University of Twente Student Theses


Predicting the Internal Load of Amateur Athlete’s Based on Their External Load Using Accessible Sensors

Loof, R. (2019) Predicting the Internal Load of Amateur Athlete’s Based on Their External Load Using Accessible Sensors.

[img] PDF
Abstract:Injuries are major determinants of an athlete’s chance at success. Training programs, therefore, try to maximize the result of the training, while minimizing the risk of an injury. This is commonly done by looking at the training load, which can be described by the external- and internal load. A good training program is based on the internal load. Unfortunately, it is hard to keep track of the internal load, whereas it is rela-tively easy to measure the external load. As a result, it be-comes interesting to investigate to what extent the external load can predict the internal load. Research regarding the predictability of the internal load based on the external load has been performed multiple times with the use of expensive sensors which are not accessible/affordable for amateur athletes. This research extends previous research by investi-gating the predictability of an athlete’s heart rate, based on external load measures that are collected using accessi-ble/affordable sensors for amateur athletes. Several measures for the external load have been identified and their relevance is investigated. Using these measures, the accuracy of several machine learning algorithms is evaluated. The Ridge Regres-sion algorithm proved to be able to predict the general trend of moderate heart rates with the use of an accelerometer, gyroscope and GPS tracker.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:50 technical science in general
Programme:Business & IT BSc (56066)
Keywords:Training load, Machine learning, Injury prevention, Predictive analysis
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page