Predictive Modelling of Physical Activity Intensity Using Deep Neural Networks
This study presents a novel approach to quantifying physical exertion using various machine learning algorithms. Such techniques include, among others, random forests, decision trees, linear regression, and gradient boosting. A large dataset has the potential to predict numerous variables, including...
Saved in:
Published in | 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) pp. 1 - 6 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
18.04.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | This study presents a novel approach to quantifying physical exertion using various machine learning algorithms. Such techniques include, among others, random forests, decision trees, linear regression, and gradient boosting. A large dataset has the potential to predict numerous variables, including but not limited to heart rate, calories expended, intensity, steps, and time range. This is the primary objective of the investigation. To mitigate the risk of hybridization, a comprehensive evaluation is conducted on each machine learning model before granting it autonomous operation to ascertain its capability of comprehending the complexity of exercise data. The study thoroughly examines the intricacies of contrasting multiple methodologies to improve the capacity to forecast diverse types of physical activity. This study establishes the foundation for enhanced machine learning models that predict physical activity levels. Such advancements may have far-reaching consequences for individualized treatments, health surveillance, and fitness monitoring. |
---|---|
DOI: | 10.1109/ADICS58448.2024.10533642 |