Tools
Tools
Joseph Vijayan, Christy Lyona (2023) Emotion Sensitive Music Broadcasting by Analysing Facial Expressions using Machine Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (13MB) | Preview |
Preview |
PDF (Configuration manual)
Download (4MB) | Preview |
Abstract
Music has the power to be a medicine and a medium to inspire, rejuvenate and help oneself commit to a task at hand. To enjoy a seamless musical experience has been in focus from the invention of the Microphone itself. However, it is still a struggle in this Modern age of Technology. Hence, using the Top Edge technologies available to us at our fingertips to better the experience and facilitate a new way of enhancing this feeling with complex Recurrent Neural Networks and Machine Learning does seem to be a requirement than a privilege.
Using a complex CNN network and training the model using a modified VGG16 and training was carried out on over 10 thousand images and after 75 epochs and 13 hours an acceptable accuracy of 67% was achieved. With the introduction to Multithreading live image detection and detection of most dominant emotions were achieved and this information was then fed in a simple Machine Learning Model namely Gausian Naive Based to predict and recommend the top 10 songs for the two strongest feelings displayed by the user. For the last piece in this project I have used the opensource SoundCloud where the songs are fed in via api calls to SoundCloud via the webdrivers.
Finally with over 67% accuracy in Facial Recognition using a modified version of VGG16andover 78% of accuracy in recommending the songs according to the users two dominant emotions and feeding these songs into the SounCloud and playing them I have created a complete Music Player that plays songs based on the users emotion and tries to elevate it to the best possible condition over time.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Hafeez, Taimur UNSPECIFIED |
| Subjects: | M Music and Books on Music > M Music 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 |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 22 Nov 2024 13:44 |
| Last Modified: | 22 Nov 2024 13:44 |
| URI: | https://norma.ncirl.ie/id/eprint/7194 |
Actions (login required)
 |
View Item |