Energy-efficient activity recognition via multiple time-scale analysis
Namita Lokare, Shamim Samadi, Boxuan Zhong, Laura Gonzalez, Farrokh Mohammadzadeh, Edgar J. Lobaton · 2017
In this work, we propose a novel power-efficient strategy for supervised human activity recognition using a multiple time-scale approach, which takes into account various window sizes. We assess the proposed methodology on our new multimodal dataset for activities of daily life (ADL), which combines the use of physiological and inertial sensors from multiple wearable devices. We aim to develop techniques that can run efficiently in wearable devices for real-time activity recognition. Our analysis shows that the proposed approach Sequential Maximum-Likelihood (SML) achieves high F1 score across all activities while providing lower power consumption than the standard Maximum-Likelihood (ML) approach.