<?xml version="1.0" encoding="UTF-8"?>

<article xmlns="https://www.ijrdes.com/schema/article"
         version="1.0"
         language="en">

    <journal>
        <name>International Journal of Research and Development in Engineering Sciences</name>
        <website>https://www.ijrdes.com</website>
    </journal>

    <metadata>
        <title>Neurodegenerative Disorder Detection using CNN</title>

        <authors>
			<author><name>D. Dileep Kumar</name>     </author>
        </authors>

        <volume>6</volume>
        <issue>2 (March - April)</issue>

        <publication>
            <year>2024</year>
			<month>04</month>
			
			<period>March-April</period>
        </publication>

		<language>en</language><keywords><keyword>Parkinson's Disease</keyword><keyword>Neurological Disorder</keyword><keyword>Remote diagnosis</keyword><keyword>ML</keyword><keyword>Exception Architecture.</keyword></keywords> 
    </metadata>

    <abstract>A neurological condition that affects millions of people is Parkinsons disease globally The effects of Parkinsons disease PD sixty percent of persons over fifty It is challenging for people Having Parkinsons illness in order to get to treatment and monitoring appointments since they have difficulty speaking and moving It is feasible for Parkinsons disease PD sufferers to have normal lives with treatment The necessity for precise early and remote PD identification is highlighted by the aging global population The early identification and detection of Parkinsons disease has shown great promise in recent years thanks to machine learning methods We describe a novel approach for the diagnosis of Parkinsons illness in this work using exception architecture and machine learning approaches Specifically we focus on the Parkinsons disease diagnosis illness </abstract>

    <copyright>
        <statement>
            Copyright (c) 2026 International Journal of Research and Development in Engineering Sciences. All rights reserved.
        </statement>
        
            <year>2024</year>
        <license>All Rights Reserved</license>
    </copyright>

</article>
