Quantum machine learning models for biomedical time-series: applications to ECG signal processing

The convergence of quantum computing and biomedical signal processing offers a promising frontier for innovation. Biomedical time-series, such as ECG data, are complex, high-dimensional, and often nonlinear, presenting an ideal challenge for exploring the representational power of quantum models. By combining quantum feature maps, variational quantum circuits, and classical neural networks, students will investigate whether quantum models can achieve better generalization, parameter efficiency, or robustness under noise compared to conventional deep learning approaches. The project aims to investigate the viability of application of quantum machine learning techniques in wearable medical devices.