Daily Physical Activity Monitoring -- Adaptive Learning from Multi-source Motion Sensor Data

TL;DR

This paper presents a transfer learning framework that uses multi-source laboratory data to improve single-source daily physical activity monitoring, enhancing accuracy and robustness in healthcare applications.

Contribution

It introduces a novel transfer learning approach with a new metric to effectively leverage multi-source data for better activity classification from single-source wearable data.

Findings

Outperforms existing methods in classification accuracy

Demonstrates robustness to noise in sensor data

Enhances daily activity monitoring for healthcare

Abstract

In healthcare applications, there is a growing need to develop machine learning models that use data from a single source, such as that from a wrist wearable device, to monitor physical activities, assess health risks, and provide immediate health recommendations or interventions. However, the limitation of using single-source data often compromises the model's accuracy, as it fails to capture the full scope of human activities. While a more comprehensive dataset can be gathered in a lab setting using multiple sensors attached to various body parts, this approach is not practical for everyday use due to the impracticality of wearing multiple sensors. To address this challenge, we introduce a transfer learning framework that optimizes machine learning models for everyday applications by leveraging multi-source data collected in a laboratory setting. We introduce a novel metric to leverage the inherent relationship between these multiple data sources, as they are all paired to capture aspects of the same physical activity. Through numerical experiments, our framework outperforms existing methods in classification accuracy and robustness to noise, offering a promising avenue for the enhancement of daily activity monitoring.