Faculty of Computing Scopus 2
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4896
Browse
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 Open Access A physics-informed machine learning for detecting suspicious satellite maneuvers (orbital manipulation)(Elsevier B.V., 2026) Karunathilake K.K.H; Abeywardena, K.Y; Vecchini, SSatellite systems have become prime targets for cyberthreats given their critical role in global infrastructure and general lack of security. Among these, orbital manipulation, a form of satellite hijacking, is a particularly severe threat that can disrupt essential operations and impact national security. To address these concerns, this research proposes an Artificial Intelligence (AI)-based anomaly detection system that utilizes Machine Learning (ML) models to analyze telemetry data for possible orbital manipulations with a multi-gate physics architecture grounded in orbital mechanics, to verify that detected anomalies are kinematically inconsistent and are therefore genuine integrity failures. This research demonstrates that temporal-based models like LSTM are essential for this domain, achieving high recall rates which are then validated by the physics component. While the framework includes multiple physical constraints, this study specifically validates the energy-based Vis-Viva gate, with the Tsiolkovsky and Angular Momentum gates established as architectural designs for future verification. This study concludes that successful AI deployment in orbital cybersecurity requires a comprehensive approach that integrates domain-specific context and physics-informed validation beyond traditional performance metricsItem Embargo Adaptive Video Game Content Generation through Player Centered Modeling(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Hapuarachchi H.A.R.S; Herath H.M.N.R; Kaveesha B.G.S; Deheragoda D.M.L.M; Rathnayake, S; Chamara, DThis research introduces a novel, integrated AI system for Adaptive Video Game Content Generation Through Player Centered Modeling, designed to overcome the limitations of conventional static game mechanics by dynamically modifying gameplay elements (levels, quests, music, and enemy behavior) in real-time based on player biometric and behavioral data. Key contributions include the Personalized Quest Generation System, where the CatBoost model performed well in predicting player engagement, and shifting to the YOLO11X-CLS classification model substantially reduced computational lag for real-time emotional adaptation. For Level Generation, the implementation of a bootstrapping methodology during DCGAN training enabled continued refinement, resulting in lower Symmetry Error and Block Diversity Error, while the Intelligent Enemy Agent, trained using Dueling DQN, demonstrated a clear upward trend in Mean Rewards, successfully generalizing learned pursuit strategies to a real-time environment. Despite these successes, limitations include potential mild overfitting in the emotion recognition model, evidenced by a slight increase in validation loss after 20 epochs, and the CNN used for dynamic music adjustment struggled with low-resolution webcam inputs, leading to occasional minor misclassifications and slight delays in music transitions when multiple biometric parameters changed simultaneously.Publication 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, HSensor 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.Publication Open Access Blockchain–AI–Geolocation Integrated Architecture for Mobile Identity and OTP Verification(Multidisciplinary Digital Publishing Institute (MDPI), 2025-11-23) SULOCHANA, G. G. D.; De Silva, D.IOne-Time Passwords (OTPs) are a core component of multi-factor authentication in banking, e-commerce, and digital platforms. However, conventional delivery channels such as SMS and email are increasingly vulnerable to SIM-swap fraud, phishing, spoofing, and session hijacking. This study proposes an end-to-end mobile authentication architecture that integrates a permissioned Hyperledger Fabric blockchain for tamper-evident identity management, an AI-driven risk engine for behavioral and SIM-swap anomaly detection, Zero-Knowledge Proofs (ZKPs) for privacy-preserving verification, and geolocation-bound OTP validation for contextual assurance. Hyperledger Fabric is selected for its permissioned governance, configurable endorsement policies, and deterministic chaincode execution, which together support regulatory compliance and high throughput without the overhead of cryptocurrency. The system is implemented as a set of modular microservices that combine encrypted off-chain storage with on-chain hash references and smart-contract–enforced policies for geofencing and privacy protection. Experimental results show sub-0.5 s total verification latency (including ZKP overhead), approximately 850 transactions per second throughput under an OR-endorsement policy, and an F1-score of 0.88 for SIM-swap detection. Collectively, these findings demonstrate a scalable, privacy-centric, and interoperable solution that strengthens OTP-based authentication while preserving user confidentiality, operational transparency, and