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 32 for “"Graph Convolutional Neural Networks"”.

  1. Graph Convolutional Neural Networks for Brain Connectivity Analysis

    We explore the potential and limitation of Graph Convolutional Neural Networks (GCNs) for classification of brain graphs derived from MRI measurements of subjects with Alzheimer’s disease (AD). GCNs differ from regular Artificial Neural Networks (ANNs) in that they operate directly on graph …

    chalmers Repository record for Graph Convolutional Neural Networks for Brain Connectivity Analysis (opens in a new tab)

  2. Detection of Autism using Magnetic Resonance Imaging data and Graph Convolutional Neural Networks

    … about each subject to train variations of a Graph Convolutional Neural Network to detect if a subject is Autistic or Neurotypical. The time series information as well as the connectivity information of specific parts of the brain are the features used for analysis. The thesis converts fMRI …

    rit Repository record for Detection of Autism using Magnetic Resonance Imaging data and Graph Convolutional Neural Networks (opens in a new tab)

  3. Some Mathematical Perspectives of Graph Neural Networks

    Many real-world entities can be modelled as graphs, such as molecular structures, social networks, or images. Despite coming with such a great expressive power, the complex structure of graphs poses significant challenges to traditional deep learning methods, which have been extremely successful in …

    waterloo Repository record for Some Mathematical Perspectives of Graph Neural Networks (opens in a new tab)

  4. High-Performance, Energy-Efficient, and Scalable Accelerator Design for Emerging Machine Learning Applications

    … handle irregular sparsity in accelerating graph convolutional neural networks. Furthermore, the dissertation uncovers the extensive intermediate feature data reuse opportunities and their communication bottlenecks in complex graph neural network models. These innovative accelerator designs …

    ucf Repository record for High-Performance, Energy-Efficient, and Scalable Accelerator Design for Emerging Machine Learning Applications (opens in a new tab)

  5. Spatio-Temporal Deep Learning Approaches for Addressing Track Association Problem using Automatic Identification System (AIS) Data

    … as Multi Model Long Short-Term Memory (LSTM), 1D Convolutional-LSTM, and Temporal-Graph Convolutional Neural Networks— in addressing the problem of track association. The performance of these proposed models are compared against different deep learning algorithms specialized in track association …

    wvu Repository record for Spatio-Temporal Deep Learning Approaches for Addressing Track Association Problem using Automatic Identification System (AIS) Data (opens in a new tab)

  6. Machine learning and optimization for intelligent decision-making

    … and power systems. By integrating advanced neural architectures with robust optimization techniques, the work delivers scalable solutions designed to improve efficiency, reliability, and decision-making in dynamic and real-world environments. The first study introduces a two-stage approach …

    njit Repository record for Machine learning and optimization for intelligent decision-making (opens in a new tab)

  7. On the motion and action prediction using deep graph models

    … deep learning techniques, such as recurrent and convolutional architectures. These approaches are not representative of the spatial and temporal aspects of the observations. This dissertation presents novel approaches using spatio-temporal graphs to model the observations. We model each agent as …

    texas Repository record for On the motion and action prediction using deep graph models (opens in a new tab)

  8. Positivity and Invariance: From Radial Basis Functions to Graph Signal Spaces

    … second half turns to shift-invariant spaces on graphs and their applications in signal recovery. Extending classical shift-invariant theory to graph settings, we introduce graph shift-invariant spaces (GSIS) defined via commutative shift operators and investigate their analytic and spectral …

    ucf Repository record for Positivity and Invariance: From Radial Basis Functions to Graph Signal Spaces (opens in a new tab)

  9. Swin PoseFormer, Efficient Skeleton Based Human Activity Recognition

    … sensor data. Deep learning techniques, including convolutional neural networks, recurrent neural networks, and graph convolutional neural networks, have demonstrated the ability to automatically learn features and achieve state-of-the-art results. Dynamic skeletal data, represented as the 2D/3D …

    queens Repository record for Swin PoseFormer, Efficient Skeleton Based Human Activity Recognition (opens in a new tab)

  10. Applications of deep learning in protein structure prediction : from complexes to intrinsically disordered proteins

    … experimental methods like X-ray crystallography and NMR spectroscopy, despite their accuracy, are costly and time-consuming. This has prompted the exploration of computational models, particularly deep learning techniques, to predict protein structures, especially of complexes, more …

    missouri Repository record for Applications of deep learning in protein structure prediction : from complexes to intrinsically disordered proteins (opens in a new tab)

