Browsing by Author "Dharmapriya, S"

Now showing 1 - 2 of 2

Embargo
Ai-Based Urine Microscopy Image Analysis for Predicting Urinary Tract and Renal Diseases
(Institute of Electrical and Electronics Engineers, 2026-05-29) Senanayake, K; Panagoda, P; Dharmapriya, S; Chathurya, R; Wijendra, D; De Silva, H; Jayawardana, D
The manual microscopic examination of urine is a crucial step in diagnosis of urinary tract and renal diseases. However, the process is time-consuming and operator dependent. Most of the existing automated urinalysis techniques only consider the microscopic examination of individual components or the black-box-based prediction models. There is a lack of a comprehensive framework that incorporates the microscopic examination of the microscopic components with the clinical diagnostic logic. In this regard, the present work proposes an artificial intelligence-based urinalysis system for the microscopic examination of the components in the urine sample to generate diagnostic outcomes. In the proposed system, the microscopic components like white blood cells, red blood cells, bacteria, yeast, crystals, and casts are detected and analyzed to generate the diagnostic outcomes for the diagnosis of urinary tract infection, kidney stone risk, hematuria causes, and casts-related renal diseases. In the proposed system, efficient lightweight models ensure precision and effectiveness in identifying various biological entities. White blood cells are detected with a mAP@0.5 score of 0.96, yeast with over 0.94, and crystals with more than 0.91, yielding a classification accuracy of 99.41% for crystals. The system detects microscopic elements like casts with a mAP@0.5 score of 0.80. The system also incorporates auxiliary clinical data to enhance diagnostic results for various diseases.
Open Access
A Multi -Objecti ve Opti mizati on Model to Support Freshly Cut Vegetable Processing Decisions
(Faculty of Humanities and Sciences, SLIIT, 2024-12-04) Wijesuriya, T. B; Dharmapriya, S; Kulathunga, A. K; Premarathne, P; Daundasekara, S.S
This study presents a multi -objecti ve opti mizati on approach for decision making in fresh-cut vegetable processing, opti mizing processing ti mes and costs through the selecti on of alternati ve processes at various stages of the producti on. Despite the limited att enti on given to the fresh-cut vegetable industry, parti cularly in applying multi -objecti ve opti mizati on methods to support processing decisions, this study addresses the research need. The stages of freshcut vegetable processing, including peeling, cutti ng, washing, and packing, off er multi ple alternati ve methods with varying costs and processing ti mes. The problem is formulated as an integer bi-objecti ve combinatorial opti mizati on model aimed at opti mizing total processing ti me and cost. Two algorithms, the discrete non-dominati ng sorti ng geneti c algorithm- II (NSGA II) and the discrete non- dominated sorti ng parti cle swarm algorithm (NPSO), were applied to explore their complementary algorithmic performance. The local search behaviour of NSGAII was enhanced through several innovati ve local search operators including crossover, and mutati on operators, while various positi on and velocity update operators were used in NPSO. Both primary and secondary data were uti lised in esti mati ng the process parameters of each alternati ve processing methods. The results showed that NPSO exhibited more robust convergence, while NSGA-II produced a greater number of soluti ons in the Pareto front.