regulatory compliance across mobile network operators.Publication Open Access Bridging Language Barriers in Programming Education: Java Programming Assistance Tool for Sinhala Native Speakers(International Association of Computer Science and Information Technology, 2025-09-12) Athukorala, K. S.N; De Silva, D.IThis study presents an innovative programming assistance tool designed to address language barriers faced by Sinhala-speaking novice Java programmers. The tool provides real-time Java code generation and diagram creation based on Sinhala programming queries, enhancing conceptual understanding. Developed using a Design-Based Research methodology, the tool underwent iterative testing with 122 Sinhala-speaking learners, incorporating user feedback to refine usability and performance. Central to the system is Generative Pre-trained Transformer, version 3.5 Turbo, ensuring accurate translations and programming assistance, alongside a transformer-based model that translates Sinhala queries into English for processing. The translation model achieved 91.37% accuracy, with strong Bilingual Evaluation Understudy scores validating its contextual relevance. The tool’s practical applications extend beyond academia, supporting educational institutions, self-learners, and industry professionals in learning and skill development. Statistical evaluation of user performance demonstrated significant improvements in programming comprehension, reinforcing its effectiveness. By promoting inclusivity and expanding access to programming knowledge, this research contributes to the advancement of Sri Lanka’s technology sector and establishes a scalable framework for broader implementation in multilingual programming education. CopyrightPublication Open Access Comparison of cardiovascular risk prediction models developed using machine learning based on data from a Sri Lankan cohort with World Health Organization risk charts for predicting cardiovascular risk among Sri Lankans: A cohort study(BMJ Publishing Group, 2025-01-15) Mettananda, C; Solangaarachchige, M; Haddela, P; Dassanayake, A.S; Kasturiratne, A; Wickremasinghe, R; Kato, N; De Silva, H.JIntroduction Models derived from non-Sri Lankan cohorts are used for cardiovascular (CV) risk stratification of Sri Lankans. Objective To develop a CV risk prediction model using machine learning (ML) based on data from a Sri Lankan cohort followed up for 10 years, and to compare the predictions with WHO risk charts. Design Cohort study. Setting The Ragama Health Study (RHS), an ongoing, prospective, population-based cohort study of patients randomly selected from the Ragama Medical Office of Heath area, Sri Lanka, focusing on the epidemiology of non-communicable diseases, was used to develop the model. The external validation cohort included patients admitted to Colombo North Teaching Hospital (CNTH), a tertiary care hospital in Sri Lanka, from January 2019 through August 2020. Participants All RHS participants, aged 40-64 years in 2007, without cardiovascular disease (CVD) at baseline, who had complete data of 10-year outcome by 2017, were used for model development. Patients aged 40-74 years admitted to CNTH during the study period with incident CV events or a disease other than an acute CV event (CVE) with complete data for CVD risk calculation were used for external validation of the model. Methods Using the follow-up data of the cohort, we developed two ML models for predicting 10-year CV risk using six conventional CV risk variables (age, gender, smoking status, systolic blood pressure, history of diabetes, and total cholesterol level) and all available variables (n=75). The ML models were derived using classification algorithms of the supervised learning technique. We compared the predictive performance of our ML models with WHO risk charts (2019, Southeast Asia) using area under the receiver operating characteristic curves (AUC-ROC) and calibration plots. We validated the 6-variable model in an external hospital-based cohort. Results Of the 2596 participants in the baseline cohort, 179 incident CVEs were observed over 10 years. WHO risk charts predicted only 10 CVEs (AUC-ROC: 0.51, 95% CI 0.42 to 0.60), while the new 6-variable ML model predicted 125 CVEs (AUC-ROC: 0.72, 95% CI 0.66 to 0.78) and the 75-variable ML model predicted 124 CVEs (AUC-ROC: 0.74, 95% CI 0.68 to 0.80). Calibration results (Hosmer-Lemeshow test) for the 6-variable ML model and the WHO risk charts were χ 2 =12.85 (p=0.12) and χ 2 =15.58 (p=0.05), respectively. In the external validation cohort, the sensitivity, specificity, positive predictive value, negative predictive value, and calibration of the 6-variable ML model and the WHO risk charts, respectively, were: 70.3%, 94.9%, 87.3%, 86.6%, χ 2 =8.22, p=0.41 and 23.7%, 79.0%, 35.8%, 67.7%, χ 2 =81.94, p<0.0001. Conclusions ML-based models derived from a cohort of Sri Lankans improved the overall accuracy of CV-risk prediction compared with the WHO risk charts for this cohort of Southeast Asians.Publication Embargo Data-centric single teacher guided knowledge distillation for alleviating sub-optimal supervision in image classification(Elsevier