Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
482 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access Enhancing Organizational Threat Profiling by Employing Deep Learning with Physical Security Systems and Human Behavior Analysis(Science and Information Organization, 2025) Senevirathna D.H; Gunasekara W.M.M; Gunawardhana K.P.A.T; Ashra M.F.F; Fernando, H; Abeywardena, K. YOrganizations need a comprehensive threat profiling system that uses cybersecurity methods together with physical security methods because advanced cyber-threats have become more complex. The objective of this study is to implement deep learning models to boost organizational threat identification via human behavior assessment and continuous surveillance activities. Our method for human behavior analysis detects insider threats through assessments of user activities that include logon patterns along with device interactions and measurement of psychometric traits. CNN, together with Random Forest classifiers, has been utilized to identify behavioral patterns that indicate security threats from inside the organization. Our model uses labeled datasets of abnormal user behavior to properly differentiate between normal and dangerous user activities with high accuracy. The physical security component improves surveillance abilities through the use of MobileNetV2 for real-time anomaly detection in CCTV video data. The system receives training to detect security breaches and violent and unauthorized entry attempts, and specific security-related incidents. The combination of transfer learning and fine-tuning methodologies enables MobileNetV2 to deliver outstanding security anomaly detection alongside low power requirements, thus it fits into Security Operations Centers operations. Experiments using our framework operate on existing benchmark collection sets that assess cybersecurity, together with physical security threats. Experimental testing establishes high precision levels for detecting insider threats along with physical security violations by surpassing conventional rule-based methods. Security Operation Centers gain an effective modern threat profiling solution through the application of deep learning models. The investigation generates better organization defenses against cyber-physical threats using behavioral analytics together with intelligent surveillance systems.Publication Open Access Real Time Accident Detection and Emergency Response Using Drones, Machine Learning and LoRa Communication(Science and Information Organization, 2025) Bandara H.M.S.I.D; Maduhansa H.K.T.P; Jayasinghe S.S; Samararathna A.K.S.R; Fernando, H; Lokuliyana, SRoad accidents and delayed emergency responses remain a major concern in urban environments, contributing to over 1.4 million fatalities globally each year. With rapid urbanization and increasing vehicle density, timely detection and efficient traffic management are critical to reducing the impact of such events. This study proposes a real time Accident Detection and Emergency Response System with integrating Machine Learning IoT enabled drones and LoRa communication. The system combines real time accident detection using CCTV, drone assisted fire detection for post accident scenarios, crime activity monitoring and automated traffic management to reduce congestion and improve public safety. LoRa ensure long range, energy-efficient communication. ML models improve detection accuracy across accidents, fires, crimes and vehicles. Figures and sensor data are analyzed in real time to trigger alerts and assist emergency responders. The system supports scalable integration with existing urban infrastructure, promoting the development of smart city safety frameworks. By minimizing emergency response time, limiting secondary incidents and improving situational awareness, the proposed solution addresses critical gaps in current urban safety systems. It offers a practical, intelligent and adaptive approach to accident mitigation and traffic control in smart cities.Publication Open Access A Deep Learning-Based Dual-Model Framework for Real-Time Malware and Network Anomaly Detection with MITRE ATT&CK Integration(Science and Information Organization, 2025) Migara H.M.S; Sandakelum M.D.B; Maduranga D.B.W.N; Kumara D.D.K.C; Fernando, H; Abeywardena, KThe contemporary world of high connectivity in the digital realm has presented cybersecurity with more advanced threats, such as advanced malware and network attacks, which in most cases will not be detected using traditional detection tools. Static cybersecurity tools, which are traditional, often fail to deal with dynamic and hitherto unseen attacks, including signature-based antivirus systems and rule-based intrusion detection. To ad-dress this issue, we would suggest a two-part, AI-powered solution to cybersecurity which would allow real-time threat detection on an endpoint and a network level. The first element uses a Feedfor-ward Neural Network (FNN) to categorize Windows Portable Ex-ecutable (PE) files, whether they are benign or malicious, by using structured static features. The second component improves net-work anomaly detection with a deep learning model that is aug-mented by Generative Adversarial Networks (GAN) and effec-tively addresses the data imbalance issue and sensitivity to rare cyber-attacks. To enhance its performance further, the system is integrated with the MITRE ATT&CK adversarial tactics and techniques, which correlate real-time detection results with adver-sarial tactics and techniques, thus offering actionable context to incident response teams. Tests based on open-source datasets pro-vided accuracies of 98.0 per cent of malware detection and 96.2 per cent of network anomaly detection. Data augmentation using GAN was very effective in improving the detection of less popular attacks, including SQL injections and internal reconnaissance. Moreover, the system is horizontally scalable and responsive in real-time due to Docker-based deployment. The suggested frame-work is an effective, explainable and scalable cybersecurity de-fense system, which is perfectly applicable to Managed Security Service Providers (MSSPs) and Security Operations Centers (SOCs), greatly