nanoML for Human Activity Recognition
It addresses the problem of high energy and memory demands for human activity recognition in healthcare, fitness, and IoT applications, offering a practical solution for edge and wearable devices, though it is incremental as it applies an existing method to a specific domain.
This paper tackles the challenge of deploying accurate human activity recognition models on resource-constrained devices by applying Differentiable Weightless Neural Networks (DWNs), achieving competitive accuracies of 96.34% and 96.67% with energy consumption as low as 56nJ per sample and significant reductions in energy and memory compared to state-of-the-art methods.
Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due to high energy and memory demands. This paper demonstrates the application of Differentiable Weightless Neural Networks (DWNs) to HAR, achieving competitive accuracies of 96.34% and 96.67% while consuming only 56nJ and 104nJ per sample, with an inference time of just 5ns per sample. The DWNs were implemented and evaluated on an FPGA, showcasing their practical feasibility for energy-efficient hardware deployment. DWNs achieve up to 926,000x energy savings and 260x memory reduction compared to state-of-the-art deep learning methods. These results position DWNs as a nano-machine learning nanoML model for HAR, setting a new benchmark in energy efficiency and compactness for edge and wearable devices, paving the way for ultra-efficient edge AI.