Faculty of Computing

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

Browse

Filters

Advanced Search

Filter by

Settings

Search Results

Now showing 1 - 10 of 129
  • Thumbnail Image
    ItemEmbargo
    SmartSphere: Bridging AI-Powered Automation and Tesla Coil Wireless Energy for Smarter Living
    (Institute of Electrical and Electronics Engineers Inc., 2025) Jurison Jenaraj, J.K; Umasuthan, A; Vigneswaran, V; Raveendran, K; Thiruthanigesan, K; Kasthuriarachchi, S
    This paper presents SmartSphere, an intelligent, secure, and wire-free home automation system that synergizes artificial intelligence, multi-factor access control, and resonant wireless power transmission. Built on an edge-computing architecture using ESP32 and Arduino Mega 2560 microcontrollers, SmartSphere integrates facial recognition, fingerprint authentication (96.7% accuracy), and IR-based presence detection to reduce false activations by 75%. The system employs OpenCV and TensorFlow Lite for real-time anomaly detection and environmental personalization, including weather-responsive adjustments and emotion-aware lighting via facial expression analysis. A key innovation is the incorporation of a Tesla coil-based wireless power transmission module, which eliminates conventional wiring constraints and reduces installation cabling by 86%. Experimental validation demonstrates a 14% improvement in energy efficiency, 75% faster response time (0.3 s), and seamless compatibility with 92% of tested IoT devices. Through comprehensive testing and validation, this research establishes SmartSphere as a secure, intelligent, and sustainable solution for next-generation smart homes, addressing the limitations of traditional wired systems while enhancing the user experience through AI-driven personalization.
  • 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
    Mobile Application for Enhance Sustainable Tea Farming in Sri Lanka
    (Institute of Electrical and Electronics Engineers Inc., 2025-10-27) Lokuliyana, S; Wijesiri, P; Kulathunga H.A.S.C; Perera K.N.T.; Koongahage M.G
    Ensuring sustainable tea farming requires intensive monitoring of plant conditions, nutritional status, and disease infections. To that end, this research presents a smartphone application that is powered by machine learning to assist Sri Lankan tea farmers in identifying fertilizer and chemical deficiencies, predicting tea yield quality, and detecting diseases at early stages. The system makes use of a trained machine-learning model to scan images of leaves for relevant characteristics to provide instant feedback through a user-friendly smartphone interface. The app offers advice to farmers to improve yield and reduce crop loss. This approach enhances accuracy in farming, minimizes reliance on over-fertilization, and assists in efficient farming methods. The given system is designed to target small scale and far-away farmers to make it more popular in diversified agricultural lands. The research involves mass-scale agricultural image dataset collection and processing, deep learning model training, and deployment of a robust mobile application for field implementation. Outputs strive to contribute to Sri Lankan smart agriculture by allowing farmers to make data-driven decisions to ultimately improve productivity and sustainability.
  • Thumbnail Image
    ItemEmbargo
    Hybrid Deep Learning Approach Using YOLO and Spatial Transformers for Kinesthetic Math Education in Low-Resource Settings
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Sellapperuma M.S; Wasana, K.H. I; Dhananjana, B.K. T; Anuruddhika, D. L. N; Krishara, J; Wijendra, D
    This research presents a hybrid deep-learning system to enhance kinesthetic math education for Grade 4 and 5 students in low-resource Sri Lankan classrooms, addressing addition, subtraction, and time-telling skills in Sinhala. Integrating fine-tuned You Only Look Once version 11 (YOLOv11) for real-time abacus recognition and pre-trained Spatial Transformer Network (STN) with Residual Network 50 (ResNet50) for analog clock analysis, the system bridges physical manipulatives with digital feedback. Optimized for low-cost hardware via post-training quantization, it reduces model sizes by up to 56.6% and inference times by 45.9%, enabling deployment on standard PCs. The methodology employs YOLOv11 to detect abacus beads (mean Average Precision, mAP50-95: 0.898) and STN + ResNet50 to correct clock perspectives (95.2% accuracy on SynClock), delivering immediate Sinhala feedback through a culturally adapted interface. The system was evaluated on an Intel Core i5 PC with 8GB RAM and achieved sub-second inference (YOLOv11: 170.1 ms, STN + ResNet50: 32 ms post-quantization) while retaining accuracy. A pilot study with 20 students showed a 25% improvement in arithmetic scores and 30% in time-telling accuracy, with 85% reporting higher engagement. These findings demonstrate the system's efficacy in boosting numeracy and interaction in resource-scarce settings, aligning with the Visual, Aural, Read/Write, Kinesthetic (VARK) framework. Despite challenges like hardware constraints and real-world variability, this scalable, offline-capable solution offers a novel approach to educational technology, with potential for broader deployment in Sri Lanka and similar contexts, addressing gaps in artificial intelligence-driven kinesthetic learning tools. ©
  • Thumbnail Image
    ItemEmbargo
    Intelligent Water Quality Monitoring and Prediction System
    (Institute of Electrical and Electronics Engineers Inc., 2025-06-25) Shiraz, S; Karunasena, K; Mudelige, H; Kumarasinghe, O; Nawinna, D; Perera, J
