Training plan evolution based on training models

Schaefer, David; Asteroth, Alexander; Ludwig, Melanie

doi:10.1109/inista.2015.7276739

Cited by 17 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, due to the high number of possible training inputs, the model should be suitable for high-dimensional optimization, i.e., for derivative-based optimization [24]. Fourth, the model should allow to incorporate real-life constraints into the optimization problem, e.g., days or weeks off [38]. Last, the model should be assessed for its predictive ability.…”

Section: Model Prerequisitesmentioning

confidence: 99%

A mathematical model-based approach to optimize loading schemes of isometric resistance training sessions

Herold

Sommer

2020

Preprint

View full text Add to dashboard Cite

Individualized resistance training (RT) is necessary to optimize training results. A model-based optimization of loading schemes could provide valuable impulses for practitioners and complement the predominant manual program design by customizing the loading schemes to the trainee and the training goals. We compile a literature overview of model-based approaches used to simulate or optimize the response to single RT sessions or to longterm RT plans in terms of strength, power, muscle mass, or local muscular endurance by varying the loading scheme. To the best of our knowledge, contributions employing a predictive model to algorithmically optimize loading schemes for different training goals are nonexistent in the literature. Thus, we propose to set up optimal control problems as follows. For the underlying dynamics, we use a phenomenological model of the time course of maximum voluntary isometric contraction force. Then, we provide mathematical formulations of key performance indicators for loading schemes identified in sport science and use those as objective functionals or constraints. We then solve those optimal control problems using previously obtained parameter estimates for the elbow flexors. We discuss our choice of training goals, analyze the structure of the computed solutions, and give evidence of their real-life feasibility. The proposed optimization methodology is independent from the underlying model and can be transferred to more elaborate physiological models once suitable ones become available.

show abstract

Section: Model Prerequisitesmentioning

confidence: 99%

A mathematical model-based approach to optimize loading schemes of isometric resistance training sessions

Herold

Sommer

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This is achieved in practice by performing a period of training and performance measurement with parameters retrospectively fit to best match the input and output data generated. This process is referred to as the 'model training' phase and once complete, the model and fitted parameters can be used to predict future responses to physical training and inform its design [6]. Accurate quantification of training load and regular best-effort criterion trials (e.g.…”

Section: Introductionmentioning

confidence: 99%

The effects of measurement error and testing frequency on the fitness-fatigue model applied to resistance training: A simulation approach

Hemingway

Burgess

Elyan

et al. 2019

International Journal of Sports Science & Coaching

View full text Add to dashboard Cite

This study investigated the effects of measurement error and testing frequency on prediction accuracy of the standard fitness-fatigue model. A simulation-based approach was used to systematically assess measurement error and frequency inputs commonly used when monitoring the training of athletes. Two hypothetical athletes (intermediate and advanced) were developed and realistic training loads and daily ‘true’ power values were generated using the fitness-fatigue model across 16 weeks. Simulations were then completed by adding Gaussian measurement errors to true values with mean 0 and set standard deviations to recreate more and less reliable measurement practices used in real-world settings. Errors were added to the model training phase (weeks 1–8) and sampling of data was used to recreate different testing frequencies (every day to once per week) when obtaining parameter estimates. In total, 210 sets of simulations (N = 104 iterations) were completed using an iterative hill-climbing optimisation technique. Parameter estimates were then combined with training loads in the model testing phase (weeks 9–16) to quantify prediction errors. Regression analyses identified positive associations between prediction errors and the linear combination of measurement error and testing frequency ([Formula: see text]=0.87–0.94). Significant model improvements (P < 0.001) were obtained across all scenarios by including an interaction term demonstrating greater deleterious effects of measurement error at low testing frequencies.The findings of this simulation study represent a lower-bound case and indicate that in real-world settings, where a fitness-fatigue model is used to predict training response, measurement practices that generate coefficients of variation greater than [Formula: see text]4% will not provide satisfactory results.

show abstract

“…The model accounted for two primary physiological components: the positive effects of training, called fitness, and the negative effects of training, called fatigue. Several studies have built upon the Banister model with promising results [5,6,8,10,12,15]. However, these studies also recognized that the Banister model was based on linear systems theory, which limits its accuracy and applicability.…”

Section: Introductionmentioning

confidence: 99%

“…However, these studies also recognized that the Banister model was based on linear systems theory, which limits its accuracy and applicability. One concerning feature from past linear performance models is that they predict steadystate performance continues to increase indefinitely with increases in training stress [12]. Thus linear performance models only capture the temporal or short-term negative effects on performance and not the important long-term and nonlinear relationships that limit performance.…”

Section: Introductionmentioning

confidence: 99%

“…It is the incorporation of these well-known phenomena into a performance modeling framework that provides a more realistic and necessary counter balance; the inclusion of these phenomena also allows performance to be optimized. However, despite the potential concerns associated with the linear modeling approach, it has been used to successfully inform training strategies for many athletes by approximating optimal recovery times between workouts, predicting the success of training regimens, and determining how an athlete should taper before a competition [5,7,8,10,12,13,15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A nonlinear model for the characterization and optimization of athletic training and performance

Turner

Mazzoleni

Little

et al. 2017

Biomedical Human Kinetics

View full text Add to dashboard Cite

SummaryStudy aim: Mathematical models of the relationship between training and performance facilitate the design of training protocols to achieve performance goals. However, current linear models do not account for nonlinear physiological effects such as saturation and over-training. This severely limits their practical applicability, especially for optimizing training strategies. This study describes, analyzes, and applies a new nonlinear model to account for these physiological effects. Material and methods:This study considers the equilibria and step response of the nonlinear differential equation model to show its characteristics and trends, optimizes training protocols using genetic algorithms to maximize performance by applying the model under various realistic constraints, and presents a case study fitting the model to human performance data.Results: The nonlinear model captures the saturation and over-training effects; produces realistic training protocols with training progression, a high-intensity phase, and a taper; and closely fits the experimental performance data. Fitting the model parameters to subsets of the data identifies which parameters have the largest variability but reveals that the performance predictions are relatively consistent. Conclusions: These findings provide a new mathematical foundation for modeling and optimizing athletic training routines subject to an individual's personal physiology, constraints, and performance goals.

show abstract

Training plan evolution based on training models

Cited by 17 publications

References 15 publications

A mathematical model-based approach to optimize loading schemes of isometric resistance training sessions

A mathematical model-based approach to optimize loading schemes of isometric resistance training sessions

The effects of measurement error and testing frequency on the fitness-fatigue model applied to resistance training: A simulation approach

A nonlinear model for the characterization and optimization of athletic training and performance

Contact Info

Product

Resources

About