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 61 for “"Network Robustness"”.

  1. Network Robustness: Diffusing Information Despite Adversaries

    … problem of diffusing information resiliently in networks that contain misbehaving nodes. Previous strategies to achieve resilient information diffusion typically require the normal nodes to hold some global information, such as the topology of the network and the identities of non-neighboring …

    waterloo Repository record for Network Robustness: Diffusing Information Despite Adversaries (opens in a new tab)

  2. ENHANCING THE EFFICACY OF NEURAL NETWORK ROBUSTNESS ANALYSIS

    As neural networks have taken on a critical role in real-world applications, formal verification is needed to guarantee the safety properties of neural networks. Nevertheless, it remains challenging to balance the trade-off between precision and efficiency, given diverse verification requirements. …

    nus Repository record for ENHANCING THE EFFICACY OF NEURAL NETWORK ROBUSTNESS ANALYSIS (opens in a new tab) Download file for ENHANCING THE EFFICACY OF NEURAL NETWORK ROBUSTNESS ANALYSIS (opens in a new tab)

  3. Improving Convolutional Neural Network Robustness to Adversarial Images Through Image Filtering

    … extremely high accuracy. Convolutional neural networks exist that can correctly classify 96\% of 1.2 million images of complex scenes. However, with just a few carefully positioned imperceptible changes to the pixels of an input image, an otherwise accurate network will misclassify this almost …

    ut-knoxville Repository record for Improving Convolutional Neural Network Robustness to Adversarial Images Through Image Filtering (opens in a new tab)

  4. A Hybrid Approach to Network Robustness Optimization using Edge Rewiring and Edge Addition

    Networks are ubiquitous in the modern world. From computer and telecommunication networks to road networks and power grids, networks make up many crucial pieces of infrastructure that we interact with on a daily basis. These networks can be subjected to damage from many different sources, both …

    brock Repository record for A Hybrid Approach to Network Robustness Optimization using Edge Rewiring and Edge Addition (opens in a new tab)

  5. ADDRESSING DRIVER CONCERNS: THE NETWORK ROBUSTNESS INDEX APPROACH TO PLANNING CITY CYCLING INFRASTUCTURE

    On congested North American urban road networks, driver concerns over increased travel time play a major role in whether or not cycling infrastructure is built. This fact is recognized by transportation planning agencies in Canada and the United States, including the Ministry of Transportation …

    mcmaster Repository record for ADDRESSING DRIVER CONCERNS: THE NETWORK ROBUSTNESS INDEX APPROACH TO PLANNING CITY CYCLING INFRASTUCTURE (opens in a new tab)

  6. Understanding and modelling the robustness of complex networks for varying degrees of structural information

    Complex networks provide a framework for modelling and understanding the behaviour of a wide variety of real world systems, and one network property of interest is robustness. Here we explore several different understandings of network robustness, developing new models and methods in order to …

    bristol Repository record for Understanding and modelling the robustness of complex networks for varying degrees of structural information (opens in a new tab) Download PDF for Understanding and modelling the robustness of complex networks for varying degrees of structural information (opens in a new tab)

  7. TEMPORAL CONNECTIVITY AS A MEASURE OF ROBUSTNESS IN NONORTHOGONAL MULTIPLE ACCESS WIRELESS NETWORKS

    … generation (5G) and beyond 5G (B5G) wireless networks. Through the technique of overloading, NOMA has the potential to support higher connection densities, increased spectral efficiency, and lower latency than orthogonal multiple access. The role of NOMA in 5G/B5G wireless networks …

    nps Repository record for TEMPORAL CONNECTIVITY AS A MEASURE OF ROBUSTNESS IN NONORTHOGONAL MULTIPLE ACCESS WIRELESS NETWORKS (opens in a new tab)

  8. TROPICAL GEOMETRY IN NEURAL NETWORKS: A NOVEL DEFENSE AGAINST ADVERSARIAL ATTACK

    Neural networks, though powerful, are highly susceptible to adversarial attacks, which can severely impact their reliability and performance in critical applications, especially within the Department of Defense (DoD). This thesis employs Tropical Convolutional Neural Networks (TCNN), a novel …

    nps Repository record for TROPICAL GEOMETRY IN NEURAL NETWORKS: A NOVEL DEFENSE AGAINST ADVERSARIAL ATTACK (opens in a new tab)

  9. AIR TRANSPORTATION INFRASTRUCTURE ROBUSTNESS ASSESSMENT FOR PROACTIVE SYSTEMIC RISK MANAGEMENT

    A key attribute of resilience, robustness serves as a predictor of infrastructure system performance under disruptions, thus informing proactive infrastructure risk management. A literature review indicated that previous studies did not consider some key factors that can influence the robustness of …

    mcmaster Repository record for AIR TRANSPORTATION INFRASTRUCTURE ROBUSTNESS ASSESSMENT FOR PROACTIVE SYSTEMIC RISK MANAGEMENT (opens in a new tab)

