[email protected]
Author
Contributions by role
Author 1
ORCID
0000-0003-4948-8513
Neeraj Kumar Pandey
Graphic Era Deemed to be University Dehradun
Summary
Dr. Neeraj Kumar Pandey currently serves as an Associate Professor in the Department of Computer Science & Engineering at Graphic Era (Deemed to be) University, Dehradun. He is an accomplished academician with over 15 years of diverse experience in both academia and industry. His research interests include Cloud Computing, Computer Vision, and Deep Learning, with a focus on innovative solutions and applications in these domains. Dr. Pandey has authored over 80 research papers in prestigious international journals and conferences and holds seven patents in the field. He is an Editor for Frontiers in Medicine-Pathology and Journal of Intelligent Systems and Applied Data Science, contributing to the advancement of knowledge in these areas. Dr. Pandey has also played an active role in organizing several high-profile conferences, including those hosted by IEEE, Elsevier and Springer. He is a member of IEEE, CSTA, ERDA and IAENG.
Edited Journals
IECE Contributions
Articles
1
Edited
0
Open Access | Research Article | 03 June 2025
Diabetic Retinopathy Detection and Analysis with Convolutional Neural Networks and Vision Transformer
by
Yogesh Tewari
,
Nitin Singh Parihar
,
Karan Rautela
,
Nishant Kaundal
,
Manoj Diwakar
,
Neeraj Kumar Pandey
Biomedical Informatics and Smart Healthcare | Volume 1, Issue 1: 18-26, 2025 | DOI: 10.62762/BISH.2025.724307
Abstract
Diabetic Retinopathy occurs when elevated blood sugar levels damage retinal blood vessels, potentially leading to vision impairment. In this paper, we have tested the performance of CNN, ViT and their hybrid models. The dataset used is publicly available on Kaggle and the dataset contained around 35,000 retinal images which were divided into 5 classes namely No DR, Mild DR, Moderate DR, Severe DR and Proliferative DR. In CNN we tested 4 different architectures in which we achieved the best accuracy of 75.4% with Resnet50 architecture and with ViT model we achieved an accuracy of 83.9% and from the hybrid model we achieved an accuracy of 88.4% from the Resnet50 + ViT. The results shown by the... More >
Graphical Abstract
Diabetic Retinopathy Detection and Analysis with Convolutional Neural Networks and Vision Transformer