Using LSTM Networks and Future Gradient Values to Forecast Heart Rate in Biking

Henry Gilbert, Jules White, Quchen Fu, Douglas Schmidt

2022

Abstract

Heart Rate prediction in cycling potentially allows for more effective and optimized training for a given individual. Utilizing a combination of feature engineering and hybrid Long Short-Term Memory (LSTM) models, this paper provides two research contributions. First, it provides an LSTM model architecture that accurately forecasts the heart rate of a bike rider up to 10 minutes into the future when given the future gradient values of the course. Second, it presents a novel model success metric optimized for deriving a model’s accuracy to predict heart rate while an athlete is zone training. These contributions provide the foundations for other applications, such as optimized zone training and offline reinforcement models to learn fatigue embeddings.

Paper Citation

in Harvard Style

Gilbert H., White J., Fu Q. and Schmidt D. (2022). Using LSTM Networks and Future Gradient Values to Forecast Heart Rate in Biking. In - icSPORTS, ISBN , pages 0-0. DOI: 10.5220/0011541800003321

in Bibtex Style

@conference{icsports22,
author={Henry Gilbert and Jules White and Quchen Fu and Douglas Schmidt},
title={Using LSTM Networks and Future Gradient Values to Forecast Heart Rate in Biking},
booktitle={ - icSPORTS,},
year={2022},
pages={},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011541800003321},
isbn={},
}

in EndNote Style

TY - CONF

JO - - icSPORTS,
TI - Using LSTM Networks and Future Gradient Values to Forecast Heart Rate in Biking
SN -
AU - Gilbert H.
AU - White J.
AU - Fu Q.
AU - Schmidt D.
PY - 2022
SP - 0
EP - 0
DO - 10.5220/0011541800003321