SAMoSA: Sensing Activities with Motion and Subsampled Audio

Abstract

Despite in and human activity recognition systems, a practical, power-efficient, and privacy-sensitive activity recognition system has remained elusive. State-of-the-art activity recognition systems often require power-hungry and privacy-invasive audio data. This is especially challenging for resource-constrained wearables, such as smartwatches. To counter the need audio-based activity system, we make use of compute-optimized IMUs sampled 50 Hz to act for detecting activity events. detected, multimodal deep augments the data captured on a smartwatch. subsample this 1 spoken unintelligible, power consumption on mobile devices. multimodal deep recognition of 92 2% 26 activities