  11. Contributions to the Computational Treatment of Non-literal Language

    … structured prediction. We also develop a novel neural architecture to speci fically address the issue of discontinuous MWEs using a combination of Graph Convolutional Neural Networks (GCNs) and self-attention. The proposed model is subsequently tested on several languages where it is shown to …

    wlv Repository record for Contributions to the Computational Treatment of Non-literal Language (opens in a new tab) Download file for Contributions to the Computational Treatment of Non-literal Language (opens in a new tab)

  12. Forecasting Pedestrian Trajectory Using Deep Learning

    … and then this information is passed through some neural network to capture social information. In our work we build a robust architecture to incorporate these social interactions via Graph Convolutional Neural Networks (GCN) and Transformers. GCN first, extracts Spatio-Temporal (ST) …

    unlv Repository record for Forecasting Pedestrian Trajectory Using Deep Learning (opens in a new tab) Download PDF for Forecasting Pedestrian Trajectory Using Deep Learning (opens in a new tab)

  13. TIME SERIES DEEP LEARNING APPROACH FOR THE INTERMITTENT OPERATIONAL PERFORMANCE OF A WELLHEAD WATER TREATMENT AND DESALINATION SYSTEM

    … serving disadvantaged communities that are geographically segregated from centralized water distribution networks. However, given the remote nature of the communities, these systems must operate autonomously adapting to intermittent operations due to varying water use patterns and …

    csusb Repository record for TIME SERIES DEEP LEARNING APPROACH FOR THE INTERMITTENT OPERATIONAL PERFORMANCE OF A WELLHEAD WATER TREATMENT AND DESALINATION SYSTEM (opens in a new tab)

  14. Advances in robust signal processing and applications

    … including structural perturbations in graph-based models, complex non-Gaussian noise in communication systems, and the structural heterogeneity of high-dimensional tensor data. This thesis addresses these critical challenges by developing a suite of robust methodologies grounded in …

    aalto Repository record for Advances in robust signal processing and applications (opens in a new tab)

  15. Optimization for Electric Vehicle Infrastructure and Route Planning in Special Services Systems

    … of traffic flow prediction within logistics networks. A stochastic model is first introduced to capture the variability in ELV charging demand, utilizing the Wasserstein distance metric to effectively represent the inherent uncertainties. This is complemented by a deep learning model that …

    unsw Repository record for Optimization for Electric Vehicle Infrastructure and Route Planning in Special Services Systems (opens in a new tab) Embargoed

  16. Domain adaptation and multi-scale relational graph neural network in classification of prostate cancer histopathology images

    … due to the domain shift in the data. While graph convolutional neural networks have shown significant potential in natural and histopathology images, their use in histopathology images has only been studied using a single magnification or multi-magnification with late fusion. In this thesis, …

    ubc Repository record for Domain adaptation and multi-scale relational graph neural network in classification of prostate cancer histopathology images (opens in a new tab) Download PDF for Domain adaptation and multi-scale relational graph neural network in classification of prostate cancer histopathology images (opens in a new tab)

  17. Social Media Analytics with Graph Convolutional Networks

    … social relationships established on social networks can be leveraged to market products or make recommendations. However, the open nature of online social media provides a favorable environment for malicious users to spread incorrect information, either for financial gains or to increase …

    toronto-retro Repository record for Social Media Analytics with Graph Convolutional Networks (opens in a new tab)

  18. Developing Efficient Electrocatalysts for Oxygen Evolution at High Current Densities

    … compared to RuO2. Finally, I use crystal graph convolutional neural networks and computational descriptors to optimize the acidic stability of OER catalysts. I find that incorporating Ti increases the metal-oxygen covalency and Pourbaix dissociation energy of RuO2 resulting in improved …

    toronto-retro Repository record for Developing Efficient Electrocatalysts for Oxygen Evolution at High Current Densities (opens in a new tab)

  19. Molecular representation modeling with graph neural networks for antibiotic discovery

    … can be considered as non-structural data, graph convolutional neural networks (GCNs), which can learn and aggregate the local information of molecules, have been used to predict molecular properties with great success. Furthermore, given the merits and various successful practices of …

    manitoba Repository record for Molecular representation modeling with graph neural networks for antibiotic discovery (opens in a new tab)

Page 1 of 2