Faculty of Computing

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4776

Browse

Filters

2025 - 202627

Advanced Search

Filter by

Settings

Start date: 2025Subject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 10 of 27
  • Thumbnail Image
    ItemEmbargo
    AI-Assisted Criminal Investigations: Enhancing Testimony Analysis and Case Correlation
    (Institute of Electrical and Electronics Engineers Inc., 2025-12-08) Karunarathna K.A.D; Ediriweera E.R.L.C; Fernando N.D.R.N; Abeywardana B.A.I.S; Abeywardhana, L
    This paper presents Lexa AI, a holistic AIpowered solution for improving criminal investigative practices through four phases that target key drawbacks found in traditional practices. The first model provides an automated data/information collection stage that accepts legal documents in multiple formats and utilizes a three-stage processing pipeline based on Gemini 2.0 Flash model, which performs Optical Character Recognition (OCR) with a higher level of accuracy and speed compared to alternative approaches. The collected data will be forwarded to the next phase by leveraging dynamic question generation that uses Reinforcement Learning (RL), instantaneous multilingual capabilities, and real-time scoring of relevance. The third phase conducts Multimodal Behavioral and Physiological Analysis (MBPA), which includes facial signals, speech signals, and heart rate signals to create a combined Stress Index as an objective indicator and avoids subjective judgment. Finally, semantic similarity will be measured to correlate incidents, assess risk for victims, and provide explainable predictions
  • Thumbnail Image
    ItemEmbargo
    A Mobile Application to Enhance Skills in Children with Nonverbal Learning Disability
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Harshana W.C; Hettiarachchi H.K.Y.K; Mendis T.S.P; Madanayake P.C.S.; Weerasinghe, L; Nawarathne, M
    Nonverbal Learning Disability (NVLD) is a neurodevelopmental disorder affecting children, characterized by strong verbal skills but significant challenges in visual-spatial processing, motor skills, and communication. This paper introduces a mobile application designed to address these challenges through interactive and personalized activities. The app leverages machine learning and artificial intelligence to improve visual-spatial abilities, communication skills, and cognitive development. By engaging children in pattern recognition, word recognition, and touch screen integration, the app aims to enhance critical thinking, decision-making, and relationship identification in children aged 10-13. The algorithms used in this research are the Dynamic Difficulty Adjustment Algorithm, Random Forest Classifier, Real-Time Object Detection Algorithm, and Deep Q-Network (DQN). This paper explores the development, features, and impact of the app in supporting children with NVLD.
  • Thumbnail Image
    ItemEmbargo
    NSCLC 360 - Leveraging Multi-Omics Data for a Holistic and Explainable Decision Support for Non Small Cell Lung Cancer Management
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Pirabaharan, A; Irfan, A. A.; Lareef, W; Ahamed, S; Rathnayake, S; Shyamalee, T
    Non-Small Cell Lung Cancer (NSCLC) remains a leading cause of cancer-related mortality, with existing diagnostic and prognostic models often failing to capture the complexity of tumor biology. This study proposes a holistic and explainable decision support system that integrates multi-omics data - including genomics, transcriptomics, and proteomics - along with advanced machine learning (ML) and deep learning (DL) techniques to enhance NSCLC detection, prognosis prediction, complication forecasting, and recurrence assessment. To address the challenge of interpretability in AI-driven healthcare, we incorporate Explainable AI (XAI) methods such as SHAP and LIME, ensuring model transparency and clinical trust. Additionally, traditional statistical models like Cox proportional hazards regression are combined with ML approaches for robust survival analysis, while modern AI architectures, including Vision Transformers and multi-task learning models, improve tumor localization and TNM classification. By developing an interpretable and clinically meaningful AI-based decision support system, this research aims to advance personalized lung cancer management and improve patient outcomes through seamless integration into clinical workflows.
  • Thumbnail Image
    ItemEmbargo
    AI Driven Smart Tourism Platform for Personalized Safe and Sustainable Travel Planning
    (Institute of Electrical and Electronics Engineers Inc., 2025-12-08) Srikanthan, S; Senevirathne, C; Rasarathnam, T; Jayalath, T; Rajendran, K
    Tourism planning remains challenging due to the need for group preference alignment, personalized itinerary generation, and real-time budget control, challenges that are not adequately supported by existing platforms. This paper presents an AI-driven modular framework that integrates three components: a semantic-aware group recommender that uses Sentence-BERT embeddings with a learning-to-rank model to match travelers; a hybrid itinerary planner that fuses content-based filtering, collaborative filtering, and machine-learning-based rating prediction to generate preference-aligned and geographically coherent travel plans and a predictive budgeting system that applies regression-based forecasting with live API data to provide dynamic cost estimation. The platform is developed specifically for the Sri Lankan tourism context, incorporating regional travel behavior patterns and destination characteristics into its models. Experiments indicate strong performance across all modules, including high-quality group matching, accurate itinerary prediction, and a substantial improvement in budget estimation accuracy compared with static baselines. Early user testing further highlights increased satisfaction with itinerary relevance and budget transparency. Overall, the framework demonstrates a scalable and adaptive approach to smart tourism planning, advancing personalization, collaboration, and sustainable travel support.
