Mitigating Bias in Fitbit Data: A Comprehensive Analysis and Model Enhancement using Ensemble learning

Jayeoba, Olayinka Mayowa (2024) Mitigating Bias in Fitbit Data: A Comprehensive Analysis and Model Enhancement using Ensemble learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Over time, wearable technology has revolutionized the way people manage their health and fitness. However, there are still some worries about potential biases in the data these devices produce, especially when it comes to the result conclusion Fitbit device gives. This paper undertakes a multifaceted exploration to detect, understand, and mitigate biases in Fitbit data, with a specific focus on calorie expenditure and sleep patterns. The study aims to not only identify and understand biases in Fitbit calorie and sleep data but also propose and implement effective solutions, culminating in the enhancement of predictive models using linear regression and random forest models to train an improved predictive model for calorie expenditure and sleep tracking. This would also ensure the improved accuracy of health and fitness data, contributing to a more reliable and trustworthy wearable technology ecosystem.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Trinh, Anh Duong UNSPECIFIED
Uncontrolled Keywords:	Fitbit; Wearable Technology; Bias Detection; Bias Mitigation; Linear Regression; Random Forest; Calorie Tracking; Sleep Pattern
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence B Philosophy. Psychology. Religion > BJ Ethics > Conduct of life > Reliability > Information integrity > Data integrity H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Tamara Malone
Date Deposited:	07 Apr 2025 11:50
Last Modified:	07 Apr 2025 11:50
URI:	https://norma.ncirl.ie/id/eprint/7382

Actions (login required)

View Item