Activity Monitoring with a Wrist-Worn, Accelerometer-Based Device.

Area of Science:

• Biomedical Engineering
• Wearable Technology
• Activity Monitoring

Background:

• Continuous monitoring of physical activity (PA) and daily living activities (ADL) is crucial for health assessment.
• Existing methods often lack quantitative metrics for activity intensity and regularity.
• Wearable MEMS accelerometer-based devices offer a promising solution for unobtrusive, long-term health monitoring.

Purpose of the Study:

• To develop and validate simple assessment models for quantifying physical activity (PA) levels using wrist-worn accelerometer data.
• To create an algorithm for accurate sleep duration detection.
• To quantitatively assess the regularity of activity of daily living (ADL) and introduce novel metrics.

Main Methods:

• Utilized data from a MEMS accelerometer-based, wrist-worn device worn continuously (24h/day).
• Developed an activity index (AI) to categorize PA into 5 levels: rest/sleep, sedentary, light, moderate, and vigorous.
• Introduced a regularity index (RI) to quantitatively measure ADL regularity.

Main Results:

• The proposed models effectively quantify PA levels and sleep duration from continuous accelerometer data.
• The activity index (AI) successfully categorizes different PA intensities.
• The regularity index (RI) provides a quantitative measure of ADL patterns.

Conclusions:

• Simple, accelerometer-based wrist-worn devices can provide valuable quantitative data on PA, sleep, and ADL regularity.
• The developed AI and RI parameters offer practical tools for health monitoring and medical-care applications.
• These models are suitable for integration with cloud computing services for scalable health solutions.