Unleashing the power of Data: Personalized Anxiety Interventions

Periyasamy, Manoj Kumar (2023) Unleashing the power of Data: Personalized Anxiety Interventions. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

This research aims to examine how real-time data analytics may lead to personalized anxiety treatments. We use machine learning models combined with fitness tracker data so as to discover such patterns and potential predictors of anxiety disorders. In this study, data is used at the minute’s level of output of physical activities, heart rate recording and sleep monitoring. To ensure more credible and relevant insights, data pre-processing and feature selection techniques are utilized. Predictive machine learning models such as Linear Regression, Gradient Boosting, Decision Tree, and Random Forest are employed for the prediction of anxiety. The findings indicate that Random Forest outperforms other machine learning models, demonstrating the lowest MSE values across most features compared to other machine learning models. Although Decision Tree was competitive, it exhibited slightly higher MSE values. A comprehensive analysis involving Mean Squared Error (MSE) and R-squared further solidified Random Forest’s superiority, showcasing the lowest MSE and an impressive R-squared value. These results suggest that Random Forest excels in capturing intricate relationships within the data, making it particularly useful for precise anxiety level predictions. Finally, different deep learning models are also implemented, likely Feed-forward Neural Network and an Long Short Term Memory(LSTM). While both demonstrated comparable results results with R square values and MSE values. This shows that Neural Network also excels in capturing intricate relationships within the data which is useful for Anxiety prediction. The insights derived from this analysis not only contribute to refining predictive models but also advance the understanding of anxiety dynamics, catering to the broader goal of improving intervention strategies.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Chikkankod, Arjun UNSPECIFIED
Uncontrolled Keywords:	Machine Learning; Deep Learning; Decision Tree; Linear Regression; Gradient Boost; Random Forest; Long Short Term Memory; Feed-forward Neural Network; Fitness Tracking; Data Preprocessing; Health Monitoring
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > RA790 Mental Health Q Science > QA Mathematics > Computer software > Mobile Phone Applications T Technology > T Technology (General) > Information Technology > Computer software > Mobile Phone Applications R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	20 May 2025 14:14
Last Modified:	20 May 2025 14:14
URI:	https://norma.ncirl.ie/id/eprint/7589

Actions (login required)

View Item