مشروع البحث:
DEVELOPMENT OF NEURAL NETWORK ALGORITHMS FOR AUTOMATION OF EARLY DIAGNOSIS OF EYES DISEASES

dc.contributor.advisorProf. Dr. Nenad Kopar
dc.date.accessioned2025-08-26T07:00:29Z
dc.date.available2025-08-26T07:00:29Z
dc.descriptionIn this work, we implement and build Eye Diseases Expert System based on convolutional neural network to detects and diagnoses of eye diseases. Two models have been implemented to create Expert System. The first model called GMD model based on multi-label classification and Grad-Cam techniques. The second model is GMDS model also based on multi-label classification and segmentation techniques (U-Net). In addition, we applied additional techniques to improve the accuracy, avoid overfitting, overconfidence, and speed up the training models.
dc.description.abstractEyes diseases include Glaucoma, Myopia and Diabetic retinopathy are very serious health problems in the life of people. Timely, early diagnosis of these diseases is very important to avoid blindness. There are many methods have been developed for this purpose. Deep learning is the most technology in 21century and it gives more information about how computers can understand data and learning from. In deep learning, networks of artificial neurons analyse large dataset to automatically discover patterns.
dc.identifier681
dc.identifier.urihttps://dspace.academy.edu.ly/handle/123456789/1728
dc.subjectEYES DISEASES
dc.titleDEVELOPMENT OF NEURAL NETWORK ALGORITHMS FOR AUTOMATION OF EARLY DIAGNOSIS OF EYES DISEASES
dspace.entity.typeProject
project.endDate2024
project.funder.nameعلوم الحاسوب
project.investigatorمحمود محمد صميدة
project.startDate2023
relation.isOrgUnitOfProject784d19bf-029a-47b8-b883-c9daefb34588
relation.isOrgUnitOfProject.latestForDiscovery784d19bf-029a-47b8-b883-c9daefb34588
الملفات
الحزمة الأصلية
يظهر اﻵن 1 - 1 من 1
لا توجد صورة مصغرة متاحة
اﻻسم:
CompleteThesisMahmoudSmaida.pdf
الحجم:
2.96 MB
التنسيق:
Adobe Portable Document Format
حزمة الترخيص
يظهر اﻵن 1 - 1 من 1
لا توجد صورة مصغرة متاحة
اﻻسم:
license.txt
الحجم:
1.71 KB
التنسيق:
Item-specific license agreed to upon submission
الوصف: