Browsing by Author "Fernando, H"

Now showing 1 - 11 of 11

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, K
The 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)
Embargo
A Dual-Branch CNN and Metadata Analysis Approach for Robust Image Tampering Detection
(Institute of Electrical and Electronics Engineers Inc., 2025) Zakey, A; Bawantha, D; Shehara, D; Hasara, N; Abeywardena, K.Y; Fernando, H
Image tampering has become a widespread issue due to the availability of advanced tools such as Photoshop, GIMP, and AI-powered technologies like Generative Adversarial Networks (GANs). These advancements have made it easier to create deceptive images, undermining their reliability and fueling misinformation. To address this growing problem, we propose a hybrid approach for image forgery detection, combining deep learning with traditional forensic techniques. Our study integrates a dual-branch Convolutional Neural Network (CNN) with handcrafted features derived from Error Level Analysis (ELA), noise residuals from the Spatial Rich Model, and metadata analysis to enhance detection capabilities. Metadata analysis plays a crucial role in identifying inconsistencies in image properties such as timestamps, geotags, and camera details, which often accompany tampered images. The CASIA dataset, a publicly available benchmark for tampered images, was used to train and evaluate the proposed model. After 30 epochs of training, the hybrid method achieved an accuracy of 95%, demonstrating its effectiveness in distinguishing between authentic and tampered images. This research highlights the advantages of combining deep learning models with traditional feature extraction methods and metadata analysis, offering a robust solution for detecting manipulated images. Our findings contribute to advancing image forensics by improving detection accuracy, even in cases involving sophisticated tampering methods driven by AI.
Embargo
Advancing Canine Health and Care: A Multifaceted Approach using Machine Learning
(IEEE, 2023-06-26) Wimukthi, Y; Kottegoda, H; Andaraweera, D; Palihena, P; Fernando, H; Kasthurirathnae, D
This research paper proposes a comprehensive approach to enhance the well-being of dogs through a range of innovative technologies. Firstly, we develop an automated system for dog breed and age identification using a Convolutional Neural Network (CNN) and a transfer learning model. This system aims to provide an efficient and reliable solution for dog owners and new adopters who are interested in discovering more about their canine companions. Secondly, we propose the development of a system that uses Reinforcement Learning to generate personalized meal plans based on a variety of factors such as the dog's breed, age, weight, health status, and emotional state. The system aims to provide dog owners with a reliable and effective tool for generating personalized meal plans that will enhance their pets' overall health and well-being. Thirdly, we present a dog disease recognition application that utilizes an artificial neural network (ANN) for identifying dog diseases based on their symptoms. Lastly, we introduce a real-time remote dog monitoring system using loT devices with edge computing to detect aggressive and anxious sounds. Our system provides an accurate classification of dog sounds related to aggression and anxiety, which can help dog owners detect and respond to potential issues early on. This research aims to provide dog owners and veterinarians with a range of technologies that can help them better understand and care for their furry friends.
Open Access
AI-Driven Adaptive Security for Sensor Networks: Next-Generation Firewalls for Attack Detection
(John Wiley and Sons, 2025-07-25) Meegammana, N.W; Fernando, H
Sensor networks are increasingly critical in modern smart environments; however, their limited computational resources expose them to sophisticated cyber threats. Traditional static firewalls and computationally intensive deep learning models are impractical for securing such networks. This study proposes an adaptive next-generation firewall (NGFW) that dynamically switches between shallow and deep AI models based on real-time network load and resource availability. Four neural network models were trained using 20 and 40-feature subsets of the UNSW-NB15 dataset. Two runtime strategies (i) on-demand model loading and (ii) preloaded model switching were developed and evaluated through simulation under real-time conditions. Experimental results indicate that the preloaded approach achieves up to 96% accuracy, 98% precision, and 4-ms inference latency, with a memory footprint of 19 MB, outperforming static AI firewalls in both efficiency and scalability. The proposed NGFW framework offers a resilient and scalable solution for real-time attack detection in resource-constrained environments without requiring frequent model retraining. Future enhancements include hybrid shallow–deep model architectures, continuous federated learning for decentralized adaptability, and the integration of explainable AI to enhance transparency and trustworthiness in edge security deployments.
Embargo
Assessing the Efficacy of Machine Learning Algorithms in Predicting Critical Properties of Gold Nanoparticles for Pharmaceutical Applications
(Springer Nature Link, 2025-07-08) Fernando, H; Mohottala, S; Jayanetti, M; Thambiliyagodage, C
Au 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.
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, C
Au 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.
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. Y
Organizations 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.