    The paper aims to develop an integrated approach to improve water treatment processes using predictive modeling and SCADA integration in order to meet the specific needs of water purification systems in Sri Lanka. The current systems utilized for this need are outdated since these systems are based on traditional technologies and do not have the means for predictions or real-time data accessibility outside the system. The proposed solution will focus on raw water quality prediction, optimization of chemical usage to bring in efficiency, sustainability, and resource management, ensuring seamless access to all the relevant data required to manage and monitor. In order to achieve this, past data provided by the Meewatura water plant in Sri Lanka, sourced from the Mahawali river, is utilized for the relevant predictions alongside of the data gathered through the SCADA system. The data is not directly accessible since the SCADA system is mainly built for monitoring, and in order to get the data, a MODBUS connection through the PLC is utilized alongside of an IOT device. In addition to the extracted data, past data that was provided by the water plant is also incorporated. The combined data set is utilized for the predictions while continuously improving itself with new data. The present study contributes to the establishment of sustainable and adaptable water treatment frameworks for a wide range of operational needs within the water plants by addressing the gaps in the existing water quality management systems and improving upon them.
  • 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
    Evaluating and Enhancing the Robustness of Convolutional Neural Networks Against Adversarial Attacks: A Case Study on MNIST
    (Institute of Electrical and Electronics Engineers Inc., 2025-12-12) Aththanayaka A.M.R.E; Jayakody, A
    Convolutional Neural Networks (CNNs) have achieved exceptional performance in computer vision tasks, particularly in image classification domains such as MNIST digit recognition. However, their susceptibility to adversarial attacks poses serious security threats that limit their deployment in real-world applications. This research comprehensively examines CNNs vulnerability through systematic evaluation of five potent adversarial attacks such as FGSM, BIM, PGD, Deep Fool, and Carlini-Wagner on MNIST dataset. The baseline CNN model achieves 99.23% accuracy on clean data, but experiences catastrophic performance degradation under adversarial conditions, with accuracy dropping to as low as 8.91% against BIM attacks. To address these vulnerabilities, this study proposes CADF: a Comprehensive Cyber Attack Detection Framework that implements a multi-layered defense strategy. The framework incorporates a binary detection classifier achieving 99.56% accuracy in identifying adversarial examples, followed by a multi-class attack identifier with 93.56% accuracy in categorizing specific threat types. CADF's adaptive defense engine dynamically selects optimal countermeasures including feature squeezing, spatial smoothing, and ensemble defenses based on the identified attack characteristics. This integrated approach provides a scalable and efficient solution for enhancing CNN robustness without compromising computational performance, offering significant advancements in securing deep learning systems against evolving adversarial threats.
  • Thumbnail Image
    ItemEmbargo
    LexAyudha : Personalized AI-Driven Rehabilitation for Adolescents with Dyslexia and Dyscalculia
    (Institute of Electrical and Electronics Engineers Inc., 2025-07-03) Silva, U; Madusanka, I; Thalangama, T; Dissanayake, T; Thelijjagoda, S; Vidanaralage, A. J
    Dyslexia and dyscalculia, the most common learning disabilities, produce a considerably challenging environment for adolescents and lead to frustration, disengagement, and reduced self-esteem. While assistive technologies with influential functionalities exist, they lack personalization for effective and supportive learning. LexAyudha is an AI-powered platform addressing these gaps by integrating proven medical methodologies such as chromatic variation, Touch Math, and multisensory teaching strategies. Advanced AI technologies like Convolutional and Recurrent Neural Networks have been used in LexAyudha to dynamically adjust reading content, visual layouts, and lesson plans in the gamified app based on students' performances to cater for their requirements. Moreover, a novel emotion recognition algorithm even adjusts difficulty levels of activities and voice output with altered audio features to ensure a stress-free learning process and a stimulating environment. Initial findings based on the user performances tests conducted with the dyslexic and dyscalculia adolescents in Sri Lanka, represents significant improvements in reading fluency, comprehension, and motivation, showing that adaptive learning with AI has the potential to revolutionize learning for dyslexic and dyscalculia students. The research identifies the potential of rehabilitation with AI-driven technology as a flexible and scalable solution for personalized education in dyslexia and dyscalculia.
  • 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
    Context-Aware Behavior-Driven Pipeline Generation
    (Institute of Electrical and Electronics Engineers Inc., 2025-04-24) Gunathilaka, P; Senadheera, D; Perara, S; Gunawardana, C; Thelijjagoda, S; Krishara, J
    An efficient CI/CD process is crucial for modern software teams, but manual pipeline creation is error-prone and requires high DevOps expertise, slowing deployment speed and reducing productivity. This research introduces a context-aware, behavior-driven approach to fully automating CI/CD pipeline generation by analyzing GitHub user activity patterns. The proposed solution utilizes a historical analysis of repository events, developer contributions, and workload distribution to dynamically generate pipelines and assign reviewers to pull requests based on expertise. Unlike previous template-based and generative AI solutions that require manual intervention, our approach leverages pattern recognition and adaptive decision-making to continuously refine automation. This paper presents the methodology behind data collection, analysis, and pipeline generation, demonstrating its effectiveness in reducing human effort while improving software delivery efficiency. This research highlights how behavior-driven automation streamlines the complexity of CI/CD pipeline creation, enabling more adaptive and intelligent systems that effectively respond to the evolving needs of software development teams.