Online Human Activity Recognition using Low-Power Wearable Devices

TL;DR

This paper introduces a novel online human activity recognition framework utilizing low-power wearable sensors and neural networks, achieving high accuracy with minimal energy consumption on IoT devices.

Contribution

It presents the first framework capable of online training and inference for HAR using textile sensors and accelerometers, optimized for low-power IoT devices.

Findings

97.7% activity recognition accuracy

Less than 12.5 mW power consumption

Effective online training with policy gradient

Abstract

Human activity recognition~(HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer. Using these features, we design an artificial neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.