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
2613 results
Search Results
Item Embargo 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, JThe 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.Item Embargo 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, WCoconut 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.Item Embargo 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, DThis 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 operationsItem Embargo PregAssist: Pregnancy Support Mobile Application for Pregnant Mothers and Doctors(Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Buddika, B. P; Jayasinghe N.; Perera A.N.M; Wijethunga D.N; Weerasinghe, M; Dunuwila, OPregnant care involves constant follow-ups, timely risk detection, and successful interactions between mothers and medics. This paper introduces PregAssist, a mobile integrated support system that is a synthesis of four products, including fetal health decision support, physical health risk prediction, AI-based mental health monitoring, and AR-driven emergency training. The fetal health module provides explainable and offline-capable cardiotocography (CTG) classification to assist clinical decision-making. XGBoost classifier with SHAP-based interpretability is used to analyze physical risks to generate individual recommendations and alerts. Mental health assessment integrates questionnaire-based indicators with CNN-driven facial emotion recognition, while federated learning preserves data privacy through on-device training. AR-based deterministic expert system offers protocol-adherent emergency simulations to improve preparedness activity when facing high-level of risk. Through the convergence of predictive analytics, explainable AI, privacy preserving learning, and training design, PregAssist assists in proactive maternal attention in urban and resource constrained environments via combining a hybrid mobile architecture.Item Embargo Secure Enhanced JWT Framework with Post-Quantum Cryptography(Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Sunera, A; Ransika, Y; Rasiru, M; Gunawardane, A; Abeywardena, K. Y; Senarathne, AJSON Web Tokens (JWTs) are widely used in distributed authentication, but many implementations still rely on classical algorithms such as RSA and provide limited support for key transparency, guarded validation, and secure revocation. These limitations reduce their suitability for future-ready security environments [1], [2], [3]. This research proposes a secure enhanced JWT framework built on four integrated components: a post-quantum signing and verification service, a transparency-driven key distribution service, a guard layer for policy enforcement, and a secure revocation service. The framework introduces ML-DSA-based post-quantum signatures while strengthening key integrity, token validation, and revocation control. A classical RS256-based authentication system was used as the baseline and compared against the integrated post-quantum system. The baseline recorded an average login latency of 77.891 ms, verification latency of 17.078 ms, protected endpoint latency of 14.608 ms, and an average token size of 519 bytes. The integrated post-quantum system achieved an overall average request latency of 67.245 ms, 97.667 ms p95 request latency, zero request failures, and 71.943 requests per second in the scoped live benchmark. The results show that the proposed framework maintains operational stability while delivering stronger security properties than conventional JWT systems, contributing a unified JWT security architecture that integrates post-quantum signatures, transparency-based key distribution, guarded validation, and revocation-aware trust enforcement into a single end-to-end authentication model.Item Embargo AgriSense LK: Weekly Automated Machine Learning for Sri Lankan Produce Prices with Business Continuity Plan, Market Opportunity Ranking, Cultivation Targeting, and Yield Quality Valuation(Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Matharaarachchi, Charaka J.; Samarasinghe, Ravindu T; Vidyasarani G.G.T.; Fasnas, M; Siriwardana, D; Wijesooriya, AIn Sri Lanka, agricultural decision-making remains largely traditional: decisions are often based on historical practices, informal consultation, and heuristic judgment. The primary barrier is that market price data is difficult to interpret without analytical expertise, resulting in unpredictable price volatility and suboptimal farmer income. AgriSense LK is a machine learning platform that converts historical price records into actionable recommendations for farmers and traders. The system comprises four components: business strategy classification, market opportunity ranking, cultivation targeting, and smartphone-based produce quality grading. The platform was trained on 123,985 real price records sourced from the Central Bank of Sri Lanka (CBSL), spanning 2017 to 2025. Key results include a MAPE of 0.7% and MAE of Rs. 1.86 on weekly price forecasting (a 98.1% improvement over the naive baseline), a ROC-AUC of 0.9056 on cultivation targeting, and 91.49% crop classification accuracy with 89.84% quality grade accuracy in the computer vision component. Direct price regression over a seven-day horizon proved unreliable; a binary profitability classifier was adopted instead and substantially outperformed the regression approach. While results are promising, further validation under real-world deployment conditions is required.Item Embargo Early Detection of Student Mental Health and Academic Burnout Using Multimodal AI-Based Behavioral, Physiological, and Emotional Analysis(Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Indrapala W.V.H.; Kumarasinghe K.D.K.Y.; De Silva A.H.H.; Ranathunga A.K.M.; Weerasinghe, L; Weerathunga, IMental health issues such as stress, anxiety, depression, and academic burnout are increasingly common among university students and have a significant impact on academic performance and long-term well-being. Existing assessment approaches rely mainly on self-reported questionnaires and periodic evaluations, which are reactive, subjective, and ineffective for early intervention. This paper presents a multimodal artificial intelligence-based system for early identification of student mental health conditions by analyzing behavioral, physiological, emotional, and academic data. The proposed framework integrates facial emotion recognition, wearable sensor data analysis, natural language processing of