mmFiT: Contactless Fitness Tracker Using mmWave Radar and Edge Computing Enabled Deep Learning

Internet of things (IoT) is transforming the way we imagine healthcare with ubiquitous connectivity, faster response and deeper personalized insights using large amounts of data. Fitness trackers provide useful insights to maintain balance of a healthy lifestyle. Nowadays, fitness trackers are available as wearable devices which creates a sense of unease in exercise and may cause skin irritation. In this paper, we present mmFiT, an edge computing enabled, contactless, real-time fitness tracker using a single mmwave radar point cloud data. It has the inherent advantage of user privacy preservation while tracking indoor fitness activities. Experimental results show that the system can classify various exercises with real-time accuracy of 95.53\% and is also capable of counting repetitions of exercises. This implementation is computationally inexpensive, and therefore, the system can be deployed in an IoT connected edge device for real-time operations. This system will be an ideal fit in a smart home or smart gymnasium setting.