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 37 for “"network layers"”.
-
Transform Domain Deep Neural Network Layers and Their Applications
… orthogonal transform theory with deep neural network architectures to achieve efficient data compression, representation learning, and image correction. The motivation stems from the increasing demand for accurate and resource-efficient data processing in biomedical and industrial systems, …
-
Physics-Inspired Deep Learning for Inverse Problems in MRI
… resonance imaging (MRI), from individual network layers to the network architecture design and inference procedure. First, we propose neural network layers that combine image space representations with representations in Fourier space, where MRI data is acquired. These layers can be used …
-
Dafny-HLS: verified and optimized high-level synthesis via MLIR with LLM-assisted bug repair
… on ten PolyBench kernels and multiple neural network layers, including the first formally specified and verified convolutional layer in Dafny. Our LLM-assisted repair achieves up to 95% auto-repair success on neural network layers and 74% on PolyBench kernels, while optimized HLS C/C++ outputs …
-
Protocol design and analysis for a dynamic hierarchical local area network
… a protocol for a dynamic hierarchical local area network are addressed. The dynamic hierarchy is an extension of the static hierarchical topology with the exception that the apex node can vary among a prescribed set of candidates. A simulation model is used to evaluate the benefits of dynamic apex …
-
Graph-Based Approach: Bridging Insights from Structured and Unstructured Data
… systems. In healthcare, we examine how social networks influence the attitudes of hemodialysis patients toward kidney transplantation. Using a network-based approach, we investigate how social networks within hemodialysis clinics affect patients' attitudes, contributing to a growing …
-
Successive structuring of source coding algorithms for data fusion, buffering, and distribution in networks
Numerous opportunities to improve network performance present themselves when we make communication networks aware of the characteristics of the data content they are handling. In this thesis, we design such content-aware algorithms that span traditional network layers and are successively …
-
A measurement-based analysis of the interaction among MAC, network and application layers in wireless sensor networks
… been a number of recent proposals for link and network-layer protocols in the sensor networking literature, each of which claims to be superior to other approaches. However, a proposal for a networking protocol at a given layer in the stack is typically evaluated in the context of a single set …
-
Machine Learning for Intrusion Detection into Unmanned Aerial System 6G Networks
<p>Progress in the development of wireless network technology has played a crucial role in the evolution of societies and provided remarkable services over the past decades. It remotely offers the ability to execute critical missions and effective services that meet the user's needs. This advanced …
-
Design, Implementation and Characterization of a Cooperative Communications System
… nodes. While cooperation can occur at different network layers and time scales, physical layer cooperation at symbol time scales offers the largest benefit. However, symbol level cooperation poses significant implementation challenges, especially in the context of a network of distributed nodes. …
-
Data-Driven Deep Learning Methods for Physically-Based Simulations
… problems modeled through Discrete Fracture Networks, training Deep Learning models as reduced models for Uncertainty Quantification. In particular, we look for trained Neural Networks able to predict the outflowing fluxes of a Discrete Fracture Network model. These Neural Networks are also …
-
Advances in integrating autonomy with acoustic communications for intelligent networks of marine robots
… of the physical acoustic link and higher network layers by the AUV’s decision making software. This thesis presents a modular acoustic networking framework, realized through a C++ library called goby-acomms, to provide collaborating underwater vehicles with an efficient short-range …
-
Sonic Analysis for Machine Learning: Multi-Layer Perceptron Training using Spectrograms
… goal is achieved through the use of neural networks. Originally, DeepDream came about as a way of visualising the weights inside neural network layers – matrices of variables containing the data that determines what information the network has learned – for better understanding of training …
-
Multilevel Parallel Communications
… at multiple levels to realize high-speed networks that offer advantages in throughput, cost, reliability, and flexibility over alternative approaches. This research specifically considers use of parallelism at two levels: the "upper" level and the "lower" level. At the upper level, N …
-
Performance of adaptive admission\congestion control policies on a hybrid MC-CDMA\TDMA integrated multimedia networks
Future 3G CDMA networks are expected to have the ability to accommodate variety of users, each with its own transmission characteristics and quality of service (QoS) requirements to be maintained. Compatible multi-access system should provide the means to control (i.e. admission congestion) the …
-
Simulating Network Structure, Layering Multi-layer Network System and Developing Network Block Configuration Model to Understand and Improve Energy Conservation in Residential Buildings
… information among residents in a peer network. However, most of this research relies on experimental tests and does not theorize concepts related to peer network energy efficiency systematically. My dissertation addresses this research gap on two levels. First, I examined if and how the …
-
Comparing Learned Representations Between Unpruned and Pruned Deep Convolutional Neural Networks
<p>While deep neural networks have shown impressive performance in computer vision tasks, natural language processing, and other domains, the sizes and inference times of these models can often prevent them from being used on resource-constrained systems. Furthermore, as these networks grow larger …
-
Advances in integrating autonomy with acoustic communications for intelligent networks of marine robots
… of the physical acoustic link and higher network layers by the AUV's decision making software. This thesis presents a modular acoustic networking framework, realized through a C++ library called goby-acomms, to provide collaborating underwater vehicles with an efficient short-range …
-
Protocol stacks for power-aware wireless microsensor networks
… system, a need to prolong the lifetime of the network is crucial and limited by battery capacity. As communication traffic among sensor nodes is triggered by sensing events, the network can exploit these time-varying scenarios to obtain power savings by adjusting its operating conditions …
-
Comparing Duplexing, Multiplexing, and Multiple Access Techniques in Ad Hoc Networks
Wireless ad-hoc networks have seen much attention in recent years, and are still a topic of much interest, especially as a result of an increasing need for ubiquitous connectivity. Ad-hoc networks have applications in tactical military systems as well as in commercial systems because of the …
-
Reliable and Energy Efficient Network Protocols for Wireless Body Area Networks
In a wireless Body Area Network (WBAN) various sensors are attached on clothing, on the body or are even implanted under the skin. The wireless nature of the network and the wide variety of sensors offers numerous new, practical and innovative applications. A motivating example can be found in the …
Page 1 of 2