On-Device Personalization for Human Activity Recognition on STM32

Human Activity Recognition (HAR) is one of the most interesting application for machine learning models running on low cost and low-power devices, such as microcontrollers (MCUs). As a matter of fact, MCUs are often dedicated to performing inference on their own acquired data, and any form of model training and update is delegated to external resources. We consider this mainstream paradigm a severe limitation, especially when privacy concerns prevent data sharing, thus model personalization, which is universally recognized as beneficial in HAR. In this work, we present our HAR solution where MCUs can directly fine-tune a deep learning model using locally acquired data. In particular, we enable training functionalities for 1-D Convolutional Neural Networks (CNN) on STM32 microcontrollers and provide a software tool to estimate the memory and computational resources required to accomplish model personalization.