increasing the precision rate and contextual in-sight of threat detection. © (2025), (Science and Information Organization)Publication Open Access A novel application with explainable machine learning (SHAP and LIME) to predict soil N, P, and K nutrient content in cabbage cultivation(Elsevier B.V., 2025-03-06) Abekoon, T; Sajindra, H; Rathnayake, N; Ekanayake, I, U; Jayakody, A; Rathnayake, UCabbage (Brassica oleracea var. capitata) is commonly cultivated in high altitudes and features dense, tightly packed leaves. The Green Coronet variety is well-known for its robust growth and culinary versatility. Maximizing yield is crucial for food sustainability. It is essential to predict the soil’s major nutrients (nitrogen, phosphorus, and potassium) to maximize the yield. Artificial intelligence is widely used for non-linear predictions with explainability. This research assessed the predictive capabilities of soil nitrogen, phosphorus, and potassium levels with explainable machine learning methods over an 85-day cabbage growth period. Experiments were conducted on cabbage plants grown in central hills of Sri Lanka. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to clarify the model’s predictions. SHAP analysis showed that high feature values of the number of days and plant average leaf area negatively impacted for nutrient predictions, while high feature values of leaf count and plant height had a positive effect on the nutrient predictions. To validate the results, 15 greenhouse-grown cabbage plants at various growth stages were selected. The nitrogen, phosphorus, and potassium levels were measured and compared with the predicted values. These insights help refine predictive models and optimize agricultural practices. A user-friendly application was developed to improve the accessibility and interpretation of predictions. This tool is a user-friendly platform for end-users, enabling effective use of the model’s predictive capabilities.Publication Open Access Hybrid neural network methods to model the external wind pressure on a low-rise flat-roofed building in an irregularly shaped urban environment(Elsevier Ltd, 2025-06-23) Sajindra, H; Dharmawansha, S; Wijesundara, H; Herath, S; Rathnayake, U; Meddage D.P.PThe present study used hybrid artificial neural networks to model the wind pressure (mean and fluctuating) on a flat-roofed, low-rise building in an irregularly shaped urban environment. Four neural networks, each combined with an artificial bee colony (ABC), genetic algorithm (GA), particle swarm optimisation (PSO), and independent component analysis (ICA), along with an individual artificial neural network (ANN) model and a convolutional neural network (CNN), were used for the wind pressure predictions. The data was obtained from Tokyo Polytechnic University’s boundary layer wind tunnel and was used to train the neural network models. The results revealed that all models accurately captured the wind pressure on the low-rise building in a dense urban environment. Specifically, the genetic algorithm-artificial neural network (GA-ANN) model outperformed the remaining models, achieving good prediction accuracy for test data (coefficient of determination (R²) = 0.96 for mean pressure R² = 0.84 for fluctuation pressure). The use of machine learning explainability methods confirmed the consistency of GA-ANN with the fundamentals of wind engineering. Notably, the GA-ANN approach accurately modeled the special flow features on the building surface, such as flow separation, vortex formation, and pressure gradients, to a greater extent compared to the wind tunnel results. Therefore, the authors propose this method as an complementary approach for predicting wind pressure on low-rise buildings in complex urban environmentsPublication Embargo Assessing the Efficacy of Machine Learning Algorithms in Predicting Critical Properties of Gold Nanoparticles for Pharmaceutical Applications(Springer, 2025-07-08) Fernando, H; Mohottala, S; Jayanetti, M; Thambiliyagodage, CAu nanoparticles are increasingly used in pharmaceuticals, but their synthesis is costly and time-intensive. Machine Learning can help optimize this process. In this research, eight distinct Machine Learning models were implemented and optimized on a dataset comprising 3000 records of gold nanoparticles. The performance of these models was assessed using four accuracy metrics and the time required for training and inference. The results are promising, with all seven models demonstrating high accuracy and low time requirements. Notably, the XGBoost and Artificial Neural Network models exhibited exceptional performance, with Mean Squared Error values of 0.0235 and 0.0098, Mean Absolute Error values of 0.1021 and 0.0674, Mean Absolute Percentage Deviation values of 0.4945 and 0.3590, R2 scores of 0.9995 and 0.9998, and inference times of 0.0029 and 0.4299 s, respectively. The Explainable Artificial Intelligence analysis of the resulting models revealed some interesting insights into how the models make the predictions and what factors heavily contribute to the nanoparticle AVG_R, allowing chemists to optimize the synthesis for gold nanoparticles better. The key contributions of the research include the design and development of eight Machine Learning models using industry-standard frameworks, the training, tuning, and evaluation of these eight models using five different metrics, and further assessment of these trained models using Explainable Artificial Intelligence. The findings indicate a substantial potential for applying neural networks in the design phase of nanoparticle synthesis, which could lead to significant reductions in both the time and cost required for synthesizing Au nanoparticles for pharmaceutical applications.Publication Open Access Machine learning-based criminal behavior analysis for enhanced digital forensics(Public Library of Science, 2025-10-06) Dananjana, W. P; Arambawela, J. S; Gonawala, D.G. S. N; Rathnayaka, R.K. G.H; Senarathne, A. N; Siriwardena, S.M. D.NIn an increasingly digital world, uncovering criminal activity often relies on analyzing vast amounts of online behavior. Traditional methods in digital forensics struggle to keep up with the complexity and volume