Improving Emotion Detection and Music Recommendation Through Advanced Facial Recognition and Optimized Hyper-parameters Tuning

Sharma, Vipin (2024) Improving Emotion Detection and Music Recommendation Through Advanced Facial Recognition and Optimized Hyper-parameters Tuning. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Facial expression recognition is an important component of human-computer interaction which enables systems to understand and respond to human emotions. This study investigates how hyper-parameters optimize the accuracy and flexibility of facial expression recognition models and their integration with a music recommendation system. The primary goal is to develop the personalized music recommendation model on seven types of different facial expressions and determine the impact of hyper-parameters such as learning rate, optimizers, batch size, number of epochs, and activation functions on model performance. In the research, Convolutional neural networks (CNN) with hyper-parameter tuning and other two pre-trained deep learning models ResNet50 and Xception with hyper-parameter tuning were applied, and analyzed the validation accuracy and validation loss. A complete design specification is shown that combines advanced facial recognition techniques with user-define function (UDF) music recommendation features. The accuracy of the model is 65% with the proposed CNN architecture, 51.75% with ResNet50, and 70% with Xception when we evaluated different models under various hyper-parameters. All the findings show that hyper-parameter tuning increases the performance of facial expression-based music recommendation systems and provides a valuable contribution to the development of more interactive and responsive user experiences.

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 B Philosophy. Psychology. Religion > Psychology > Emotions Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Music Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	25 Aug 2025 15:03
Last Modified:	25 Aug 2025 15:03
URI:	https://norma.ncirl.ie/id/eprint/8630

Actions (login required)

View Item