Ghunalan, Ashok Kumar (2024) Deep learning approach to analyze Sleep & Apps usage pattern to predict Problematic Smartphone Usage (PSU). Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (3MB) | Preview |
Abstract
Problematic Smartphone Usage (PSU) and its relationship with poor sleep quality has been the rising concerns on mental and physical health. This study aims to develop deep learning techniques to analyze sleep duration and apps usage pattern to predict PSU. The objective is to compare all the models built to accurately predict PSU. Two distinct datasets have been employed in this research, one for analysing the sleep quality and another for apps usage. Deep learning models like Feedforward Neural Networks (FNN), Convolution Neural Networks (CNN) and Recurrent Neural Networks Long-Short Term Memory (RNN-LSTM) were developed and evaluated. Hyperparameter tuning is used for the sleep data to optimize the model performance. For the sleep quality dataset, the RNNLSTM and CNN model with hyperparameter tunning has outperformed the other models with highest accuracy of 94%. On the other hand, FNN has slightly less accuracy with high level of precision. For the app usage dataset, FNN and RNN has achieved 99.87% & 99.80% accuracy. The CNN was slight less in accuracy 98% and showed lower precision. RNN-LSTM model emerged as a consistent model for both the dataset by offering balanced approach to predict PSU. Hyperparameter tuning has helped to increase model performance only for the CNN model.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Makki, Ahmed UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Q Science > QA Mathematics > Computer software > Mobile Phone Applications T Technology > T Technology (General) > Information Technology > Computer software > Mobile Phone Applications |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 18 Aug 2025 15:11 |
Last Modified: | 18 Aug 2025 15:11 |
URI: | https://norma.ncirl.ie/id/eprint/8569 |
Actions (login required)
![]() |
View Item |