physical fitness attributes in basketball players: A meta-analysis

Determining jumping performance from a single body-worn accelerometer using machine learning

Determining jumping performance from a single body-worn accelerometer using machine learning

Contact Info

Product

Resources

About