Browsing by Author "Fernando, A."

Now showing 1 - 2 of 2

Embargo
Automated Diabetic Retinopathy Screening With Montage Fundus Images
(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Kumari, S.; Padmakumara, N.; Palangoda, W.; Balagalla, C.; Samarasingha, P.; Fernando, A.; Pemadasa, N.
Diabetic retinopathy (DR), also known as diabetic eye disease is one of the major causes of blindness in the active population. The longer a person has diabetes, higher the chances of developing DR. This research paper is an attempt towards finding an automatic way to staging DR using montage eye images through artificial intelligence (AI). Convolutional neural networks (CNNs) play a big role in DR detection. Using transfer learning and hyper-parameter tuning DR staging is analyzed through different models. VGG16 gave the highest classification accuracies for the stages Proliferative DR (PDR) & Non-proliferative DR (NPDR). The highest level of NPDR is severe DR which achieved 94.9% classification accuracy (CA) & special features like cotton wool & laser treatment performed at 83.3% CA for each. Moreover, by using patient's history data such as age, right eye & left eye value accuracies & diabetic diagnosed year, system can predict the DR stages. That predictive model has achieved the best CA of 94 % by using Xgboost classifier. Overall, a fully functional app has been developed to detect DR stages with Montage Fundus images using AI.
Open Access
Stormwater runoff quality in Malabe, Sri Lanka
(2018-02-28) Rathnayake, U. S; Fernando, A.
Stormwater runoff is the primary nonpoint source that pollutes all water resources. Stormwaterpollution at a sewage outfall is a mixture of different kinds and strengths of pollutants from different surfaces. It is essential to understand typical pollutants from each of several impervious surfaces of a specific suburbanized area in order to properly analyze and design water quality improvement systems. Two types of impervious surfaces, roads and pavement, of two catchments in northern and southern Malabe, a western suburb of Colombo, were studied to determine the physicochemical characteristics of their stormwater runoff pollutants. For each surface type from each catchment, the first flush was sampled using a sheetflow technique. Five pollution paramters, i.e., pH, turbidity, colour, electrical conductivity (EC), and nitrate content, were analyzed and compared with that of the rain water. The pavement surfaces showed higher values of turbidity, colour, and nitrate, while EC was higher for road surfaces. The turbidity and colour values were higher in the northern catchment than that in the southern one while EC values were opposite. The nitrate concentration values of pavements were consistently higher than that of the roads for both catchments, which were not much higher than that of rain water. The pH value was consistently neutral for both surface types while rain water was slightly acidic.