P
Pradeepa Samarasinghe
Researcher at Sri Lanka Institute of Information Technology
Publications - 42
Citations - 148
Pradeepa Samarasinghe is an academic researcher from Sri Lanka Institute of Information Technology. The author has contributed to research in topics: Computer science & Image restoration. The author has an hindex of 6, co-authored 22 publications receiving 61 citations. Previous affiliations of Pradeepa Samarasinghe include Australian National University.
Papers
More filters
Proceedings ArticleDOI
Pubudu: Deep Learning Based Screening And Intervention of Dyslexia, Dysgraphia And Dyscalculia
Ruchira Kariyawasam,Madhuka Nadeeshani,Tuan Hamid,Inisha Subasinghe,Pradeepa Samarasinghe,Pasangi Ratnayake +5 more
TL;DR: “Pubudu” shows significant potential for screening and intervention of dyslexia, dysgraphia and dyscalculia in local languages motivating children and interactively making them able and would be an enabling app for most of the underprivileged children in Sri Lanka.
Journal ArticleDOI
A predictive model for paediatric autism screening
Benjamin Wingfield,Shane Miller,Pratheepan Yogarajah,Dermot Kerr,Bryan Gardiner,Sudarshi Seneviratne,Pradeepa Samarasinghe,Sonya Coleman +7 more
TL;DR: A culturally sensitive autism spectrum disorder screening mobile application that embeds an intelligent machine learning model and uses a clinically validated symptom checklist to monitor and detect autism Spectrum disorder in low- and middle-income countries for the first time.
Proceedings ArticleDOI
Morphology Based Automatic Disease Analysis through Evaluation of Red Blood Cells
TL;DR: This research has filled the gaps in the existing literature by developing an integrated system to Count RBC, Diagnose Elliptocytes, Microcytic, Macrocyte and Spherocytes Anemia, Detect abnormalities and Separate overlapped cells, automatically, accurately and efficiently.
Proceedings ArticleDOI
Minimum Kurtosis CMA Deconvolution for Blind Image Restoration
TL;DR: No research has been done on the effect of source correlation on adaptive blind deblurring of images through CMA, and this paper addresses that gap, coming up with a novel model of addressing the source correlation problem in the imagedeblurring through C MA.
Proceedings ArticleDOI
Automatic anemia identification through morphological image processing
TL;DR: A fully automatic low cost and accurate system to identify four common types of anemia and report on blood cell count and results indicate a good impact with the manually processed results of 99.678% accuracy of Red Blood Cell count.