  10. Percolation and reinforcement on complex networks

    Complex networks appear in almost every aspect of our daily life and are widely studied in the fields of physics, mathematics, finance, biology and computer science. This work utilizes percolation theory in statistical physics to explore the percolation properties of complex networks and develops a …

    bu Repository record for Percolation and reinforcement on complex networks (opens in a new tab)

  11. Robustness and entropy for dynamics on networks

    <p>Robustness and entropy are widely used concepts in the study of networks in various disciplines. There exist various notions of network robustness and network entropy, because there are many network properties that can be robust to perturbations and there are many network-associated …

    oxford Repository record for Robustness and entropy for dynamics on networks (opens in a new tab)

  12. Essays in network theory applications for transportation planning

    <p>Throughout the dissertation, network methods are developed to address pressing issues in transportation science and geography. These methods are applied to case studies to highlight their use for urban planners and social scientists working in transportation, mobility, housing, and health. The …

    utk-theses Repository record for Essays in network theory applications for transportation planning (opens in a new tab)

  13. TOWARDS NETWORKS WITH EFFICIENCY, EXPLAINABILITY AND ROBUSTNESS

    … to the evolution of various underlying network architectures. However, the real-world deployment of these visual recognition systems has surfaced several challenges. Key among them is achieving operational efficiency, particularly in terms of computational cost. Additionally, there is a …

    jhu Repository record for TOWARDS NETWORKS WITH EFFICIENCY, EXPLAINABILITY AND ROBUSTNESS (opens in a new tab)

  14. NEURAL NETWORK DISTRIBUTIONAL INITIAL CONDITION ROBUSTNESS IN POWER SYSTEMS

    How can we measure and classify neural network robustness across differently distributed data to avoid misuse of machine learning tools? This thesis adopts several metrics to measure the initial condition robustness of feedforward neural networks, allowing the creators of such networks to measure …

    nps Repository record for NEURAL NETWORK DISTRIBUTIONAL INITIAL CONDITION ROBUSTNESS IN POWER SYSTEMS (opens in a new tab)

  15. ROBUST TIME-VARYING FORMATION CONTROL WITH ADAPTIVE SUBMODULARITY

    … is developed to position nodes within a mobile Network Control System (NCS) composed of heterogeneous agents. Each node is represented with distinct capabilities and constraints with regard to communications, sensing, and mobility. Metrics used to quantify network robustness are developed for …

    nps Repository record for ROBUST TIME-VARYING FORMATION CONTROL WITH ADAPTIVE SUBMODULARITY (opens in a new tab)

  16. SWARM CHARACTERISTICS CLASSIFICATION USING NEURAL NETWORKS

    … demonstrates feasibility of using neural network time series classification to rapidly infer adversarial swarm behaviors from limited observations. Various deterministic neural network architectures achieve over 90% accuracy in classifying swarm agent attributes and tactics, even under …

    nps Repository record for SWARM CHARACTERISTICS CLASSIFICATION USING NEURAL NETWORKS (opens in a new tab)

  17. Circuit and algorithm design to enable edge intelligence

    … cost, processing latency, data security, network robustness, and so on. However, EI Design is essentially challenging to support ever-demanding artificial intelligence on resource-constrained devices with a slowly-evolving technology node. Moreover, as an emerging field, a systematic …

    gatech Repository record for Circuit and algorithm design to enable edge intelligence (opens in a new tab)

  18. CITY NETWORK RESILIENCE QUANTIFICATION UNDER SYSTEMIC RISKS: A HYBRID MACHINE LEARNING-GENETIC ALGORITHM APPROACH

    … impact the operation of critical infrastructure networks because they may instigate network-level cascade (i.e., systemic) risks. Therefore, quantifying and enhancing the resilience of such complex dynamically evolving networks ensure minimizing the possibility and consequences of systemic risks. …

    mcmaster Repository record for CITY NETWORK RESILIENCE QUANTIFICATION UNDER SYSTEMIC RISKS: A HYBRID MACHINE LEARNING-GENETIC ALGORITHM APPROACH (opens in a new tab)

  19. Influence of Hydrologic and Anthropogenic Disturbance on Stream Populations and Communities

    … model was performed using Spatial Stream Network modeling on Smallmouth Bass at the southern extent of their range, the Ozark-Ouachita Interior Highlands. Hydrologic variation was the main driver of Smallmouth Bass occurrence. Smallmouth Bass were most likely to occur in groundwater …

    arkansas Repository record for Influence of Hydrologic and Anthropogenic Disturbance on Stream Populations and Communities (opens in a new tab)

Page 1 of 4