Light-Weight Convolutional Neural Network Model for Early Emotional Detection

Reyna Torres, Luis Antonio (2024) Light-Weight Convolutional Neural Network Model for Early Emotional Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration Manual) Download (756kB) | Preview

Abstract

This research addresses the development of a Light-Weight Convolutional Neural Network(CNN) Model and its implementation for early emotional detection in users based on images. Early detection of emotions is crucial to address problems such as stress, anxiety, and depression, which can negatively impact users’ daily performance and quality of life. The research focuses on developing and training an efficient CNN model, optimized for mobile devices, that is able to identify emotions such as happy, sad, and angry from facial expressions captured in real-time. The Model receives supervised training with seven different emotions based on labeled images. Finally, the performance of the model is evaluated with a stack of algorithms to measure its accuracy and loss in classifying images based on the training provided. For the deployment of this model, a mobile app is developed using iOS technology like Swift and Core ML framework for Machine Learning Models, allowing its implementation on devices such as the iPhone and iPad to process and analyze images in real-time. The implementation of artificial intelligence in mobile applications offers a powerful tool for emotional monitoring and support, due to its portable use and wide data provided by users, contributing to the well-being of users.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science B Philosophy. Psychology. Religion > Psychology > Emotions Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > RA790 Mental Health
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	02 Jul 2025 17:59
Last Modified:	02 Jul 2025 17:59
URI:	https://norma.ncirl.ie/id/eprint/8000

Actions (login required)

View Item