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 20 of 85 for “"Adaptation method"”.

  1. Climate adaptation method for resilience of coastal communities over long time horizons

    … addresses this gap by proposing a quantitative methodology to evaluate community resilience over extended time horizons under a changing climate. Long-term resilience to hurricane-induced multi-hazards is assessed through population outmigration, which serves as an indicator of community …

    colostate Repository record for Climate adaptation method for resilience of coastal communities over long time horizons (opens in a new tab) Embargoed until 2027-06-05

  2. Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation

    We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling …

    uiuc Repository record for Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation (opens in a new tab)

  3. Comparison of two methods for two dimensional unstructured mesh adaptation with elliptic smoothing

    A new mesh adaptation method for unstructured grids is presented. The technique uses virtual control volumes that are iteratively manipulated to conform the mesh to match either a Riemannianmetric tensor field or an equal distribution of scalar weights. Forcing functions similar to those used for …

    utc Repository record for Comparison of two methods for two dimensional unstructured mesh adaptation with elliptic smoothing (opens in a new tab)

  4. DEVELOPMENT OF DEEP LEARNING METHODS FOR PROGNOSTICS AND HEALTH MANAGEMENT

    … we first develop a new fault diagnosis method generalizing convolutional neural network to transfer learning scenario. To reduce domain discrepancy caused by different working conditions, multi-layer adaptation based on multiple kernels is used. Owing to the availability of multiple …

    nus Repository record for DEVELOPMENT OF DEEP LEARNING METHODS FOR PROGNOSTICS AND HEALTH MANAGEMENT (opens in a new tab) Download file for DEVELOPMENT OF DEEP LEARNING METHODS FOR PROGNOSTICS AND HEALTH MANAGEMENT (opens in a new tab)

  5. Enabling Transfer Learning Across Heterogeneous Domains Using Input Alignment

    … We propose a few-shot-learning-based test-time adaptation method for Neural Network (NN)s to address this gap. The proposed approach aligns target features using a fully-connected NN to leverage existing knowledge from a pre-trained source model, and then stacking the results from the source …

    texas-state Repository record for Enabling Transfer Learning Across Heterogeneous Domains Using Input Alignment (opens in a new tab)

  6. Analysis of Ventricular Depolarisation and Repolarisation Using Registration and Machine Learning

    … a laborious task. Hence, automated and accurate methods are required to extract markers for the study of ventricular lability and detection of common diseases, such as myocardial ischemia and myocardial infarction. The aim of this thesis is to improve automated marker extraction and detection of …

    adelaide Repository record for Analysis of Ventricular Depolarisation and Repolarisation Using Registration and Machine Learning (opens in a new tab)

  7. Anisotropic Residual-Based Mesh Adaptation for Reaction-Diffusion Systems: Applications to Cardiac Electrophysiology

    … they represent. The development of efficient methods is crucial to cut down the demands of computational resources. In this thesis we consider the use of adaptive space and time methods driven by a posteriori error estimation. The error estimators for the spatial discretization are built from …

    ottawa-retro Repository record for Anisotropic Residual-Based Mesh Adaptation for Reaction-Diffusion Systems: Applications to Cardiac Electrophysiology (opens in a new tab)

  8. Vibration Suppression Using Smart Materials in the Presence of Temperature Changes

    … board. This research develops two different adaptation methods to perform vibration suppression in the presence of thermally induced frequency changes of the representative panel. To adjust the PPF filter parameters an open-loop adaptation method and an auto-tuning method are investigated. …

    vt Repository record for Vibration Suppression Using Smart Materials in the Presence of Temperature Changes (opens in a new tab)

  9. Handling Concept Drift Using the Correlation between Multiple Data Streams

    … Motivated by this, this research proposes four methods to deal with the correlations between data streams. A concept drift adaptation method is firstly proposed to overcome the insufficient training problem caused by scarce newly arrived data. By introducing correlation between multiple data …

    uts Repository record for Handling Concept Drift Using the Correlation between Multiple Data Streams (opens in a new tab)

  10. Tradução e adaptação transcultural do módulo Acute Care do Programa E-learning do National Early Warning Score 2 para o português brasileiro

