Research Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194

This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.

Browse

Filters

2022 - 20261.8K

Advanced Search

Filter by

Settings

Start date: 2022

Search Results

Now showing 1 - 10 of 1794
  • No Thumbnail Available
    PublicationEmbargo
    Joint Resource Allocation and Network Slicing in Hybrid RF/VLC Systems: A Proportional-Fairness Approach
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-01) Rajahrajasingh, H; Jayakody, D. N. K.; Peha, J. M
    This article presents a joint resource allocation and network slicing framework for hybrid radio frequency (RF) and visible light communication (VLC) systems based on a proportional-fairness (PF) objective. The proposed approach formulates a convex optimization problem that jointly allocates bandwidth resources across multiple slices and access technologies to balance aggregate throughput and user fairness. A relaxed PF solution is first derived via projected gradient optimization, followed by two practical rounding strategies: a simple threshold-based method and a greedy assignment heuristic that produce integer allocations with low complexity. Simulation results for a 20 MHz hybrid RF/VLC system (10 MHz/band) demonstrate that the proposed PF-based allocation achieves aggregate sum-rates of approximately 450-500 Mb/s with Jain's fairness indices greater than 0.9, thus outperforming static and rounding baselines by 10%-15% in throughput while maintaining high fairness. The analysis is further extended to asymmetric RF/VLC bandwidth conditions, demonstrating that the proposed PF-based slicing maintains high fairness while scaling throughput effectively. These results confirm that the PF formulation effectively captures the throughput fairness tradeoff and provides near-optimal slicing performance under realistic indoor bandwidth and power constraints.
  • No Thumbnail Available
    PublicationEmbargo
    OcupHI: knowledge-driven colorimetric interpretation framework for high-precision real-time ocular pH diagnostics
    (Springer Nature, 2026-08-12) Kahandawala, B, S; Sandaruwan, H. H. P. B; Liyanage, P; Dassanayake, R.S; Costha, N.P; Liyanage, R.N; Wijenayake, U; Wijesinghe, R.E; Silva, B.N; Manatunga, D.C
    Ocular injuries due to chemical spills pose a substantial concern, representing 10–22% of all ocular trauma. Although precise detection of ocular pH is crucial for determining the optimal medical treatment, many existing methods remain invasive, biased, or insufficiently precise. Reliance on subjective visual assessment of subtle color differences limits the objectivity and hinders high-throughput analysis. Therefore, an advanced colorimetric knowledge-driven ocular pH detection method was developed using a biosensor (OcupHI) based on a Clitoria ternatea (Butterfly Pea) anthocyanin sensing agent. The proposed work delivers fast, high-precision, and easily measurable pH prediction across clinically relevant ranges, while supporting real-time decision support for eye physicians. The pH range from 1 to 12 was tested and compared with six different anthocyanin concentrations: 5, 10, 20, 30, 40, and 50 ppm, and five different machine learning models, namely, Decision Tree (DT), K-Nearest Neighbors (KNN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machines (SVM). The results revealed that the 40 ppm anthocyanin concentration trained with the XGBoost model produced the most accurate ocular pH values, achieving superior performance with an overall accuracy of 96%, a significantly higher F1-score for early detection. Experimental validation clearly demonstrates strong predictive accuracy, robustness, and interpretability, highlighting the potential for next-generation ocular diagnostics. Further research findings support Sustainable Development Goal (SDG) 3 – good health and well-being through a real-time ocular pH monitoring kit, and SDG 12 – responsible consumption and production by optimizing the use of the natural colorant anthocyanin for sensor development.
  • Thumbnail Image
    ItemEmbargo
    An Integrated Smart Framework for Post-Harvest Optimization and Market Intelligence
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Gamage U.V.A; Wimalarathna B.P.K; Dharmappriya W.A.I.U.; Rathnayaka S.J.; Tissera, W; Rupasinghe, S; De Silva, H; Priyadarshana W.H.D.