Embargo
Intelligent Detection of Corporate Targeted Phishing Emails - A Hybrid Approach Combining Deep Learning Models with Domain Anomaly Detection
(Institute of Electrical and Electronics Engineers Inc., 2025) Seethawaka, R; Chathurya N.E.G; Chandrasiri D.K.W.G.G.T; Kavithma K.A.S; Fernando, H; Wijesooriya, A
This paper introduces a system designed to detect corporate-targeted phishing emails by combining two key strategies: advanced email content analysis and domain similarity analysis. The system first examines the text of emails using a hybrid deep learning model that merges modern language understanding techniques with sequential pattern recognition, achieving high accuracy in identifying phishing intent. Two models were tested - a standalone Bi-LSTM sequential model and a hybrid version(BERT - Bi-LSTM) with the hybrid model proving superior, scoring an F1 score of 0.97 compared to 0.93 for the standalone model. Second, the system verifies sender domains to detect spoofing attempts, such as subtle typos, homograph attacks or TLD/subdomain spoofing. This domain check reduces reliance on text analysis alone, helping analysts prioritize threats more effectively. Tested against a mix of legitimate and malicious domains, the domain module achieved near-perfect accuracy, minimizing false alarms. By integrating these approaches, the system addresses a critical gap in existing methods, which often focus on only one aspect of phishing (e.g., email content or URL features). This dual strategy ensures a more comprehensive defense, particularly against sophisticated attacks that use convincing language paired with fake domains. The combined model not only improves detection accuracy but also supports security teams by providing clear, actionable insights, making it practical for real-world corporate environments.
Embargo
Precision Agriculture with Centralized IoT-Enabled Greenhouse Management for Sustainable Vanilla Production
(Institute of Electrical and Electronics Engineers Inc., 2025) Karunathilaka M.M.D.N; Samaraweera H.M.C.D; Balachandra B.A.D.K.M; Thenabandu W.S.D; Silva, S; Fernando, H
After saffron, vanilla is the second most significant spice in terms of economic impact worldwide. The vanilla business faces challenges from pests, illnesses, and environmental variables, especially fungal diseases like fusarium wilt and unfavorable climatic circumstances that can significantly reduce productivity and lower bean quality. This study offers a clever remedy that helps all parties involved by identifying and categorizing plant illnesses, predicting vanilla bean growth and quality, vanilla bean market value analysis and future prediction and build cost prediction and improve operational efficiency. Stakeholders can also obtain forecasts for the quality and growth of vanilla beans in the future. Deep learning algorithms are used in the suggested solution to track the location of diseased areas, diagnose and classify plant diseases in real-time, and apply pesticides or growth-regulating chemicals selectively. For sustainable vanilla production, machine learning algorithms are used to forecast yields, advise ideal greenhouse conditions, and recommend the best vanilla beans. In precision agriculture, the types, applications, and monitoring of IoT devices and sensors are also discussed. Data analysis and management, disease and pest control, fertilization and irrigation management, and environmental monitoring are a few examples. The suggested method produced high accuracy rates in identifying illnesses, evaluating bean quality, estimating yields, and optimizing greenhouse conditions in controlled studies using data from vanilla farms and greenhouses. This technology could assist the vanilla business, producers, and sustainable agricultural practices. It could also boost productivity and production of vanilla, decrease yield loss, and maintain constant bean quality with the help of our suggesting vanilla greenhouse application.
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, S
Road 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.
Open Access
A User-oriented Ensemble Method for Multi-Modal Emotion Recognition
(SLAAI - International Conference on Artificial Intelligence, 2019-12-12) Iddamalgoda, N; Thrimavithana, P; Fernando, H; Ratnayake, T; Priyadarshana, Y. H. P. P; Aththidiye, R; Kasthurirathna, D
Emotions play a vital role in mental and physical activities of human lives. One of the biggest challenges in Human-Computer Interaction is emotion recognition. With the resurgence in the fields of Artificial Intelligence and Machine learning, a considerable number of studies have been carried out in order to address the challenge of emotion recognition. The individual heterogeneity of expressing emotions is a key problem that needs to be addressed in accurately detecting the emotional state of an individual. The purpose of this work is to propose a novel ensemble method to predict the emotions using a multimodal approach. The presented multimodal approach with the modalities of facial expressions, voice variations and, speech and social media content, are used to identify seven emotional states: anger, fear, disgust, happiness, sadness, surprise and neutral emotion. In this study, for the facial expression-based emotion recognition and voice variation-based emotion recognition, Deep Neural Network models have been used, and for emotion recognition using speech and social media content, Multinomial Naïve Bayesian algorithm is used. The mentioned three modalities were integrated using a novel ensemble method that captures the heterogeneity of individuals in how they express their emotions. The proposed ensemble method was evaluated with respect to real states of human emotions of a sample user group and the experimental results suggest that the suggested ensemble method may be more accurate in recognizing emotions. Accurate recognition of emotions may have myriad applications in domains such as healthcare, advertising and human resource management.