tinyRadar for Fitness: A Contactless Framework for Edge Computing

Healthcare technology is evolving from a conventional hub-based system to a personalized healthcare system accelerated by rapid advancements in smart fitness trackers. Modern fitness trackers are mostly lightweight wearables and can monitor the user's health round the clock, supporting ubiquitous connectivity and real-time tracking. However, prolonged skin contact with wearable trackers can cause discomfort. They are susceptible to false results and breach of privacy due to the exchange of user's personal data over the internet. We propose tinyRadar, a novel on-edge millimeter wave (mmWave) radar-based fitness tracker that solves the issues of discomfortness, and privacy risk in a small form factor, making it an ideal choice for a smart home setting. This work uses the Texas Instruments IWR1843 mmWave radar board to recognize the exercise type and measure its repetition counts, using signal processing and Convolutional Neural Network (CNN) implemented on board. The radar board is interfaced with ESP32 to transfer the results to the user's smartphone over Bluetooth Low Energy (BLE). Our dataset comprises eight exercises collected from fourteen human subjects. Data from ten subjects were used to train an 8-bit quantized CNN model. tinyRadar provides real-time repetition counts with 96% average accuracy and has an overall subject-independent classification accuracy of 97% when evaluated on the rest of the four subjects. CNN has a memory utilization of 11.36 KB, which includes only 1.46 KB for the model parameters (weights and biases) and the remaining for output activations.