Ltd, 2026-02-23) Sharma, K; Silva, B. NIn recent years, larger, deeper, and more complex deep learning models have emerged as a result of advancements in deep learning techniques. Nevertheless, the computational costs have also increased with the growing model size. Thus, Knowledge Distillation has evolved into a cornerstone in contemporary machine learning, facilitating the transfer of knowledge from cumbersome teacher models to more compact student models. However, student learning is persistently challenged by sub-optimal supervision caused by erroneous and ambiguous teacher predictions. Moreover, the learning process is further deteriorated by the complications introduced through frequently encountered noisy labels in real-world datasets. Existing methods often resort to the ensemble of teachers, introducing additional complexity. We propose a novel, simple, and efficient learning method, Corrective Knowledge Distillation (CKD), to alleviate these drawbacks while relying solely on a single-teacher model. The proposed work employs a two-phase learning paradigm. In the initial phase, the teacher selectively teaches extremely confident knowledge to the student, and in the subsequent phase, the student leverages its own past learning experiences, conditioning its knowledge acquisition on the guidance of the teacher. The proposed method consistently exhibits superior performance in addressing sub-optimal supervision, as evidenced by comprehensive experiments on benchmark datasets such as CIFAR-100, CIFAR-100N-Fine, and ImageNet-1K. Notably, CKD surpasses established baselines, achieving substantial accuracy gains of up to 3.53% in real-world scenarios. Furthermore, CKD exhibits exceptional robustness in highly noisy environments, outperforming ensemble techniques by a significant margin of up to 5.18%. Our code is available at https://github.com/Karthick47v2/ckd.Publication Embargo Deep Q-Network-Based Path Planning in a Simulated Warehouse Environment with SLAM Map Integration and Dynamic Obstacles(Department of Agribusiness, Universitas Muhammadiyah Yogyakarta, 2025-09-19) Medagangoda, H; Jayawickrama, N; de Silva, R; Samantha K.R.U.U; Abeygunawardhana, P.K.WWith the rise of e-Commerce and the evolution of robotic technologies, the focus on autonomous navigation within warehouse environments has increased. This study presents a simulation-based framework for path planning using Deep Q-Networks (DQN) in a warehouse environment modeled with moving obstacles. The proposed solution integrates a prebuilt map of the environment generated using Simultaneous Localization and Mapping (SLAM), which provides prior spatial knowledge of static obstacles. The reinforcement learning model is formulated with a state space derived from grayscale images that combine the static map generated by SLAM and dynamic obstacles in real time. The action space consists of four discrete movements for the agent. A reward shaping strategy includes a distance-based reward and penalty for collisions to encourage goal-reaching and discourage collisions. An epsilon-greedy policy with exponential decay is used to balance exploration and exploitation. This system was implemented in the Robot Operating System (ROS) and Gazebo simulation environment. The agent was trained over 1000 episodes and metrics such as the number of actions executed to reach the goal and the cumulative reward per episode were analyzed to evaluate the convergence of the proposed solution. The results across two goal locations show that incorporating the SLAM map enhances learning stability, with the agent reaching a goal approximately 150 times, nearly double the success rate compared to the baseline without map information, which achieved only 80 successful episodes over the same number of episodes. This indicates faster convergence and reduced exploration overhead due to improved spatial awareness.Publication Embargo Eco-friendly bismuth halide chalcogenide perovskites for solar energy harvesting(Royal Society of Chemistry, 2025-03-04) Don Muditha Akmal, U. K; Hu, D; Wijesekara Abeygunawardhana, P.K; Sewvandi, G. AThe quest to eliminate lead (Pb) content in perovskite photovoltaic materials has significantly shifted focus towards identifying viable Pb-free alternatives. This study provides a comprehensive theoretical investigation of CH3NH3BiI2Se and CH3NH3BiI2S as Pb alternative candidates. Density Functional Theory (DFT) calculations and the solar cell capacitance simulator (SCAPS) were used. The DFT analysis reveals that both CH3NH3BiI2Se and CH3NH3BiI2S possess indirect band gaps of 1.35 eV and 1.39 eV, respectively. CH3NH3BiI2Se demonstrates a higher absorption coefficient, stronger absorption in the UV-visible regions, a broader absorption spectrum and better charge carrier mobilities compared to CH3NH3BiI2S. CH3NH3BiI2Se and CH3NH3BiI2S based solar cells which show 24.06% and 21.85% power conversion efficiencies (PCEs), respectively. This study emphasizes the potential of CH3NH3BiI2Se as a promising bismuth mixed halide chalcogenide compound for the development of sustainable perovskite solar cells. The findings provide a foundation for the guided