of data, particularly when trying to detect subtle deviations in online activity that could signal illegal intent. This research introduces an innovative approach that leverages machine learning to analyze internet activity—specifically browser artifacts—shedding new light on criminal behaviors that would otherwise remain hidden.Using advanced machine learning techniques such as Long Short-Term Memory (LSTM) networks and Autoencoders, this study focuses on detecting suspicious patterns and anomalies in browsing activity. By understanding the sequence and timing of a user’s online actions, this method enhances digital forensics investigations, allowing for faster and more accurate detection of criminal intent and behavior. The research aims to improve the speed and accuracy of identifying malicious online activity but also offers law enforcement and investigators a powerful tool to make sense of complex data. These findings represent an important step towards advancing digital forensics, enabling deeper insights into criminal behavior and more effective investigations, ultimately contributing to a safer digital environment.Publication Open Access Optimizing Asset Transfer Process in ERP Using Business Process Management Technique(Science and Information Organization, 2025-10-30) Yasarathne, R; Ranatunga, N; Herath, V; Chalinda, L; Kahandawaarachchi, C; Perera, S; Randula, CEnterprise Resource Planning (ERP) systems are critical for managing enterprise-wide business processes, including asset management. Yet, many ERP platforms lack efficient mechanisms for bulk asset transfers, leading to high manual effort, increased costs, and data inconsistencies. This study applies Business Process Reengineering (BPR) techniques as the methodology to optimize ERP asset management, focusing on workflow optimization and automation, contributing both practical and methodological insights. A mixed-method approach was adopted, analyzing a financial organization with 256 branches and over 450 Oracle ERP users. Data from 51 representative branches identified inefficiencies such as manual transfer delays, approval bottlenecks, and synchronization issues. The proposed solution introduces automated bulk asset transfers, optimized approval workflows, and real-time data synchronization, along with new metrics for evaluating efficiency, compliance, risk, and asset utilization. Compared to the As-Is system, the reengineered framework achieved a 100% reduction in operational costs per user ($7,500 annual saving), an 80% reduction in compliance incidents, a 67% reduction in asset transaction errors, and a 20% improvement in asset utilization. These results demonstrate a scalable, adaptable, and effective framework that enhances ERP operational efficiency, strengthens data integrity, and advances both academic understanding and industrial practice of asset management process reengineering.Publication Open Access A cost effective machine learning based network intrusion detection system using Raspberry Pi for real time analysis(PLOS ONE, 2025-12-29) Wijethilaka R.W.K.S; Yapa, K; Siriwardena, DIn an increasingly interconnected world, the security of sensitive data and critical operations is paramount. This study presents the development of a Network Intrusion Detection System (NIDS) that analyzes both inbound and outbound network traffic to detect and classify various cyber attacks. The research begins with an extensive review of existing intrusion detection techniques, highlighting the limitations of traditional methods when addressing the unique security challenges posed by distributed networks. To overcome these limitations, advanced machine learning algorithms, including Random Forest, Long Short Term Memory (LSTM) networks, Artificial Neural Networks (ANN), XGBoost, and Naive Bayes, are employed to create a robust and adaptive intrusion detection system. The practical implementation utilizes a Raspberry Pi as the central processing unit for real time traffic analysis, supported by hardware components such as Ethernet cables, LEDs, and buzzers for continuous monitoring and immediate threat response. A comprehensive alert system is developed, sending email notifications to administrators and activating physical indicators to signify detected threats. Our proposed NIDS achieves 96.5 detection accuracy on the NF-UQ-NIDS dataset, with a significantly reduced false positive rate after applying SMOTE. The system processes real time network traffic with an average response time of 50 milliseconds, outperforming traditional IDS solutions in accuracy and efficiency. Evaluation using the NF-UQ-NIDS dataset demonstrates a significant improvement in detection accuracy and response time, establishing the system as an effective tool for safeguarding networks against emerging cyber threats.Publication Embargo Evaluating the Success of Digital Learning in Sri Lankan Tertiary Education(IEEE, 2022-12-09) Weerapperuma, J; Nawinna, D; Gamage, NThis paper takes a social capital perspective to explain the underlying mechanisms that drive the success of digital learning in tertiary education in an emerging economy. It is crucial to explore ways in which the success of tertiary education can be maximized since these students will immediately contribute to the economy. Although digital-learning initiatives have advanced in developed countries, it is still in its early phases in many developing countries, including Sri Lanka. This study focuses on structural, relational, and cognitive dimensions of social capital and provides a new theoretical framework to examine its relationship to digital educational success. The study uses a quantitative approach where the data is collected from University students in Sri Lanka using a survey deployed online. The model is validated using the structural equation modeling technique. The findings of this study indicated that the three dimensions of social capital positively influence the success of digital education at the tertiary level. Further, this paper contributes to the existing literature on Social Capital Theory and provides valuable insights and recommendations for policymakers in the educational sector on improving digital learning achievements.