Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 4 of 4 for “"Domain-Constrained"”.

  1. Domain-Constrained Adversarial Attacks on Time Series Data and Defences

    … to many critical applications across various domains, including finance, healthcare, manufacturing, and smart infrastructure. As machine learning models become the backbone of forecasting, anomaly detection, and classification in these systems, their vulnerability to adversarial perturbations …

    unsw Repository record for Domain-Constrained Adversarial Attacks on Time Series Data and Defences (opens in a new tab)

  2. Domain-Constrained Clustering: A Two-Stage Framework for Muscle Fiber Type Identification

    … intensity data. The study identified the constrained Linear Grouping Algorithm (cLGA), which we developed by modifying the original Linear Grouping Algorithm (LGA) by adding domain-specific angular constraints, as outperforming other methods, particularly in noisy scenarios with …

    ucf Repository record for Domain-Constrained Clustering: A Two-Stage Framework for Muscle Fiber Type Identification (opens in a new tab)

  3. Algorithm and architecture for simultaneous diagonalization of matrices applied to subspace-based speech enhancement

    … analysis technique for subspace-based time-domain constrained speech enhancement technique is proposed. The proposed technique analyses the signal in its subbands to build accurate estimates of the covariance matrices of speech and noise, exploiting the inherent low varying characteristics …

    concordia Download PDF for Algorithm and architecture for simultaneous diagonalization of matrices applied to subspace-based speech enhancement (opens in a new tab)

  4. Deployment-Aware Hybrid and Neuromorphic Learning for Intelligent Infrastructure Inspection

    … short-range spatiotemporal modelling, and domain-constrained synthetic augmentation. The hybrid framework addresses severe class imbalance, limited unsafe examples, and operational variability, achieving 93.6% overall accuracy and improved sensitivity to unsafe pin states. To address …

    auckland-tech Repository record for Deployment-Aware Hybrid and Neuromorphic Learning for Intelligent Infrastructure Inspection (opens in a new tab) Embargoed until 2029-11-16