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 67 for “"Graph Network"”.
-
GNET-QG: graph network for multi-hop question generation
… In our research, we study the utilization of a Graph Attention Network (GAT) and a BART model for multi-hop question generation, Our proposed model, is GNET-QG (Graph Network for Multi-Hop Question Generation). GNET-QG efficacy is assessed on the HotpotQA dataset using metrics such as METEOR, …
-
Novel Networks in Collider Searches for New Physics
… space. A map of event similarities forms a graph network, which provides a convenient range of network variables able to quantify local topologies. In networks constructed from nodes of LHC events, we aim to use network variables to increase sensitivity to anomalous topologies local to BSM …
-
An Adaptive Land Tenure Information System Database Design for Conflict and Post-Conflict Situations
… was to design, develop, and test a schema-less graph network Land Tenure Information System (LTIS) database prototype that is integrated with data mining and social network analysis techniques for the purpose of revealing hidden tenure information in the data related to conflict and …
-
Evaluation of Citation Graph Thematic Dataset Construction and Paper Filtering Methods for Research Literature Recommendation
… for constructing datasets using citation graph networks. These networks consist of nodes representing research papers and edges representing citations between them. By leveraging citation graph networks, we gain a more comprehensive understanding of the relationships and influences among …
-
Mining Connected Frequent Boolean Expressions
… dataset [14] and protein protein interaction network [14] to discover group of dysregulated genes. Frequent Itemset Mining is a process of finding different sets of items that occur together frequently in a set of transactions. These itemsets are called Frequent Itemsets (FBE). Connected FBE …
-
Data-driven Storytelling in Dynamic Graph Comics through Hierarchical Clustering
… work, we propose a tool to generate a dynamic graph comic given dense, time-series edge-vertex data. Prior research has demonstrated the effectiveness of node-link diagrams as an expressive medium for storytelling with dynamic graphs, and in this work, we develop an interface that generates a …
-
Carbon-Dioxide Pipeline Infrastructure Route Optimization And Network Modeling For Carbon Capture Storage And Utilization
… and (b) to develop a CCUS infrastructure network which minimizes project cost. To address these goals, the dissertation introduces the CCSHawk methodology that develops pipeline routes and CCUS infrastructure networks using a variety of techniques such as multi-criteria decision analysis …
-
A Hybrid Learning Approach for Modelling and Analyzing Clickstream Data from Learning Management Systems
… a Long Short-Term Memory (LSTM) recurrent neural network (RNN) is introduced to model real-time online feedback to students when completing academic activities using online Learning Management Systems (LMS). The solution provided is a Smart Classifier which unravels, and processes hidden patterns …
-
Mathematical and computational approaches to contagion dynamics on networks
… In particular we introduce the basics of graph/network theory, epidemiological models (both well mixed and on networks), and mobility models (the gravity and radiation models). After the introduction of these topics, we propose a general framework for epidemiological network models from …
-
MLPs and KANs for data-driven learning in physical problems : a performance comparison
… has been a spike in exploring Kolmogorov-Arnold Networks (KANs) as an alternative to traditional neural networks represented by Multi-Layer Perceptrons (MLPs). While showing promise, their performance advantages in physics-based problems remain largely unexplored. Several critical questions …
-
Curvature Variation as Measure of Shape Information
… patches. We output the real world object as a graph network of patches with our CVM at the nodes describing the patch complexity. We demonstrate this algorithm with results on automotive components.</p>
-
Advancing 6DoF Object Pose Estimation: Keypoint Voting, Optimal Keypoint Sampling, and Bridging the Simulation-to-real Gap
… and RGB-D methods. Second, KeyGNet leverages a graph network to optimize the keypoint selection, improving accuracy and efficiency by learning dispersed, evenly distributed keypoints. KeyGNet enhances performance across all metrics, notably increasing ADD(S) on Occlusion LINEMOD by 16.4% and …
-
A hybrid database solution to support transportation analytics with case studies on improving emergency medical service response times
… solution---relational database system-only or graph database-only---to store and manage data can be challenging. As real-world applications ask even more complex questions related to data, the database solution should be able to facilitate answering these questions in a reasonable time. Hence, …
-
A delete-one-edge approach to network modelling and goodness-of-fit
This thesis aims to study graph networks of similar structure and statistical distribution and make inferences based on the nodal and dyadic covariates. Incorporating a small amount of randomness can drastically alter important features of the underlying structure and dynamics of a network. Our …
-
ON THE GENERALIZATION AND ROBUSTNESS OF ML-BASED NETWORK INTRUSION DETECTION SYSTEMS
Machine Learning (ML)-based Network Intrusion Detection Systems (NIDS) hold great promise for enhancing network security. As a security application, concerns persist regarding the generalization and robustness of ML-based NIDS. To facilitate real-world deployment, it is crucial to ensure the …
-
Learning invariant representations in neural networks
… learning tasks. While convolutional neural networks famously and successfully exploit translational symmetries, other symmetries have, until recently, often been neglected. Incorporating symmetries or invariances into the neural network architecture avoids costly data augmentation and …
-
INTEGRATING GRAPH AND LANGUAGE DATA IN MACHINE LEARNING MODELS: APPLICATIONS FOR COMPUTATIONAL SOCIAL SCIENCE
… three papers demonstrating how integrating graph (network) and language (text) data in machine learning models can enhance computational social science models. These two types of data are ubiquitous across many contexts in which computational social scientists work (e.g., social media …
-
Modeling, control, fault detection and isolation of chemical processes using a bond graph framework
… this work, a unified modeling concept, the bond graph is used to model multiple domains. The basic variable of a bond graph is power that unifies the distinct domains. Additionally, the bond graph network reflects the physical structure in which power exchanges are tracked and the dynamics …
-
Deep Learning for Object Relationships: Applications to Road Safety and Bin Picking
… the relationship between two objects, a graph-network architecture was designed and implemented. This architecture relies on the bounding boxes and feature maps that would be outputted by an upstream detector to estimate the relationships for pairs of detected objects. The starting edge …
-
Examining Heterogeneity in Neurodevelopmental Conditions– A Data-Driven Network-Based Approach
… through the application of data-driven network-based approaches to discover replicable subgroups of individuals with shared patterns of brain structure. The specific contributions of this thesis are three-fold: (1) Using a novel graph network analytic framework, we discovered …
Page 1 of 4