Research Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194
This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.
Browse
2 results
Search Results
Publication Open Access Diabetic Retinopathy Screening Using Image Processing(Faculty of Engineering, 2025-09-09) Wijesekara, W.M.M.P.; Karunarathna,A.E.S.H.; Haluwana,H.M.R.M.K.; Jayawardhana,S.M.M.SDiabetic retinopathy, a grave consequence of diabetes mellitus, has emerged as the leading cause of visual impairment worldwide. This ocular condition arises from the deterioration of blood vessels situated behind the retina and progresses insidiously, ultimately leading to blindness. Early detection is paramount in mitigating vision loss among afflicted individuals. In this study, we propose three distinct approaches Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Residual Networks (ResNets) for the accurate detection of diabetic retinopathy. Our aim is to determine the most effective model for this purpose, thereby improving screening efficiency. Utilizing a pre-processed dataset sourced from Kaggle, we conducted comprehensive experiments to evaluate the performance of each model. This curated dataset was instrumental in optimizing the classification algorithms. Our findings reveal notable disparities in the performance of these models. Through meticulous testing and validation, we sought to identify the model exhibiting the highest accuracy in diabetic retinopathy detection. Leveraging a dataset comprising 2750 retinal images, our experiments yielded accuracy values of 68% for SVM, 74% for CNN, and 63% for ResNet.Publication Embargo SmartCare: Detecting Heart Failure and Diabetes Using Smartwatch(IEEE, 2022-09-08) Colombage, L; Amarasiri, T; Sanjeewani, T; Senevirathne, CBusy lifestyles of people which resulted in an increase in non-communicable diseases have demanded a revolution in the healthcare system. This has prompted active research in developing smart sensing devices to automatically monitor the health status of a user with less human intervention. This could be more challenging when the disease is asymptomatic, hence smart solutions for early detection of such diseases are vital to help people to maintain a healthy and long life. In this study, we focus on the most common non-communicable diseases, Heart Failure, and Diabetes which are asymptomatic in their early stages. We propose a SmartCare solution for the real-time detection of heart failure and diabetes disease using a smartwatch. Data collected through a smartwatch along with health data provided by the user are used to detect heart failure, severity levels of the heart failure, diabetes disease, and types of diabetes. Random Forest and Logistic Regression algorithms are used to develop the four prediction models. Extensive evaluations performed on patients' data collected from local hospitals show our SmartCare system can detect the heart failure, severity levels of the heart failure, diabetes disease, and types of diabetes with an F1 score of 0.72, 0.7, 0.72, and 0.86 respectively.