Skip to content

The aim of this work was to predict the heart rate zones. To do this we applied several data transformation techniques which we then used to pull an Xgboost model.

License

Notifications You must be signed in to change notification settings

giulio-derasmo/Heart-Rate-Zones-Prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 

Repository files navigation

Heart Rate Zones Prediction

Kaggle Python scikit-learn SciPy

This project allowed us to win the Hackaton 2021/2022 reserved for students of the Statistical Learning course of the MSc in Data Science at the University of Rome, La Sapienza.

🏃 Run Baby Run 🏃🏻‍♀️

Heart rate zones, or HR zones, are a way to monitor how hard you’re training. There are typically 5+1 heart rate zones (Zone-0, Zone-1,…,Zone-5) based on the intensity of training with regard to the individual maximum heart rate.

Heart rate zones are closely linked to your aerobic and anaerobic thresholds. Understanding this can really help when considering heart rate zones exercise, especially your heart rate zones for running or heart rate zone training for other fitness goals.

The following HR zones chart shows the level of intensity as a percentage of Maximum Heart Rate used in each one.



Data Collection

Modern sports watches contain many sensors to monitor heart rate, cadence, altitude, etc. The readings are typically saved every once per second.

The data are coming from FIT files collected on many runs during 2021 and 2022. The runs were made in various environments, i.e. hilly and flat. Also, various efforts, e.g. long and slow runs and interval training, are included. The data collection was made using an Apple Watch accompanied by a Polar OH1 sensor.

Task

The data are relative to 1 minute long running efforts, the task is to predict the associated heart-rate zone being careful to obtain a performing model both on the public and on the private test set.

Team members

About

The aim of this work was to predict the heart rate zones. To do this we applied several data transformation techniques which we then used to pull an Xgboost model.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published