design of novel bismuth chalcogenide compounds for optoelectronic applications and experimental studies.Publication Open Access Enhancing blockchain technology adoption in governmental operations: A comprehensive framework for user adoption(PloS one, 2026-07-06) Gnanasekara, A; Jayakody, A; Perera, KThe purpose of this study is to investigate the factors that affect Blockchain adoption in governmental operations in Sri Lanka and to propose a comprehensive adoption framework for Blockchain technology in the Sri Lankan governmental operations. The Technology- Organization-Environment (TOE) framework is utilized due to its capacity to capture the complexities of technological adoption in the public sector, addressing both internal (organizational) and external (environmental) factors that influence the adoption process. Given the structural, regulatory, and data sensitivity challenges of governmental settings, the TOE framework integrates employee insights from technological, organizational, and environmental perspectives, making it adaptable to the public sector's needs and scalable across various government entities. It also reflects the regulatory and operational requirements specific to the Sri Lankan public institutions, including essential compliance areas such as data privacy, security regulations, and government workflows, thereby offering a practical pathway for Blockchain adoption within the local context. This study employed statistical methods to ensure the validity and reliability of data collected through a structured questionnaire distributed to Grade I-IT Directors to capture their perceptions and experiences with Blockchain technology. Using the structural equation modelling (SEM), the study finds that all the technological, organizational, and environmental dimensions of the TOE framework are significantly associated with intention to adopt Blockchain technology in the Sri Lankan governmental operations. At a more specific level, trust, compatibility, security, higher authority support, monetary resources, rivalry pressure, and regulatory support were identified as significant predictors of adoption intention, while relative advantage, IT resources, and business partner pressure were not statistically significant, and firm size showed only weak support. These findings provide an empirically grounded framework for understanding Blockchain adoption intention in the Sri Lankan public sector and offer implications for future policy and implementation planning.Item Open Access Enhancing Cognitive and Metacognitive Domains of Autistic Children Using Machine Learning(Multidisciplinary Digital Publishing Institute (MDPI), 2025-08-21) Tharaki, D; Rupasinghe, Y; Ruhunage, P; Pehesarani, A; Rathnayake, S.CASD poses special difficulty in both cognitive and metacognitive development, necessitating specialized educational strategies. This research proposes LearnMate, a web-based application powered by machine learning techniques that aims to improve the abilities of children with autism. Utilizing classification models learned from medical data, LearnMate forecasts skill acquisition and suggests personalized learning activities according to the strengths and developmental requirements of the child. The system permits instructors to monitor progress through real-time feedback, enabling adaptive learning approaches. Pilot application to more than 100 children showed significant gains in their skills. The results demonstrate the immense potential for change through machine learning in special education to facilitate data-driven, personalized learning opportunities that enhance the capabilities of both autistic students and teachers.Publication Open Access EuqAud: Detecting Gender Bias in Audio Datasets Using Polynomial Regression-Based Metric(Institute of Electrical and Electronics Engineers Inc., 2026) Jayawardena, S; Haddela, P.S; Shyamalee, T; Ekanayake, A; Mudalige, T; Dhanawardhana, IWith the growing adoption of audio based AI systems in high-stakes domains such as healthcare, law enforcement, and social media, ensuring fairness particularly regarding gender bias has become critically important. While prior work on fairness has predominantly focused on disparities in model performance, bias inherent in training datasets remains underexplored. To address this gap, we propose EuqAud, a novel, pre-trained and traceable fairness metric that quantifies gender bias in audio datasets using raw acoustic features such as pitch, energy, amplitude, and voice activity. Unlike methods dependent on demographic labels such as race, age or language, EuqAud is designed to be demographic and language agnostic, enhancing its applicability across diverse contexts. The score is computed using an equation derived from polynomial regression with L2 regularization (Ridge regression), yielding robust and generalizable outputs. It spans a range from −10 to 10, where 0 denotes neutral, positive scores indicate male dominant bias, and negative scores reflect female dominant bias. For clarity, bias severity is categorized into three tiers: Neutral (EuqAud < 2), Moderate Bias (2 ≤ EuqAud ≤ 6), and Strong Bias (EuqAud > 