Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition

arXiv:2604.10458v1 Announce Type: cross Abstract: Wearable IMU-based Human Activity Recognition (HAR) relies heavily on Deep Neural Networks (DNNs), which are burdened by immense computational and buffering demands. Their power-hungry floating-point operations and rigid requirement to process complete temporal windows severely cripple battery-constrained edge devices. While Spiking Neural Networks (SNNs) offer extreme event-driven energy efficiency, standard architectures struggle with complex b