reflective text to continuously monitor student well-being in a privacy-aware manner. Machine learning and deep learning models are employed to detect stress, anxiety, and burnout indicators and to predict future mental health risks. Experimental results obtained from real and synthetic datasets demonstrate that multimodal analysis provides more reliable and accurate predictions than single-source methods. The proposed system enables early risk identification and supports timely intervention in academic environments.Item Embargo AI-Driven Decision Support System for Sustainable Agarwood Cultivation and Export Readiness(Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Malmali W.S.V.M.O; Jayawardena L.P.G.K.; Rathnamalala R.M.B.I.T.; Kandage T.P.; Weerasinghe, LokeshaAgarwood cultivation and export involve multiple critical decision points that directly affect resin quality, economic value, and market acceptance. In current practice, decisions related to resin induction timing, disease identification, and export readiness are largely based on manual inspection and subjective judgment, leading to inconsistent assessments and avoidable losses. This paper presents an AI-based decision support system to support sustainable agarwood cultivation and export by integrating three analytical components: resin induction stage classification, export readiness and quality assessment, and leaf disease detection with remedy recommendation. A multimodal deep learning approach combining bark images and numerical tree parameters is used for resin induction stage classification, achieving a test accuracy of 93% using an EfficientNetB0 with a Multi-Layer Perceptron (MLP). Agarwood resin and chip quality grading is performed using an EfficientNetB0-based Convolutional Neural Network (CNN), while export readiness is evaluated using a Random Forest-based numerical model. Leaf disease detection is implemented using a CNN-based classifier, achieving an overall accuracy of 80% across four common agarwood leaf disease classes. Explainability mechanisms, including Gradient-weighted Class Activation Mapping (Grad-CAM) and reason based readiness analysis, are incorporated to enhance transparency and user trust. Experimental results indicate that the proposed system reduces subjectivity and supports data-driven decision-making across key stages of the agarwood value chain.Item Embargo The Multi-Tenant Customization Paradox: Formalising the Intrinsic Conflict Between Scalable Shared Codebases and Tenant-Specific Operational Customization in SaaS Architecture(Institute of Electrical and Electronics Engineers Inc., 2026-07-07) Jayasuriya, R; Piyarisi, T; Awandya, S; Wickramasooriya, S; Thelijjagoda, S; Kasthurirathna, DMulti-tenant Software-as-a-Service (SaaS) architectures promise economies of scale through a single shared codebase serving multiple tenants. However, enterprise tenants increasingly demand deep operational customization (bespoke workflows, domain-specific business rules, and industry-specific computational logic) that fundamentally conflicts with the sharedcodebase constraint. Despite the centrality of this tension to SaaS architecture, no formal definition exists in the literature. This paper formally defines the Multi-Tenant Customization Paradox (MTCP): the structural impossibility of simultaneously maximizing codebase unity and tenant customization depth without incurring costs that grow super-linearly with the number of tenants. We introduce a formal model quantifying this tension through the Paradox Coefficient $P(S)$, establish a five-dimensional customization taxonomy with per-dimension formal measures, derive the Feasibility Region governed by an architectural sophistication parameter $α(B)$, propose an operational rubric for estimating $α(B)$ in practice, and derive an upper bound on the achievable unity-depth trade-off for four canonical resolution strategies. Our formalization demonstrates that the paradox is inherent to the mathematical structure of multi-tenancy rather than incidental to implementation choices, providing architects and researchers with a theoretical foundation for reasoning about customization trade-offs.Publication Open Access Integrating industry 4.0 and 5.0 technologies in luxury fashion retail interiors: A systematic review of digital transformation, sensory design, and brand storytelling(Elsevier Ltd, 2026-05-12) Ratnayake, Janitha C; Jayasuriya, N; Suraweera, T; De Silva, LEmerging developments in Industry 4.0 and Industry 5.0 are transforming the cultural, sensory, and experiential character of luxury fashion retail interiors. These changes, driven by artificial intelligence, the Internet of Things, augmented and virtual reality, influence how individuals perceive space, form emotional connections, and engage with brand narratives across both physical and digitally enriched environments. Against this backdrop, this review aims to systematically synthesise how Industry 4.0 and Industry 5.0 technologies intersect with sensory experience, spatial design, and narrative expression in luxury fashion retail interiors, addressing the tendency of prior reviews to examine digital technologies or experiential aspects of retail in isolation. The study adopts a systematic literature review approach guided by the SPIDER framework and the PRISMA protocol. Fifty peer reviewed publications published between 2014 and 2025 were analysed to examine how digital transformation, sensory experience, and narrative expression intersect within luxury retail culture. The thematic analysis identified three closely connected areas: branding and customer experience, the interior environment of luxury stores, and the integration of advanced technologies within retail spaces. Together, these themes illustrate how contemporary luxury interiors operate as culturally expressive and emotionally charged settings shaped by new forms of technological mediation. Building on these insights, the study introduces the Multi-Layered Integration Framework, which explains the interaction between digital systems, spatial atmospheres, and brand storytelling in the creation of culturally responsive and human-centred retail interiors. The review contributes to the social sciences and humanities by demonstrating how emerging technologies reshape sensory engagement, symbolic identity, and cultural expression in luxury retail settings, while offering an expanded understanding of human experience within digitally influenced interior environments.
