M.Sc. Dissertation Proposal

Vision and Motivation

The vision of this research is to explore the potential of customizable adaptive generative music in enhancing endurance sports training like running, trail running, cycling, medium to long distance swimming, or triathlon using mobile devices. Endurance sports training often requires prolonged periods of physical exertion, and music has been shown to positively impact performance, motivation and keep the desired pace. However, existing music applications may lack adaptability to individual preferences and training needs like duration and pacing. By developing a customizable adaptive generative music system, this research aims to provide athletes with personalized music experiences tailored to their training intensity, pace, and preferences, thereby optimizing training outcomes and enhancing overall training experience.

State-of-the-Art

Previous studies have demonstrated the effectiveness of music in enhancing endurance sports training. However, existing research primarily focuses on prerecorded music playlists, which may not adequately adapt in real time to individual training needs. The proposed research builds upon recent advancements in generative music systems and mobile computing technology to develop a customizable adaptive solution. This study aims to bridge the gap between music technology and endurance sports training by developing a novel customizable adaptive generative music system. Some previous work include [2017-Hagensen],[2020-Williams] and [2020-Fazekas].

Research Methodology

This research will employ a mixed-methods approach to develop and evaluate the customizable adaptive generative music system for endurance sports training. The development phase will involve software prototyping. The system may utilize sensor data from mobile or wearable devices, such as heart rate monitors, to adapt music in real-time to the athlete’s physiological state and training context. The findings will contribute to the understanding of the effectiveness and usability of customizable real-time adaptive generative music systems for endurance sports training.

References

[2017-Hagensen] Troels Lunde Hagensen, Stefania Serafin, and Cumhur Erkut (2017): An experimental study in generative music for exercising to ease perceived exertion by use of heart beat rate as a control parameter. Student Interaction Design Research Conference (SIDeR'2016), Malmö, Sweden.

[2020-Williams] Duncan Williams, Bruno Fazenda, Victoria Williamson, and György Fazekas (2020): On performance and perceived effort in trail runners using sensor control to generate biosynchronous music. Sensors 20(16), 4528.
doi: 10.3390/s20164528

[2020-Fazekas] Duncan A.H. Williams, Bruno Fazenda, Victoria J. Williamson, and Gyorgy Fazekas (2020): Biophysiologically synchronous computer generated music improves performance and reduces perceived effort in trail runners. In Romain Michon and Franziska Schroeder (eds.), Proceedings of the International Conference on New Interfaces for Musical Expression, Birmingham, UK, July, pp.531–536.
doi: 10.5281/zenodo.4813174