Other Conference and Symposium Proceedings

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4774

Browse

Filters

20254

Advanced Search

Filter by

Settings

Author: search.filters.author.Wijesiri, PHas files: Yes

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    ItemEmbargo
    IntelliCross: Adaptive Pedestrian Crossing System
    (Institute of Electrical and Electronics Engineers Inc., 2025) Dissanayake, U; Weerasekara, D; Sumanasekara, H; Ishara, D; Wijesiri, P; Moonamaldeniya, M
    Urban traffic management at pedestrian crossings presents considerable issues, such as pedestrian safety, congestion, and effective prioritizing of emergency vehicles. Traditional traffic signal systems are frequently static, unable to respond to real-time changes in pedestrian flow, vehicle density, and environmental variables. To overcome these issues, an IoT-based adaptive pedestrian crossing system, "IntelliCross,"is presented. The system detects emergency vehicle sirens using sound sensors and automatically adjusts pedestrian signals to green to prioritize emergency vehicle passage, resulting in faster response times and shorter delays. Furthermore, machine learning algorithms alter signal timings based on real-time pedestrian counts and vehicle density, assuring smooth traffic flow and pedestrian safety. Vulnerable pedestrians, such as the elderly and disabled, are accommodated by dynamically extending green light durations to ensure safe crossing. The technology also includes real-time meteorological data, such as rain, to extend green light durations and improve pedestrian safety. IntelliCross, by combining IoT sensors with machine learning, offers a scalable and cost-effective solution for improving urban traffic management, closing crucial gaps in present systems, and contributing to the development of smart cities. Public surveys demonstrate considerable support for systems that prioritize emergency vehicles while also assuring pedestrian safety, proving the system's ability to revolutionize urban traffic infrastructure.
  • Thumbnail Image
    ItemEmbargo
    An Explainable Deep Learning Framework for Coconut Disease Detection Using MobileNetV2, Super-Resolution, and Grad-CAM++
    (Institute of Electrical and Electronics Engineers Inc., 2025) Balasooriya R.C.; Adithya E.L.A.Y; Gunarathne M.M.S.U; Silva T.C.D; Lokuliyana, S; Wijesiri, P
    Coconut production is a significant industry in Sri Lanka's economy and food security. However, it is constantly under threat from diseases such as Grey Leaf Spot and pests such as Coconut Mites (Aceria guerreronis). Detection must be early, but it is difficult, especially in field conditions where image quality is low and symptoms are not visually distinguishable. This paper proposes a two-stage deep learning solution to enhance and automate disease and pest recognition with a lightweight and mobile system. The system combines Real-ESRGAN based image super-resolution to restore visual detail in poor-quality mobile images and MobileNetV2-based classification, a lightweight convolutional neural network. The model recognizes grey leaf spot with over 97% accuracy and greatly enhanced mite recognition performance when combined with super-resolution preprocessing. In the interest of transparency and trust for users, the Grad-CAM++ and LIME interpretation techniques are utilized, and visual explanations of the predictions are presented. A mobile application was created with React Native and integrated with a Flask-based backend to enable real-time image enhancement and classification to facilitate practical deployment. Smartphone-captured field-level photos were preprocessed and categorized into healthy, diseased, and non-coconut samples. Farmers can use the proposed system in real time because it maintains good accuracy while being computationally efficient. This framework provides a scalable method for intelligent and sustainable agriculture.
  • Thumbnail Image
    ItemEmbargo
    Developing Predictive Models for Future Stress Likelihood and Recovery Time Using Behavioral and Emotional Data
    (Institute of Electrical and Electronics Engineers Inc., 2025) Weerasinghe W.P.D.J.N; Gunasekera H.D.P.M; Wickramasinghe B.G.W.M.C.R; Jayathunge K.A.D.T.R; Wijesiri, P; Dassanayake, T
    Stress has a serious impact on mental and physical well-being, but treatments as usual are often unavailable and not effective over the long term. The AyurAura application combines imaginative Ayurvedic therapies with modern AI techniques to deliver customized stress reduction by way of Mandala art and music. This research develops two predictive models for the application. In its first model, the stress prediction probability is estimated from users' behavior in a questionnaire and the result can be used to proactively intervene. The second model forecasts time needed for recovery into a stress-free state by using the changes in daily emotional state and participation in app activities. Machine learning algorithms are used to prepare behavioral and emotional data for improved prediction performance. Trained on multi-institution datasets, both models delivered 90-95% accuracy, enabling the user to detect behavior eliciting stress and the degree needed for recovery. These results highlight the possibility of combining conventional therapeutics with contemporary tech for ongoing, affordable stress relief interventions with personalized needs in mind.
  • Thumbnail Image
    ItemOpen Access
    Model Optimization for Personalized Health Metrics Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2025) Perera, M; Wijesiriwardena, A; Pathirana, A; Gamaathige, L; Wijesiri, P; Jayakody, A
    This paper investigates the development and application of four machine learning models designed to enhance personalized health management, specifically targeting young adults aged 15-30. The research addresses common health challenges, such as obesity and lifestyle-induced diseases, through data-driven methodologies that provide personalized meal plans, workout recommendations, and progress monitoring. The first model generates optimized personalized recommendations according to the user's health condition using Random Forest and Decision Tree algorithms. The second model utilizes an ensemble of Random Forest, LightGBM, and XGBoost, combined through a stacking technique with Linear Regression as the meta-model, to generate optimized personalized meal plans according to health condition. The third model generates optimized workout plans using Gradient Boosting and XGBoost classifiers, accounting for individual fitness objectives, body compositions, and medical conditions. A fourth model predicts goal achievement timelines by analyzing features such as caloric balance and hydration efficiency, providing users with actionable feedback using XGBoost. The integration of these AI-driven components into a scalable digital platform demonstrates the potential of machine learning in transforming health management. Future enhancements include improving model accuracy, enabling real-time feedback, and deploying the system as an accessible mobile application. ensemble