  • Thumbnail Image
    ItemEmbargo
    Personalized Adaptive System for Enhancing University Student Performance in Sri Lanka
    (Institute of Electrical and Electronics Engineers Inc., 2025-05-01) Dissanayake, N; Samarakoon, C; Wickramasinghe, D; Pathirana, M; Gamage N.D.U; Attanayaka, B
    The growing need for personalized learning strategies has driven the development of data-driven solutions to meet the diverse needs of Sri Lankan university students. A key challenge lies in identifying optimal learning paths that align with individual capabilities, learning styles, and engagement behaviors to improve academic performance. While previous research has explored generalized learning models, these often fail to adapt to the specific demands of individual learners. Traditional strategies lack personalization, resulting in inconsistent learning progress. To address this gap, the research introduces an assistive, data-driven approach that leverages Self-Organizing Maps (SOMs), Adaptive Learning (AL), Content-Based Filtering, Graph Neural Networks (GNNs), and Social Network Analysis (SNA) to create optimized, personalized learning strategies. Clustering algorithms and predictive analysis were used to segment learners and deliver tailored interventions based on their behavior. The proposed system integrates advanced machine learning techniques to enhance student engagement and improve overall academic outcomes through personalized pathways.
  • 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.
  • Thumbnail Image
    ItemOpen Access
    Smart Agricultural Platform for Sri Lankan Farmers with Price Prediction, Blockchain Security, and Adaptive Interfaces
    (Institute of Electrical and Electronics Engineers Inc., 2025-06-25) Kuruppu K.A.G.S.R; Kandambige S.T; Perera W.H.T.H.; Cooray N.T.L; Nawinna, D; Perera, J
    Improper management of seed demand in Sri Lanka's agricultural sector can result in market imbalances, affecting farmers' decision-making and supply chain efficiency. This research introduces an integrated system for monitoring vegetable seed demand using digital technologies. The proposed system utilizes machine learning techniques to predict vegetable prices, a blockchain network for secure transactions, and a reward-based system to encourage user engagement. It also incorporates an adaptive user interface to accommodate different levels of digital literacy, ensuring accessibility for all farmers, especially senior citizens. Furthermore, the system features an AI Chatbot powered by Langchain and Pinecone, offering domain-specific responses and real-time support for farmers. The solution aims to combine advanced technology with agricultural practices to improve seed demand forecasting, promote transparency in transactions, and ensure a more efficient supply chain. This paper presents a multi-component agricultural platform that integrates predictive analytics, blockchain-secured transactions, gamified incentives, and adaptive user interfaces to support farming decision-making. The system combines machine learning for price forecasting, dynamic reward mechanisms to drive user engagement, and personalized UI/UX optimizations tailored for diverse user groups, including senior farmers. A multilingual AI-powered chatbot enhances accessibility and real-time support, enabling a robust, transparent, and inclusive digital solution for agricultural supply chain management.
  • Thumbnail Image
    ItemEmbargo
    Grade 6 Coding Education through Interactive Learning in Sri Lanka
    (Institute of Electrical and Electronics Engineers, 2025-12-08) Nallaperuma, S; Perera, A; Nanayakkara, N; Hansaja, D; Krishara, J; Wijendra, D
    This study proposes an AI-powered Adaptive Learning Management System (LMS) to enhance coding education for school students. The system integrates six AI/ML models and FaceNet-based facial authentication to deliver adaptive learning pathways, real-time feedback, and personalized assessments. It begins with an initial benchmarking assessment across seven categories, after which the Exam Difficulty and Question Count Model and a fine-tuned GPT-2 generator collaboratively create customized multiple-choice questions based on each learner's capability. Learning is supported through skill prediction, dynamic difficulty monitoring, and emotional state detection to ensure both cognitive and emotional engagement. Students scoring above 60% advance directly to coding curricula, while others receive personalized scaffolding through multimodal learning-style-based modules. Teachers benefit from AI-powered analytics tools that offer continuous feedback, weak-topic detection, and pedagogical guidance to enhance teaching effectiveness. By combining authentication, adaptive assessment, emotional intelligence, and teacher support, this study presents a comprehensive framework to democratize coding education and foster resilience, motivation, and mastery among students aged 10-12.
  • 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
    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.