University of Twente Student Theses
Music Sequencing using the Traveling Salesman Problem
Smulders, Jorn (2024) Music Sequencing using the Traveling Salesman Problem.
|
PDF
2MB |
| Abstract: | The thesis titled "Music Sequencing using the Traveling Salesman Problem" by Jorn Smulders focuses on improving the user experience of Awaves Play, a music streaming application developed by Awaves BV. The app aims to serve as an AI DJ for student parties, but it struggles with user engagement, as the average streaming time per user is under 8 minutes. The research identifies that this issue is largely due to dissatisfaction with the music sequencing process, leading to problems like inconsistent genres, energy levels, and poor transitions. To address this, Smulders applies the Traveling Salesman Problem (TSP) heuristic to optimize the sequencing of songs in a playlist. By treating songs as points in a Euclidean space and transitions as distances, the model incorporates various audio features such as tempo, energy, and danceability. The research tests three solution methods: brute force, nearest neighbor, and an evolutionary algorithm, all of which show promise in improving playlist coherence. However, the author concludes that further validation and research are needed to fully realize the potential of this approach. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 24 dramaturgy, musicology, 55 traffic technology, transport technology |
| Programme: | Industrial Engineering and Management BSc (56994) |
| Link to this item: | https://purl.utwente.nl/essays/102828 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page