PARKINSON’S DISEASE DETECTION FROM HANDWRITTEN SKETCHES USING DENSELY CONNECTED CONVOLUTIONAL NETWORKS
S.Sethu Subramaniyan
, S.Sivanesan , G.Raakes
parkinson’s disease, detection, diagnosis, dataset, model, accuracy
Parkinson's disease (PD) is a neurological condition that worsens over time and impairs motor skills, causing tremors, rigidity, and poor coordination. Early diagnosis of PD is essential for successful therapy, but existing diagnostic techniques can be time-consuming, expensive, and insufficiently accurate. When dealing with illnesses like Parkinson's, this cannot be allowed. Therefore, we offer a novel method for PD identification in this research that makes use of handwritten sketches and a densely connected convolutional network (DenseNet). Our method takes advantage of the distinctive qualities of handwritten sketches, such as the direction and curvature of the strokes, to spot PD symptoms before they become severe. We trained a DenseNet to distinguish between sketches made by people with and without PD using a dataset of sketches created by both groups of people. On our test set, we outperformed other state-of-the- art methods with an accuracy of over 97%. Our findings show that employing handwritten sketches as a low-cost, non- invasive strategy for PD identification has promise. Our method could be used to increase the usability and effectiveness of PD diagnosis in a variety of contexts, such as telemedicine and remote patient monitoring.
"PARKINSON’S DISEASE DETECTION FROM HANDWRITTEN SKETCHES USING DENSELY CONNECTED CONVOLUTIONAL NETWORKS", TIJER - TIJER - INTERNATIONAL RESEARCH JOURNAL (www.TIJER.org), ISSN:2349-9249, Vol.11, Issue 2, page no.763-767, February-2024, Available :https://tijer.org/TIJER/papers/TIJERB001121.pdf
Volume 11
Issue 2,
February-2024
Pages : 763-767
Paper Reg. ID: TIJER_151069
Published Paper Id: TIJERB001121
Downloads: 000290
Research Area: Science and Technology
Country: TIRUVALLUR, TAMILNADU, India
ISSN: 2349-9249 | IMPACT FACTOR: 8.57 Calculated By Google Scholar | ESTD YEAR: 2014
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: TIJER (IJ Publication) Janvi Wave
