Learning Shallow Detection Cascades for Wearable Sensor-Based Mobile Health Applications

TL;DR

This paper introduces a new method for real-time detection of health-related behaviors using shallow detection cascades tailored for wearable sensor data, enabling timely interventions in mobile health systems.

Contribution

It presents a novel approach to learning shallow detection cascades specifically designed for real-time wearable health monitoring systems.

Findings

Effective cigarette smoking detection from wrist and respiration data.

Implementation of two and three stage cascades for improved detection accuracy.

Potential for real-time health intervention support.

Abstract

The field of mobile health aims to leverage recent advances in wearable on-body sensing technology and smart phone computing capabilities to develop systems that can monitor health states and deliver just-in-time adaptive interventions. However, existing work has largely focused on analyzing collected data in the off-line setting. In this paper, we propose a novel approach to learning shallow detection cascades developed explicitly for use in a real-time wearable-phone or wearable-phone-cloud systems. We apply our approach to the problem of cigarette smoking detection from a combination of wrist-worn actigraphy data and respiration chest band data using two and three stage cascades.