WiFi-Based Detection of Human Subtle Motion for Health Applications

Area of Science:

• Biomedical Engineering
• Health Informatics
• Signal Processing

Background:

• Neurodegenerative diseases, such as Parkinson's disease, manifest motor symptoms that can be subtle and fluctuate daily.
• Current clinical assessments may not fully capture the extent of motor impairments, hindering precise diagnosis and personalized treatment.
• Home-based health monitoring offers a promising avenue for continuous, quantitative data collection.

Purpose of the Study:

• To develop and evaluate a WiFi-based sensing approach for detecting and quantifying human micromotions.
• To assess the feasibility of using regular WiFi signals for contactless, privacy-preserving health monitoring in a home environment.
• To investigate the accuracy of the proposed method in capturing simulated tremors and other fine motor movements.

Main Methods:

• Utilized WiFi Channel State Information (CSI) to detect human micromotions.
• Implemented a computer algorithm to analyze CSI data for motion quantification.
• Tested the system's efficacy in a standard room environment (4.2 m × 7.9 m) using single and multiple WiFi links.
• Simulated hand tremors and other micromovements to evaluate system performance.

Main Results:

• Successfully captured micromotions across various locations within the experimental environment.
• Achieved high accuracy in computing the frequency and duration of simulated hand tremors.
• Demonstrated average accuracies of 90.9% with a single WiFi link and 95.7% with multiple WiFi links.

Conclusions:

• WiFi-based sensing is a viable, contactless method for detecting human micromotions in a home setting.
• The proposed approach enables quantitative assessment of motor symptoms, supporting early diagnosis and personalized treatment for neurodegenerative diseases.
• This technology has the potential to significantly enhance remote patient monitoring and healthcare delivery.