MicroNAS: An Automated Framework for Developing a Fall Detection System

This work presents MicroNAS, an automated neural architecture search tool specifically designed to create models optimized for microcontrollers with small memory resources. The ESP32 microcontroller, with 320 KB of memory, is used as the target platform. The artificial intelligence contribution lies in a novel method for optimizing convolutional neural network and gated recurrent unit architectures by considering the memory size of the target microcontroller as a guide. A comparison is made between memory-driven model optimization and traditional two-stage methods, which use pruning, to show the e ffectiveness of the proposed framework. To demonstrate the engineering application of MicroNAS, a fall detection system (FDS) for lower-limb amputees is developed as a pilot study. A critical challenge in fall detection studies, class imbalance in the dataset, is addressed. The results show that MicroNAS models achieved higher F1-scores than alternative approaches, such as ensemble methods and H2O Automated Machine Learning, presenting a significant step forward in real-time FDS development. Biomechanists using body-worn sensors for activity detection can adopt the open-source code to design machine learning models tailored for microcontroller platforms with limited memory. Keywords: automated machine learning, tiny machine learning, neural architecture search, pruning, class imbalance, fall detection, lower limb amputee, Inertial Measurement Unit (IMU)1. Introduction Falls present a major health risk for individuals with lower limb amputation [1, 2]. Specifically, more than half of lower limb amputees report falling in the previous 12 months. Furthermore, of those reporting a fall, approximately 75% report multiple falls [1]. Falls have the potential for multiple negative sequelae, including fractures, traumatic brain injuries, lacerations, sprains, hematomas, and even death [3]. More commonly, a fall may only result in minor injuries or bruises but can impact the person's confidence in their balance and mobility [3]. Consequently, they may limit their physical activity and social participation, leading to a decline in overall physical and emotional health. Falls also pose a barrier to successful rehabilitation, whether it be physical or emotional injury. The extent to which falls delay or prevent successful rehabilitation of individuals with lower limb amputations is unknown.