Person identification using heart rate and activity from consumer-grade wearables: How do different types of cardiac diagnosis affect the accuracy of Deep Neural Networks to identify individuals by their heart rate?

Advancements in the precision and accuracy of consumer-grade wearables, such as a Fitbit, have enabled the identification and therefore authentication of individuals based on their emitted heart frequencies using these wrist-worn devices. With this type of authentication, a password is essentially sent out every second. This makes it a perfect...

An Expanded IPFM Model for Heart Rhythm Analysis: Detecting Atrial Fibrillation Using a Physiological Model

Atrial Fibrillation affects millions of people worldwide. It is associated with an impaired quality of life and an increased risk of stroke, cardiac failure and mortality. Treatments exist, but early detection and treatment is crucial, due to the progressive nature of the disease. Algorithms can help with early detection. Machine learning...

Design the Next-generation Atrial Fibrillation Diagnosis Device: An off-hospital, continuous, long-term heart monitoring product

This is a 5-month master graduation project in collaboration with Praxa Sense to design the next generation Atrial Fibrillation diagnosis device. A long-term (more than one month) continuous, off-hospital diagnosis device is designed with the focus on user experience and diagnosis accuracy. There are several phases in this project including...

Regularization of end-to-end learning for cardiac diagnosis by multitask learning with segmentation

Cardiac magnetic resonance (CMR) is used extensively in the diagnosis and management of cardiovascular disease. Deep learning methods have proven to deliver segmentation results comparable to human experts in CMR imaging, however, no successful attempts have been made at fully automated diagnosis. This has been contributed to a lack of...