Human activity recognition using magnetic induction-based motion signals and deep recurrent neural networks

Designing reliable, scalable and energy efficient sensor-based activity recognition system remains a challenge. Here, the authors demonstrate low power wearable wireless network system based on magnetic induction which is integrated with deep recurrent neural networks for human activity recognition.

Bibliographic Details
Main Authors: Negar Golestani, Mahta Moghaddam
Format: Article
Language:English
Published: Nature Publishing Group 2020-03-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-020-15086-2