Faculty of Computing
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4776
Browse
6 results
Search Results
Item Embargo 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.GEnsuring 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.Item Open Access Enhancing IoT Resilience: Machine Learning Techniques for Autonomous Anomaly Detection and Threat Mitigation(Elsevier B.V., 2025-03-05) Lokuliyana, S; Kalupahanage A.G.A; Herath H.M.S.D; Siriwardana, D; Bulathsinhala D.N.; Herath H.M.T.MThe explosive growth of the Internet of Things (IoT) has had a substantial impact on daily life and businesses, allowing for real-time monitoring and decision-making. However, increased connectivity also brings higher security risks, such as botnet attacks and the need for stronger user authentication. This research explores how machine learning can enhance Internet of Things security by identifying abnormal activity, utilizing behavioral biometrics to secure cloud-based dashboards, and detecting botnet threats early. Researchers tested numerous machine learning methods, including K-Nearest Neighbors (KNN), Decision Trees, Logistic Regression, and XGBoost on publicly available datasets. The Decision Tree model earned an impressive accuracy rate of 0.73 for anomaly identification, proving its supremacy in dealing with complex security risks, while the XGBoost model demonstrated strong performance with a 92% accuracy rate for detecting TCP SYN flood attacks. Research findings show the effectiveness of these strategies in enhancing the security and reliability of IoT devices. This study provides significant insights into the use of machine learning to protect IoT devices while also addressing crucial concerns such as power consumption and privacy.Item Embargo Federated Edge Intelligence for Adaptive Health Prediction in Elderly Care(Institute of Electrical and Electronics Engineers Inc., 2025-12-17) Silva G.D.T; Sineth H.M.G; Constantine S.A.D.N.C.H; Dissanayake M.E; Pandithage, D; Lokuliyana, SThis research presents the development and evaluation of an IoT-based nursing home monitoring system designed to enhance elderly healthcare through real-time detection, predictive alerts, and caregiver support. The system integrates multimodal sensing with edge and server-level machine learning to monitor three critical areas: sleep quality, fall detection, and emotion recognition in dementia patients. Hardware components, including a Raspberry Pi and non-intrusive sensors, were combined with lightweight neural networks to ensure low-latency processing. Detailed model optimizations, including 8-bit quantized TensorFlow Lite MobileNetV2 and CNN-LSTM pipelines, enabled on-device inference within 80-120 ms. A caregiver dashboard and mobile application provided intuitive visualization of real-time alerts and long-term health reports. Benchmarking against threshold-based and classical ML baselines demonstrated 9-18% performance improvements and 56% lower alert latency. Experimental evaluation demonstrated promising outcomes, with fall detection achieving 95% accuracy, emotion detection 91%, and sleep monitoring 90% reliability. System uptime reached 98%, and alerts were delivered within two seconds in 96% of cases. These results indicate that the proposed solution can effectively reduce caregiver burden, improve resident safety, and establish a scalable framework for intelligent elderly healthcare monitoring.Item Embargo A Lightweight YOLOv8n-Based Binary Waste Classification Model for Autonomous Garbage-Collecting Robots(Institute of Electrical and Electronics Engineers Inc., 2026-07-02) Perera W.B.N.; Sendanayaka H.K; Nuwanthi B.D.T.; Jayasekara R.G.S; Lokuliyana, S; Silva, SEfficient waste classification is critical for automation in modern waste management systems, especially in places where it is hard to use manual classification. In this work, a model for waste and non-waste classification based on the YOLOv8n framework, known for high efficiency and applicability for embedded systems, is designed. For this purpose, a customized dataset was collected using real photos under different lighting conditions, different backgrounds, and with varying objects to reflect a more realistic environment. The training process included augmentation, normalization, and hyperparameters tuning to improve the efficiency of the model. Evaluation metrics such as accuracy, precision, recall, F1 score, and confusion matrix were used. According to the experimental results, the developed model provides an accuracy of 92.5% and F1 score of 0.94 with maintaining fast inference performance for real-time applications. The designed framework aims to become a module in an autonomous waste collecting robot to validate objects before manipulating them by robots, ensuring reliable and efficient real-world system performance.Item Embargo 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, PCoconut 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.Item Embargo Dynamic Bandwidth Allocation in Enterprise Network Architecture: A Real-Time Optimization Approach(Institute of Electrical and Electronics Engineers Inc., 2025) Wickramasinghe T.M.L.D; Costa M.M.R.S; Dissanayake S.C.W.; Abayakoon A.M.W.Y.; Lokuliyana, S; Gamage, NEnterprise networks increasingly rely on cloud platforms, remote collaboration tools, and real-time communication, placing high demands on bandwidth availability and responsiveness. Static bandwidth allocation approaches often fail to adapt to dynamic traffic conditions, leading to congestion, inefficiency, and degraded Quality of Service (QoS) for critical services such as VoIP and video conferencing. This research introduces a novel real-time bandwidth allocation system that integrates Deep Packet Inspection (DPI), supervised machine learning, and Linux traffic control (tc). Unlike prior solutions that focus only on classification or simulation, our system actively enforces bandwidth policies based on live predictions. Traffic is captured and analyzed in the WAN, while adaptive policies are deployed in the LAN. A web dashboard offers real-time traffic and bandwidth visibility. The proposed system addresses realworld enterprise challenges by enabling intelligent, responsive bandwidth management without requiring costly infrastructure changes, achieving measurable improvements in latency, throughput, and application-level prioritization.