    Post-harvest losses in Sri Lanka's fruit and vegetable supply chain remain a critical challenge, attributed to the absence of integrated quality assessment tools, real-time market intelligence, and accessible decision support systems tailored to local conditions. Existing approaches address these problems in isolation, leaving smallholder farmers without a unified platform for quality grading, price forecasting, post-harvest advisory, and cultivation planning. This paper presents CropShield, a novel four-component AI framework designed to address these gaps for Sri Lankan agricultural stakeholders. The first component employs YOLOv8 for fruit detection followed by MobileNetV2 fine-tuned on a papaya dataset for defect classification across six categories and maturity classification across three stages, with Grad-CAM explainability and a Random Forest recommendation engine integrated with Department of Agriculture knowledge. The second component delivers price forecasting across eleven crop varieties using a hybrid ensemble of ARIMAX, XGBoost, and LightGBM trained on HARTI market data from 2008 to 2025. The third component provides a bilingual post-harvest risk advisory assistant supporting Sinhala and English, integrating real-time weather data with an NLP-driven prediction engine, with SHAP-based explainability for transparent advisory outputs. The fourth component implements a Random Forest-based crop suitability and yield estimation model using district-level agronomic data with SHAP explainability for interpretable crop recommendations. The defect detection model achieved 95.65% accuracy and F1-score under clean conditions and 93.48% under robust augmentation, while the price forecasting model achieved R2=0.986 and MAPE=3.16%. CropShield delivers a scalable, explainable, and farmer-accessible platform for evidence-based agricultural decision-making across Sri Lanka
  • Thumbnail Image
    ItemEmbargo
    Voice Agentic Smart Reader Application In Sinhala and Tamil For Visually Impaired People
    (Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Siriwardana B.J.A; Hewagama A.D; Aluwihare M.C; Sharumathan M; Weerasinghe, M; Abeywardhana, L
    This paper proposes an intelligent smart reading system to improve access to documents, news articles, and printed content for visually impaired and reading-challenged users, particularly in low-resource languages such as Sinhala and Tamil. Although recent advances in computer vision, speech processing, and large language models have enabled effective document understanding, existing systems often operate independently and provide limited support for non-visual navigation, interactive information access, and expressive audio output. The proposed system integrates four main components into a unified framework. First, a voice-guided navigation module enables users to capture documents without visual assistance by providing real-time audio guidance, ensuring proper alignment and reliable image acquisition for text recognition. Second, a Tamil document understanding and question answering module processes document content and supports accurate, context-aware information retrieval using a retrieval-based approach, while also providing personalized content recommendations. Third, a voice-assisted Sinhala reading module allows users to navigate documents and access information using natural voice commands and semantic processing. Finally, an emotional text-to-speech module generates expressive speech in Sinhala and Tamil, improving the naturalness and clarity of audio output. Experimental results demonstrate that the proposed system improves document capture accuracy, navigation efficiency, information retrieval performance, and speech quality. Overall, the system provides a practical, accessible, and user-centered solution for intelligent document interaction in underrepresented languages.
  • Thumbnail Image
    ItemEmbargo
    ML-Based System to Detect GPS Spoofing and Signal Jamming via Signal Logs
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Harshani S.U.E; Wickramasinghe V.D.A; Muthukuda M.A.D.H.N; Siriwardhane H.H.D.V.; Siriwardana, D; Wijesooriya, A
    This paper describes the design, implementation, and analysis of a machine learning-based and forensic-grade desktop system to detect GPS spoofing attacks and signal jamming attacks. The system processes telemetry logs collected from Unmanned Aerial Vehicles (UAVs) and other GNSS-enabled systems to detect any malicious signal manipulations and disruptions. It utilizes a pipeline comprising modules: GPS logging, feature extraction, and an unsupervised machine learning detection engine based on Isolation Forest, One-Class SVM, and LSTM Autoencoder models. The system learns the normal behavioral patterns and is trained on actual GPS data, therefore, identifying the previously unknown attacks. One of the contributions is that forensic concepts, such as hash-SHA-256, chain-of-custody logging, and read-only processing, are factored into the human process, thus supporting evidence integrity and traceability. The system generates elaborate visual and textual reports, giving a user-friendly timeline of the attack with severity ratings. Through the experiment with real and synthetic interfered datasets, the system is found to be effective in predictably distinguishing between spoofing (jumping coordinates and unrealistic kinematics) and jamming (significantly lost signal and large drift variance) with substantial detection. This tool offers an essential feature to cybersecurity forensic investigators, drone operators, and other critical infrastructure defenders to diagnose and record GNSS susceptibility.
