Human Activity Recognition on wrist-worn accelerometers using self-supervised neural networks

TL;DR

This paper introduces a self-supervised learning approach for wrist-worn accelerometer data to improve human activity recognition, enabling accurate, device- and subject-independent monitoring with minimal labeled data.

Contribution

It presents a novel self-supervised learning paradigm and segmentation algorithm that enhance HAR accuracy and generalization across diverse real-life datasets.

Findings

Achieves high HAR accuracy with few labels

Effectively separates daily activities in benchmark datasets

Improves continuous activity recognition in real-life data

Abstract

Measures of Activity of Daily Living (ADL) are an important indicator of overall health but difficult to measure in-clinic. Automated and accurate human activity recognition (HAR) using wrist-worn accelerometers enables practical and cost efficient remote monitoring of ADL. Key obstacles in developing high quality HAR is the lack of large labeled datasets and the performance loss when applying models trained on small curated datasets to the continuous stream of heterogeneous data in real-life. In this work we design a self-supervised learning paradigm to create a robust representation of accelerometer data that can generalize across devices and subjects. We demonstrate that this representation can separate activities of daily living and achieve strong HAR accuracy (on multiple benchmark datasets) using very few labels. We also propose a segmentation algorithm which can identify segments of salient activity and boost HAR accuracy on continuous real-life data.