Generative Diffusion Model for Electrooculogram

Eye-writing, the act of drawing letters using eye movements, offers a promising avenue for human-computer interaction, especially when coupled with electrooculogram (EOG) recognition techniques. However, achieving high accuracy in eye-writing recognition using deep learning requires large datasets, which is challenging due to the time-consuming nature of data collection and privacy concerns. In this paper, we introduce a diffusion model capable of producing synthetic EOG signals, demonstrating the feasibility of generating high-quality bio-signal data. This approach not only mitigates the challenges of data collection but also facilitates the improvement of pattern recognition accuracies in small bio-signal datasets.