6). Evaluation across multiple datasets demonstrates high predictive performance, with R2 values between 0.95 and 0.99. By focusing on dataset level bias rather than model outcomes, EuqAud offers a scalable and rigorous solution for advancing fairness in audio-based AI systems.Publication Open Access Evaluating the impact of Large Language Models on problem-solving skills in programming debugging of IT undergraduates(Taylor and Francis Ltd., 2026) Riztha, F; Wickramarachchi, R; Asanka, P P G D; Dissanayake, M. AThis study investigates the impact of Large Language Models (LLMs) on problem-solving skills in source code debugging among IT undergraduates. A pre-, mid-, and post-experimental design was employed, including pre-test, mid-test, post-test (Prior), and post-test (Recent) phases to assess debugging performance with and without LLM assistance. The sample consisted of 87 students from the Department of Industrial Management, University of Kelaniya, Sri Lanka, stratified by gender, academic level, A/L stream, Z-score, and GPA. Results showed significant improvement in debugging accuracy, increasing from 46.53% in the pre-test to 69.51% in the post-test (Prior), indicating skill retention. Task efficiency also improved, with completion time reduced from 18 minutes to 10 minutes. However, transferability to new problems was moderate, with a post-test (Recent) accuracy of 58.40%. Higher academic levels, technical A/L streams, and mid-range GPAs were associated with better retention and adaptability. While LLMs enhanced immediate performance, the findings highlight the need to balance their use with independent practice to support long-term skill development. Limitations include resource constraints and short study duration, suggesting the need for longitudinal research. The study recommends structured integration of LLMs to optimize programming education outcomes.Item Open Access Exploring emergent topological properties in socio-economic networks through learning heterogeneity(2025-12-10) Karavita, C; Lyu, Z; Kasthurirathna, D; Piraveenan, MUnderstanding how individual learning behavior and structural dynamics interact is essential to modeling emergent phenomena in socio-economic networks. While bounded rationality and network adaptation have been widely studied, the role of heterogeneous learning rates–both at the agent and network levels–remains underexplored. This paper introduces a dual-learning framework that integrates individualized learning rates for agents and a rewiring rate for the network, reflecting real-world cognitive diversity and structural adaptability. Using a simulation model based on the Prisoner’s Dilemma and Quantal Response Equilibrium, we analyze how variations in these learning rates affect the emergence of large-scale network structures. Results show that lower and more homogeneously distributed learning rates promote scale-free networks, while higher or more heterogeneously distributed learning rates lead to the emergence of core-periphery topologies. Key topological metrics–including scale-free exponents, Estrada heterogeneity, and assortativity–reveal that both the speed and variability of learning critically shape system rationality and network architecture. This work provides a unified framework for examining how individual learnability and structural adaptability drive the formation of socio-economic networks with diverse topologies, offering new insights into adaptive behavior, systemic organization, and resilience.Publication Open Access Exploring nontoxic perovskite materials for perovskite solar cells using machine learning(Discover, 2025-07-06) Pabasara W.G.A; Wijerathne H.A.H.M; Karunarathne M.G.M.M.; Sandaru D.M.C; Abeygunawardhana, Pradeep K. W; Sewvandi, GPerovskite solar cells are promising renewable energy technology that faces significant challenges due to the Pb induced toxicity. The current study addresses this issue by leveraging machine learning techniques to explore Pb-free perovskite materials that ensure environmental sustainability and human safety. A highly accurate machine learning model was developed to predict Goldschmidt factor and the band gap, aiming to discover lead-free perovskites. Extreme Gradient Boost (XGBoost), Random Forest (RF), Gradient Boost Regression (GBR), and Ada Boost Regression (ABR) models were employed for this purpose. The findings exhibit that XGBoost delivers the most precise and reliable results for Goldsmith tolerance factor prediction with an accuracy of 98.5%. Furthermore, GBR model, combined with K-nearest neighbors (KNN) model delivers an impressive accuracy of 98.7% for the band gap predictions. 