Browsing by Author "Hathurusinghe, S"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemEmbargo
    Evaluating Genetic, Reinforcement Learning, and Colony Optimization Algorithms for Scalable University Timetable Scheduling
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Weerasinghe K.D.E.I.; Wijayawardhana G.L.C.N.D.; Udayantha D.M.S.; De Silva K.H.P.N.; Perera, J; Hathurusinghe, S
    University timetable scheduling, a complex optimization task, often lacks comparative algorithmic analysis under standardized, resource-scarce conditions. This research introduces an integrated framework to benchmark Genetic Algorithms (GA), Reinforcement Learning (RL), and Colony Optimization (CO) under identical, extreme resource scarcity (4 rooms for 195 activities), a key differentiator. Using standardized metrics, results revealed distinct trade-offs: GAs offer rapid initial solutions but lack flexibility; RL shows efficient resource use but requires extensive training; CO demonstrates adaptability. All algorithms struggled to assign every activity due to imposed resource limits, highlighting performance under severe contention. The developed platform, with configurable scoring and role-based access, is a practical contribution, offering data-driven insights for algorithm selection. This study offers systematic three-way comparison of these techniques under uniform, high-pressure criteria, informing future hybrid solutions.
  • Thumbnail Image
    ItemEmbargo
    MaizeGenie - Mobile Platform for Sustainable and Profitable Corn Cultivation
    (Institute of Electrical and Electronics Engineers Inc., 2026-03-26) Suraweera A.G.S.S.; Pasindu J.D; Rathnayaka R.M.T.P.B; Perera P.D.P.N; Samarakoon, U; Hathurusinghe, S
    Maize is an important crop in Sri Lanka, but many farmers still face low yields and income losses due to pest and leaf disease attacks, uncertain weather, and market price changes. Farmers also have limited access to real-time, easy-to-understand decision support in Sinhala, especially in areas with weak internet coverage. This research proposes MaizeGenie, an AI-powered mobile advisory platform that supports sustainable and profitable corn cultivation. The system combines computer vision and machine learning to deliver four main services: (1) pest identification and control guidance using object detection and image classification, (2) leaf disease identification with severity-based advice, (3) yield prediction with prediction-based site-specific real time fertilizer advisory system, and (4) price forecasting and cultivation timing decision support using time-series forecasting. The application is designed for farmerfriendly use, provides Sinhala/English guidance with voice/text output, and supports operation where possible. Overall, the proposed solution aims to reduce trial-and-error farming, improve timely actions against pests and diseases, and help farmers plan inputs and selling decisions with more confidence.
  • Thumbnail Image
    ItemOpen Access
    Transforming Education And Therapy For Children On The Autism Spectrum with Machine Learning Solutions
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Jayawickrama Y.R.C.S; Kumarasiri O.A.K.U; Kurera W.N.K; De Silva J.H.J.A; Thelijjagoda, S; Hathurusinghe, S
    Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects cognitive, social, behavioral, and sensory development. Early diagnosis and intervention are crucial but remain challenging due to cultural, environmental, and diagnostic limitations, particularly in Sri Lanka. This research proposes a machine learning-driven web-based system to assess and support children with ASD across four critical domains: behavioral observation, cognitive skills, social skills, and sensory processing. By integrating technologies such as deep learning, computer vision, and natural language processing, the system utilizes eye-tracking, facial expression analysis, and real-time video monitoring to identify developmental challenges. Additionally, culturally adaptive parental questionnaires and interactive learning activities enhance the accuracy of ASD assessments and provide personalized intervention recommendations. The proposed approach bridges gaps in early ASD detection by offering a scalable, accessible, and contextually relevant solution for Sri Lanka. Experimental results show high accuracy in behavioral (90%), cognitive (92%), social (92%), and sensory (94%) models. This scalable, accessible solution bridges gaps in early ASD detection, offering a culturally relevant tool for families and healthcare providers in Sri Lanka. The system empowers caregivers with real-time insights and tailored interventions, improving the quality of life for children with ASD and their families, and advancing inclusive support systems globally.