Therapeutic Exercise Recognition Using a Single UWB Radar with AI-Driven Feature Fusion and ML Techniques in a Real Environment

Hussain, Shahzad and Siddiqui, Hafeez Ur Rehman and Saleem, Adil Ali and Raza, Muhammad Amjad and Alemany Iturriaga, Josep and Velarde-Sotres, Álvaro and Díez, Isabel De la Torre UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, josep.alemany@uneatlantico.es, alvaro.velarde@uneatlantico.es, UNSPECIFIED (2024) Therapeutic Exercise Recognition Using a Single UWB Radar with AI-Driven Feature Fusion and ML Techniques in a Real Environment. Sensors, 24 (17). p. 5533. ISSN 1424-8220

Text sensors-24-05533.pdf Available under License Creative Commons Attribution. Download (12MB)

Abstract

Physiotherapy plays a crucial role in the rehabilitation of damaged or defective organs due to injuries or illnesses, often requiring long-term supervision by a physiotherapist in clinical settings or at home. AI-based support systems have been developed to enhance the precision and effectiveness of physiotherapy, particularly during the COVID-19 pandemic. These systems, which include game-based or tele-rehabilitation monitoring using camera-based optical systems like Vicon and Microsoft Kinect, face challenges such as privacy concerns, occlusion, and sensitivity to environmental light. Non-optical sensor alternatives, such as Inertial Movement Units (IMUs), Wi-Fi, ultrasound sensors, and ultrawide band (UWB) radar, have emerged to address these issues. Although IMUs are portable and cost-effective, they suffer from disadvantages like drift over time, limited range, and susceptibility to magnetic interference. In this study, a single UWB radar was utilized to recognize five therapeutic exercises related to the upper limb, performed by 34 male volunteers in a real environment. A novel feature fusion approach was developed to extract distinguishing features for these exercises. Various machine learning methods were applied, with the EnsembleRRGraBoost ensemble method achieving the highest recognition accuracy of 99.45%. The performance of the EnsembleRRGraBoost model was further validated using five-fold cross-validation, maintaining its high accuracy.

Item Type:	Article
Uncontrolled Keywords:	physiotherapy; ultrawide band (UWB) radar; therapeutic exercise; machine learning; opto-electronic sensors; ensemble method
Subjects:	Subjects > Physical Education and Sport Subjects > Engineering
Divisions:	University of La Romana > Research > Scientific Production
Depositing User:	Sr Bibliotecario
Date Deposited:	16 Sep 2024 09:01
Last Modified:	16 Sep 2024 09:01
URI:	http://repositorio.funiber.org/id/eprint/14207

Actions (login required)

View Item