49 Pb-free perovskite materials were screened out considering the toxicity and the abundance. Utilizing Principal Component Analysis (PCA) and K-means clustering, six optimal materials (KBiBr3, KZnBr3, RbBiBr 3, RbZnBr3, MAGeI3, and FAGeI3null) were identified as the potential environment-friendly materials for photovoltaic applications. These results show the crucial role of machine learning and statistical analysis in discovering nontoxic and environmental-friendly perovskite materials, advancing the development of sustainable energy solutionsPublication Embargo High-resolution optical imaging for sustainable fish freshness and safety assessment(Elsevier GmbH, 2026-04) Madhubhashini, M. N; Kahandawala, B.S; Sandaruwan, H.H.P. B; Silva, B.N; Wijenayake, U; Wijesinghe, R.EFish freshness evaluation is crucial to ensure consumer safety, and rapid assessment is essential for effective and accurate quality control. To overcome the limitations of the gold standards, such as lack of structural depth information, high-time consumption, and labor-intensiveness, high-resolution Optical Coherence Tomography (OCT) was employed for real-time monitoring of fish freshness non-invasively. Microstructural changes of eye and skin of Indian Anchovies ( Stolephorus indicus ) specimens were considered as the main freshness parameters during refrigeration storage. Both eye and skin tissues exhibited decreased internal scattering, loss of clarity, boundary weakening, and gradual structural degradations through the OCT observations. The quantitatively assessed variance intensity, entropy, energy, and edge density clearly revealed the internal tissue disruption over storage time due to protein denaturation, oxidative damage, and fluid imbalance. The findings of this study indicate that OCT shows an insightful correlation with microbiological and biochemical spoilage processes, enabling the advanced identification of subtle microstructural changes in fish skin and eye, even at a prior stage of deterioration. Such capability offers an objective and rapid freshness evaluation approach that could greatly benefit supply chain management and post-harvest seafood quality monitoring.Item Embargo Human-Ai Cooperative Driving Through Emotion-Aware Decision Making and Driver Personalization(Institute of Electrical and Electronics Engineers, 2025-12-09) Wickramasuriya L.H.N.Y; Rathnayaka D.B; Walpalage J.V.; Rathnayake, SConventional in-vehicle safety systems often neglect real-time emotional monitoring, prediction, and passenger influence, leading to reactive rather than proactive interventions. This paper presents an emotion-aware cooperative driving system that combines facial emotion recognition, time-series emotion forecasting, and personalized music-based regulation. The system detects both driver and front-seat passenger emotions through a Vision Transformer (ViT) model, while a time-series model anticipates the driver's upcoming emotional state. A prioritization algorithm ensures driver emotions hold precedence, with passenger states considered when the driver is stable. Based on this prioritized emotional context, the system regulates the in-cabin atmosphere using music recommendations drawn from the driver's preferred artists via the Spotify API. Experimental results show robust real-time emotion classification (86.4% validation accuracy), proactive forecasting (81.6% predictive accuracy), and improved driver acceptance due to personalization. The proposed framework advances intelligent transportation by shifting from static monitoring toward predictive, human-centered, and non-intrusive emotional regulation, thereby enhancing both safety and user comfort.Publication Open Access Hybrid ABC–HBA feature optimization with self-training using simulated unlabelled data for robust intrusion detection(Elsevier Ltd, 2026) Harischandra, S; Rajapaksha, U.U. S; Silva, B.N; Jayawardena, CThe increasing scale and heterogeneity of network traffic pose significant challenges for intrusion detection systems (IDS), particularly in detecting extremely rare attack classes and generalising to previously unseen threats under severe class imbalance. This study proposes a hybrid intrusion detection framework that integrates swarm intelligence–based feature optimisation with self-training using unlabelled data simulation to address these limitations. A novel ABC–HBA feature selection strategy is introduced, combining the efficient exploration capability of the Artificial Bee Colony (ABC) algorithm with the strong global exploitation and fast convergence of the Honey Badger Algorithm (HBA), resulting in a highly discriminative and compact feature subset. A Random Forest(RF) classifier augmented with a pseudo-labelling mechanism is then employed to enhance learning from unlabelled and unseen attack samples, enabling effective detection of novel attack patterns absent from the training set. To further mitigate extreme class imbalance, a hybrid resampling strategy is applied. Experimental evaluation on the KDD Cup 1999 dataset demonstrates that the proposed framework achieves an overall accuracy of 99.95% and a detection rate of 98.16%, while significantly improving the recognition of extremely rare attack classes, including a 92.86% detection rate for U2R attacks, which constitute less than 0.01% of the dataset. The proposed method consistently outperforms baseline RF, ABC-based, and several other state-of-the-art meta-heuristic and deep learning approaches, confirming its effectiveness in enhancing rare attack detection and generalisation to unseen threats in realistic intrusion detection scenarios.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 environments