Download

Download Full Text (165 KB)

Faculty Advisor(s)

Kurt Jackson PT, PhD

Description

Purpose/hypothesis: The ability to monitor human activity remotely may be useful in providing telerehabilitation and measuring real-world rehabilitation outcomes. Current methods of activity monitoring have significant limitations (cost, privacy, ease of use) that can limit their benefit and widespread use. Recent advances in machine learning (ML) and millimeter wave radar (MWR) have allowed for the development of a cost effective and simple way to monitor human movement continuously and remotely while maintaining reasonable privacy. The purpose of this study was to test the ability of ML and MWR to accurately classify and monitor different types of human activity including falls.

Number of Subjects: 89 healthy adults (mean age = 24 ± 7.4, range = 21-53)

Materials and Methods: A Texas Instruments IWR6843ISK-ODS MMW radar and NVIDIA Jetson nano-board (GPU) was used to collect and process radar data. Subjects spent one minute in each of the following positions, sitting, standing, lying, walking and falling within a 5 x 5-meter area. A machine learning model was applied to the training data. Receiver Operating Characteristic (ROC) analysis was then used to determine accuracy of the activity classification model.

Results: Based on the ROC analysis, the area under the curve (AUC) for each activity were as follows. Standing = 0.83, Walking = 0.96, Sitting = 0.93, Lying = 0.90, Falling = 0.88.

Conclusions: AUC values ranging from 0.83 – 0.96 demonstrated good to excellent ability of the millimeter wave radar and machine learning model to classify different functional activities in a home environment. Additionally, it has the capability to track the activities of multiple individuals in a space simultaneously and create a heat map to show the location where different activities occur most frequently.

Clinical Relevance: An inexpensive radar system could be used in both home and institutional settings to accurately monitor activity levels and detect falls over extended periods of time and provide useful information to healthcare providers.

Publication Date

5-2024

Disciplines

Physical Therapy | Rehabilitation and Therapy

An Artificial Intelligent Millimeter Wave Radar System for Human Activity Recognition and Monitoring

Share

COinS