  • Thumbnail Image
    ItemEmbargo
    An Ethical and Emotionally Intelligent Social Media Plugin Using Responsible & Explainable AI
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Wickremasinghe N.S.; Ullandupitiya U.P.L.I.; Jayawardena D.S; Jayanetti J.K.D.S.D; Rathnayake S.; Nawarathne M.
    Social media platforms encounter ongoing difficulties with fragmented moderation and interaction operations that do not collaborate effectively to deal with destructive content, inauthentic behavior, emotion-insensitive interaction, and opaque recommendations. This paper features an ethical and emotionally intelligent social media plugin using responsible and explainable AI implemented as a unified real-time service for social media applications, proven through implementation on the Open-Source Social Network (OSSN). The plugin incorporates four elements, namely multimodal cyberbullying detection, behavior-based social bot detection, explainable friend recommendation, and an emotion-aware reaction system. The cyberbullying module is a combination of transformer-based text analysis, image processing, OCR, and keyword fusion to moderate content in an explainable manner, and the fake account module uses temporal behavioral features to detect bot accounts regardless of content. The recommendation system offers interpretable recommendations with context, and the emotion-aware module provides empathetic interaction via emotion recognition and filtering. Experimental results indicate high performance across task-appropriate metrics such as accuracy for classification tasks and MCC/ROC-AUC for bot detection due to class imbalance, yielding 88.60% on text-based cyberbullying, 68.81% on image moderation, MCC 0.9704 and ROC-AUC 0.9981 on bot detection, and 73.10% F1 on sarcasm detection. The outcomes of deployments demonstrate the potential of a single, transparent, and responsible AI system to have safer and more meaningful social media interactions
  • Thumbnail Image
    ItemEmbargo
    Smart Heritage: A Blockchain and NFT Framework for Secure Authentication and Fractional Investment in Sri Lankan Handicrafts
    (Institute of Electrical and Electronics Engineers Inc., 2026-07-06) Manohara K.K.K; Dharmasena E.A.H.T.; Rajapaksha D.N; Bandara H.D; Chamara, D; Abeywardena, K.Y; Nismi, N
    The Sri Lankan handicraft sector possesses significant cultural and economic value; however, counterfeit production, limited ownership traceability, and the absence of resale royalty mechanisms restrict its global scalability. Traditional systems fail to provide reliable provenance verification and sustainable financial benefits for artisans and previous owners. This paper proposes a blockchain-enabled ecosystem integrating Non-Fungible Tokens (NFTs), NFC-based authentication, fractional ownership, and a smart security box to enhance authenticity, transparency, and value creation. Each handicraft is linked to a unique NFT and a cryptographically secured NFC tag, creating a tamper-resistant connection between the physical artifact and its digital identity. Smart contracts enable transparent ownership tracking and automated lifetime royalty distribution, ensuring artisans receive royalties from every future resale without intermediaries. The proposed framework also introduces a fractional ownership model for culturally significant, non-commercial heritage artifacts, enabling collective digital ownership with tiered access to exclusive cultural content while distributing cascading royalties to previous shareholders upon resale. A smart security box with NFC further protects high-value physical artifacts. Prototype evaluation on an Ethereum-compatible test network achieved a 100% success rate across 24 smart contract unit tests, 100% NFC authentication accuracy for 12 handicraft items with average response times of 380-450 ms, and consistent royalty and Proof-of-Residency distribution across nine simulated resale transactions. The key contributions of this work are: (1) a cryptographic NFC-NFT binding mechanism resistant to tag cloning, (2) a smart contract-based lifetime royalty engine with previous-owner redistribution, and (3) a fractional community ownership model that supports global participation in preserving non-commercial cultural heritage. The proposed architecture demonstrates the potential of blockchain technology to preserve cultural heritage while creating a sustainable economic ecosystem for artisans and investors.
