Scholarly Articles

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4890

Browse

Filters

20264

Advanced Search

Filter by

Settings

Start date: 2023Subject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    PublicationEmbargo
    Investigation of inelastic response ratios for buildings with damping subjected to near-fault ground motions using numerical simulations and transformer-based models
    (Elsevier Ltd, 2026-03-09) Konara, L; Deshika, T; Gobirahavan, R; Alahakoon, Y; Ekanayake I.U; Meddage D.P.P
    Inelastic responses are used in seismic design to estimate inelastic seismic demand from known elastic demand, yet current provisions remain limited, especially when damping and displacement ductility are considered. This study investigated the inelastic displacement ratio and inelastic velocity ratio for single degree of freedom (SDOF) systems subjected to near-fault ground motions, with particular focus on the effects of fling-step and forward-directivity motions. For numerical modeling and analysis, an extensive nonlinear response history analysis (NLRHA) was conducted on SDOF systems incorporating parametric variations in dynamic characteristics of structural systems such as elastic period, displacement ductility, and viscous damping under different ground motion conditions. From numerical modeling, empirical equations are proposed to express the inelastic displacement ratio ((Formula presented) ) and inelastic velocity ratio ((Formula presented) ) using elastic period, viscous damping ratio, displacement ductility, and the type of ground motion. In parallel, neural networks are trained on a dataset of 36,456 samples using additional variables, including the predominant period of the ground motion, moment magnitude, and closest rupture distance. Neural network models achieved (Formula presented) (for (Formula presented) ) and (Formula presented) (for (Formula presented) ) for unseen data, indicating the highest accuracy. Model explanations indicated that the predictions adhere to the domain knowledge. Comparative assessments reveal that while empirical equations capture general trends for design purposes, neural network models accurately predict even minor variations in inelastic responses. These data-driven methods provide a complementary approach in predicting the inelastic response compared to empirical equations.
  • Thumbnail Image
    PublicationOpen 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, C
    The 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.
  • Thumbnail Image
    PublicationOpen 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, S
    Satellite 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 metrics
  • Thumbnail Image
    PublicationOpen Access
    Uncertainty Reduction in Near Real-time Satellite Precipitation Estimates by Integrating Soil Moisture and Potential Evapotranspiration Using a Machine Learning Approach
    (Springer Science and Business Media, 2026) Wanniarachchi, S; Sarukkalige, R; Hapuarachchi, H. A. P; Gomes, P.I.A; Rathnayake, U
    Near-real-time (NRT) satellite precipitation data inherits complex and random errors due to various reasons. The primary objective of this research is to utilize satellite-based precipitation data for hydrological modelling in ungauged areas. The novelty of this study lies in the development of a hybrid stacking-based machine learning framework that integrates hydrologically meaningful predictors: root-zone soil moisture, potential evapotranspiration (PET), and their time-lagged representations to reduce uncertainty in near-real-time satellite precipitation (GSMaP-NRT). Unlike conventional bias-correction approaches that rely primarily on statistical adjustment between satellite and gauge rainfall, this study incorporates physically relevant catchment-state variables to improve predictive skill, with a focus on the Ovens River basin in Australia. A calibrated GR4H hydrological model was used to simulate the runoff of the catchment. Six objective functions were used to evaluate the performance of the approach. The results demonstrate that stacking machine learning algorithms reduces the Mean Absolute Error of GSMaP-NRT satellite precipitation data by 36% and the corresponding modelled streamflow error by 44% for lower precipitation events (< 2 mm/hour). All six objective functions achieved optimal performances within the low precipitation events. However, RMSE remained high for intermediate and heavy precipitation events. The model-estimated major streamflow peaks for the years 2010 and 2016, based on gauged precipitation and ML-corrected satellite precipitation, are 41% and 48% lower than the observed streamflow peaks, respectively. The reasons were the inability of the GR4H model to capture the perfect initial conditions and the x4 time parameter during the calibration process.