    … 2 e-learning program to Brazilian Portuguese. Method: Methodological study of cross-cultural adaptation, authorized by the Royal College of Physicians. Judges from the five regions of Brazil, nurses, assess the semantic, idiomatic, cultural and conceptual equivalences between the original …

    brazil-ufrn Repository record for Tradução e adaptação transcultural do módulo Acute Care do Programa E-learning do National Early Warning Score 2 para o português brasileiro (opens in a new tab)

  11. Using deep learning on histology to inform colorectal cancer patient treatment

    … prediction model. Finally, we develop a domain adaptation method to help our proposed approach generalise to different cohorts of patients.

    oxford Repository record for Using deep learning on histology to inform colorectal cancer patient treatment (opens in a new tab)

  12. Online parameter adaptation methods for population-based metaheurisistics

    … continuous line of research on parameter tuning methods since the early development of optimization algorithms. The majority of these methods addresses the tuning problem offline, i.e., prior to the algorithm’s execution. Established offline methods are based on statistical methodologies to …

    greece Repository record for Online parameter adaptation methods for population-based metaheurisistics (opens in a new tab)

  13. Monocular Camera-based Road Segmentation Using Geometric Cues

    … rapid development of autonomous driving, such methods have attracted substantial attention from both academia and industry due to their research significance and commercial potential. However, a key challenge lies in achieving robust adaptation—that is, effectively generalizing to diverse …

    york Repository record for Monocular Camera-based Road Segmentation Using Geometric Cues (opens in a new tab)

  14. A Domain Adaptation Approach for Segmenting Cell Instances in Microscopy Data

    … contrastive losses, our few-shot domain adaptation method not only performs well on all datasets tested; it even approaches the level of networks trained directly on the target datasets. In several ways, this work extends the current aims of generalized cellular instance segmentation …

    wvu Repository record for A Domain Adaptation Approach for Segmenting Cell Instances in Microscopy Data (opens in a new tab)

  15. Manipulation-Driven Adaptation for Enhancing Mobile Robot Efficiency and Versatility

    … operate on a broad variety of terrain. Physical adaptation can enable a robot to intelligently interact with the environment to benefit from efficient and versatile performance. We describe a new approach to physical adaptation through manipulation. Specifically, this work investigates how …

    gatech Repository record for Manipulation-Driven Adaptation for Enhancing Mobile Robot Efficiency and Versatility (opens in a new tab)

  16. Investigation of Machine and Deep Learning Approaches for Tuberculosis Detection on Chest Radiographs

    … Machine Learning (ML) and Deep Learning (DL) methods to address these limitations. In this research, I aimed to develop a novel DL-based method for TB detection using chest radiographs. I began by conducting two systematic reviews to evaluate the performance of existing ML and DL approaches …

    unsw Repository record for Investigation of Machine and Deep Learning Approaches for Tuberculosis Detection on Chest Radiographs (opens in a new tab)

  17. Unstructured grid simulations of shocks and detonations in two-phase flows

    … This flow solver incorporated the Finite Element Method-Flux Corrected Transport scheme, which has shown excellent predictive capability of various compressible flows which include both strong and weak shocks. Two separate two-phase flow techniques have been added to this solver to allow …

    uiuc Repository record for Unstructured grid simulations of shocks and detonations in two-phase flows (opens in a new tab)

  18. Adaptation Methods for Statistical Machine Translation In Business Scenarios

    Adaptation methods for phrase-based statistical Machine Translation (MT) have been explored in the literature under different paradigms, such as domain adaptation and topic adaptation, and most of the times in rather ideal experimental set-ups. We address this subject in three real-life industrial …

    trento Repository record for Adaptation Methods for Statistical Machine Translation In Business Scenarios (opens in a new tab)

  19. A complex networks approach to designing resilient system-of-systems

    This thesis develops a methodology for designing resilient system-of-systems (SoS) networks. This methodology includes a capability-based resilience assessment framework, used to quantify SoS resilience. A complex networks approach is used to generate potential SoS network designs, focusing on …

    gatech Repository record for A complex networks approach to designing resilient system-of-systems (opens in a new tab)

  20. Adaptive Particle Filters for Wireless Indoor Target Tracking

    … Particle filters are recursive Monte-Carlo methods based on Bayes' theorem, which fuse the previous state information and the current measurement data to obtain the target position. The advantage of using PFs is that the heterogeneous information can be combined effectively within the PFs to …

    fu-berlin Repository record for Adaptive Particle Filters for Wireless Indoor Target Tracking (opens in a new tab)

Page 1 of 5