A Machine Learning-Based Classification Method for Monitoring Alzheimer’s Disease Using Electromagnetic Radar Data

Aug 4, 2026

Upload by Jiven

Alzheimer’s and Parkinson’s disease are global neurodegenerative disorders affecting over 50 million people, making early diagnosis and assessment of disease progression essential for effective treatment. Conventional diagnosis relies on mental status exams and neuroimaging, which are costly, time-consuming, and sometimes inaccurate. Electromagnetic imaging offers a non-invasive alternative, yet microwave sensing lacks resolution for subtle early-stage changes. This study proposes a machine-learning classification framework using electromagnetic radar data and realistic simulations to enable early monitoring of Alzheimer’s disease.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Background and Motivation

Challenges With Existing Imaging Modalities

Proposed Approach Overview

Related Work and Limitations

Edinburgh Research Explorer A Machine Learning-Based Classification Method for Monitoring Alzheimer’s Disease Using Electromagnetic Radar Data Citation for published version: Ullah, R, Dong, Y, Arslan, T & Chandran, S 2023, 'A Machine Learning-Based Classification Method for Monitoring Alzheimer’s Disease Using Electromagnetic Radar Data', IEEE Transactions on Microwave Theory and Techniques, pp. 1-15. [https://doi.org/10.1109/TMTT.2023.3245665](https://doi.org/10.1109/TMTT.2023.3245665) Digital Object Identifier (DOI): 10.1109/TMTT.2023.3245665 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: IEEE Transactions on Microwave Theory and Techniques General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 10. Mar. 2023 A Machine Learning-Based Classification Method for Monitoring Alzheimer’s Disease Using Electromagnetic Radar Data Rahmat Ullah, Yinhuan Dong, Graduate Student Member, IEEE, Tughrul Arslan, Senior Member, IEEE, and Siddharthan Chandran Abstract—Alzheimer’s and Parkinson’s disease are two neurodegenerative brain disorders affecting more than 50 million people globally. Early diagnosis and appropriate assessment of disease progression are critical for treatment and improving patient’s health. Currently, the diagnosis of these neurodegenerative diseases is based primarily on mental status exams and neuroimaging scans, which are costly, time-consuming, and sometimes erroneous. A novel, cost-effective, and precise diagnostic tools and techniques are thus urgently required, particularly for early detection and prediction. In the recent decade, electromagnetic imaging has evolved as a cost-effective and non-invasive alternative approach for studying brain diseases. These studies focus on wearable and portable devices and imaging algorithms. However, microwave imaging can not detect minimal changes in the brain at early stages accurately due to its lower resolution. This paper investigates machine learning techniques for the early diagnosis of acute neurological diseases, especially Alzheimer’s disease. A machine-learning-based classification method is proposed. Simulations are performed on realistic numerical brain phantoms using the CST studio suite to get the scattered signals. A novel data augmentation method is proposed to generate synthetic data required for machine learning algorithms. A deep neural network-based autoencoder extract features to train various machine learning algorithms. The classification results are compared with raw data and manual feature extraction. The study shows that the proposed machine learning-based method could be used to monitor Alzheimer’s disease at its early stages. Index Terms—Alzheimer’s disease (AD), classification, data augmentation, microwave sensing, machine learning, radar data. I. INTRODUCTION ALZHEIMER’S disease (AD) induces physiological and pathological changes in the human brain, including brain atrophy, lateral ventricle enlargement, increase in the Cerebrospinal fluid (CSF), and the accumulation of plaques and tangles. Current approaches for monitoring neurodegenerative diseases, such as magnetic resonance imaging (MRI) and This paper is an expanded paper from “Big Data-Machine Learning Processing of Recorded Radiofr

FAQs

Why is early diagnosis of Alzheimer’s disease critical?

Early-stage detection enables more effective treatment and monitoring. It also allows assessment of disease progression before pronounced symptoms emerge.

What problem does the paper address with microwave imaging?

Microwave imaging can miss minimal physiological and pathological changes in the brain at early stages due to lower spatial resolution.

How does the proposed method support Alzheimer’s monitoring?

It proposes a machine-learning-based classification pipeline using electromagnetic radar data from realistic simulations, including a data augmentation strategy and a deep neural network autoencoder for feature extraction, then compares classification results against raw and manually extracted features.

Aug 4, 2026

Upload by Jiven