RF-Based Sensing and AI Decision Support for Stroke Patient Monitoring: A Digital Twin Approach

RF-Based Sensing and AI Decision Support for Stroke Patient Monitoring: A Digital Twin Approach

Stroke occurs when the blood flow to a certain region of the brain is disrupted. It is a leading cause of long-term disability and can result in cognitive impairments, speech difficulties, and motor dysfunction. Regular monitoring and timely intervention are critical to minimizing the damage and imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Sagheer Khan, Usman Anwar, Aftab Khan, Tughrul Arslan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Classification
digital twin
deep learning (DL)
machine learning (DL)
stroke monitoring
RF sensing
Online Access:https://ieeexplore.ieee.org/document/10978848/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stroke occurs when the blood flow to a certain region of the brain is disrupted. It is a leading cause of long-term disability and can result in cognitive impairments, speech difficulties, and motor dysfunction. Regular monitoring and timely intervention are critical to minimizing the damage and improving outcomes. This article presents a novel Radio Frequency (RF) sensing and Artificial Intelligence (AI) based Digital Twin (DT) model for effective detection of stroke. Through backscattering RF signals, the proposed Ultra Wide Band (UWB) antenna provides stroke detection. The implementation of Machine Learning (ML) and Deep Learning (DL) technologies for stroke classification provides the necessary decision support to healthcare professionals in DT stroke patient monitoring. The statistical and autonomous (AutoEncoders (AE) and Stacked AutoEncoders (SAE) with structure 32-16-32, 64-32-16-32-64, and 128-64-32-16-32-64-128) feature data is enlarged through Gaussian noise feature data augmentation. The Fine KNN algorithm provides the 93.4% and 92.3% classification accuracies of binary and multi-class classification respectively. Out of the 4 autonomous feature extraction methods, the Fine KNN algorithm with SAE structure 64-32-16-32-64 provided the highest accuracies of 88.2% and 74.8% for binary and multi-class classification.
ISSN:2169-3536

Similar Items