  • Thumbnail Image
    ItemEmbargo
    Knowledge Graph-Based AI Framework for Predicting Nutritional and Health Impacts of Food Ingredients
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Dakshina P.D.S.D; Rupasighe W.A.R.K; Waduge N.P; Nimsitha M.V.T; Tissera, W; Rathnayake, S; Krishara, J
    The increasing complexity of modern food products and dietary supplements has made it challenging for both consumers and healthcare professionals to interpret nutritional information and assess the potential health risks associated with these products. Modern food labeling schemes provide static and fragmented information and cannot effectively capture the relationships between different ingredients, nutrients and their health effects. In this study, a new AI-based framework named Food Health Risk Analyzer has been proposed that utilizes KGs, GNNs, RAG and a dose-response module based on consumption quantities to perform the dynamic, explainable and evidence-based prediction of food-related health risks. The model uses heterogeneous data in order to analyze the relationships between ingredients and diseases to predict potential health risks while generating scientifically supported explanations as well. The experimental evaluation has shown high prediction accuracy with a micro-F1 score of 0.88 and AUC of 0.85 which shows that the framework surpasses conventional machine learning baseline models. In addition to that, the use of RAG has helped in improving the interpretability of predictions through evidence-based natural language explanations whereas dose-response module improves the practical relevance of risk assessment by considering the consumption quantities of ingredients.
  • Thumbnail Image
    ItemEmbargo
    CocoSense: AI-Powered Drone-Based System for Comprehensive Coconut Tree Health Monitoring and Yield Prediction
    (Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Subasinghe, M; Panditharathne, R; Pasanjith, R; Nadun, T; Samarakoon, U; Tissera, W
    Coconut cultivation is vital to Sri Lanka's agricultural economy, yet farmers face significant challenges in early pest detection, disease diagnosis, and yield prediction. This research presents CocoSense, an AI-powered mobile application integrated with IoT technology for automated coconut tree health monitoring using drone-captured imagery. The system comprises four modules: (1) pest detection using EfficientNetB0 (91.44% accuracy) and MobileNetV2 (96.08% accuracy) with a trilingual AI chatbot for treatment recommendations; (2) disease detection for leaf rot, leaf spot, and leaf dieback classification (98.69% accuracy); (3) health assessment for leaf (93.70%) and branch health (99.63%); and (4) coconut yield estimation (87.86% accuracy) using YOLOv8 with dual-view acquisition strategy. Additionally, a coconut bunch detection (88.96% accuracy) module is developed to support yield estimation by identifying fruit clusters within tree canopies. The system integrates IoT-based GPS tracking with Google Maps API for real-time plantation visualization. Experimental results demonstrate that CocoSense provides a robust, accessible solution for intelligent coconut plantation management in Sri Lanka.
  • Thumbnail Image
    ItemEmbargo
    Sinhala-English Multilingual AI Call Center Bot with Sentiment-Aware Dialogue and Multimodal CSAT Prediction
    (Institute of Electrical and Electronics Engineers Inc., 2026-07-06) Kulathunga, T; Amarasinghe, B; Fernando, V; Lakruwani, P; Weerasinghe, M; Kasthurirathna, D
    This paper presents a Sri Lanka focused, voice-based call center automation framework supporting Sinhala, English, and Sinhala-English code-mixed conversations in low-resource environments. The system adopts an end-to-end architecture integrating bilingual dataset construction, privacy-preserving speech processing, retrieval-grounded response generation, multimodal sentiment intelligence, and customer satisfaction (CSAT) estimation. A Sinhala-English call-center corpus is created using noise reduction, speaker diarization, and transcript alignment, combined with transcript-aligned PII redaction. During live interaction, language identification routes calls to unified processing pipelines. Real-time sentiment analysis with explainable risk scoring supports escalation decisions, while retrieval-augmented generation ensures factually grounded responses. Emotion-adaptive text-to-speech enhances conversational naturalness. The framework enables interaction-based CSAT estimation without relying solely on post-call surveys, providing scalable and privacy-aware automation tailored to multilingual Sri Lankan call center operations