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 41 for “"Network algorithms"”.
-
Decentralized Network Algorithms
… problem of disseminating a large file to a large network of users. The file is divided into pieces, and different pieces are initially uploaded to different users. The users then exchange pieces to complete their individual collections. In such networks, a crucial task is piece selection: users …
-
A comparative study of neural network algorithms.
Various Neural network models are investigated for Optical Character Recognition application and a Multi-layer Feed forward neural network is trained using a Fast training algorithm. Then the fast training algorithm is compared with the delta rule training algorithm. The various neural network …
-
Delay-Aware Multi-Path Routing in a Multi-Hop Network: Algorithms and Applications
… is highly important. As a basic paradigm of networking, multi-path routing has been proven to be able to obtain lower delay performance than the single-path routing, since traffic congestions can be avoided. However, to our best knowledge, (i) many of existing delay-aware multi-path routing …
-
Design and Evaluation of Network Algorithms and Deep Learning Models in Systems Biology and Biomedicine
… novel solutions to four interrelated problems in network biology and computational biomedicine. The first two address methodological challenges in network biology, while the latter two focus on applications of network-based computational modeling in therapeutics. (i) We introduce a provenance …
-
Development and Application of Network Algorithms for Prediction of Gene Function and Response to Viral Infection and Chemicals
… cellular processes is with protein interaction networks. Due to the complexity of these networks, sophisticated computational techniques are required to extract biological insights from them. In this thesis, I develop and apply network-based algorithms for three different challenges. 1. I …
-
Continuous representations and models from random walk diffusion limits
Structured data such as sequences and networks pose substantial difficulty for traditional statistical theory which has focused on data drawn independently from a vector space. A popular and empirically effective technique for dealing with such data is to map elements of the data to a vector space …
-
Human iris categorization using artificial neural networks
… image categorization using artificial neural networks, specifically for human iris images with discernible and complicated textures. The work will allow users to quickly and automatically categorize human iris images by using supervised and unsupervised learning algorithms. Contributions of …
-
Numerical analysis for quantum electrodynamics in the ultrastrong coupling regime
… Hamiltonians that are more amenable to tensor network algorithms are developed. Furthermore, discrete exterior calculus (DEC) is considered for electromagnetic analysis of quantum devices. The study investigates the satisfaction of the generalized Helmholtz decomposition in DEC simulations in …
-
Design, modeling, and simulation of a Compact Optoelectronic Neural Coprocessor
… Substantial research has focused on using neural network algorithms to process this type of data with much success. Most of this effort, however, has resulted in sophisticated neural network-based software algorithms rather than physical neural network hardware. Consequently, most neural …
-
Hardware Implementation of a Novel Image Compression Algorithm
… transform coding, vector quantization and neural networks. In this thesis, a novel adaptive compression technique is introduced based on adaptive rather than fixed transforms for image compression. The proposed technique is similar to Neural Network (NN)-based image compression and its superiority …
-
Recursive backpropagation algorithm applied to a globally recurrent neural network
In general, recursive neural networks can yield a smaller structure than purely feedforward neural network in the same way infinite impulse response (IIR) filters can replace longer finite impulse response (FIR) filters. This thesis presents a new adaptive algorithm that trains recursive neural …
-
Organic LEDs for optoelectronic neural networks
… COIN coprocessor, a prototype artificial neural network implemented in hardware, seeks to implement neural network algorithms in native optoelectronic hardware in order to do parallel type processing in a faster and more efficient manner than all-electronic implementations. The feasibility of …
-
An End User QoS View of Buffer Sizing and Bandwidth Sharing Protocols
Much attention has been given to design of network algorithms for the Internet, assuming a fixed number of end hosts. While this is a crucial first step, the analysis is in no way complete. The current design goals such as high-link utilization, low loss probability are useful only when the number …
-
Connectomics of extrasynaptic signalling: applications to the nervous system of Caenorhabditis elegans
… first time that whole-animal volume transmission networks can be mapped from gene expression and ligand-receptor interaction data, and analysed as part of the connectome. Complete networks are presented for the monoamine systems of Caenorhabditis elegans, along with a representative sample of …
-
A binary relation inference network for constrained optimization
… This thesis presents a novel parallel computing network designed for some optimization problems which can be represented by binary relations and the calculation upon them. Traditional graph search techniques provide sequential solutions to constraint satisfaction, but their speed is limited by …
-
Distributed computation on unreliable radio channels
An important topic in wireless networking is the development of reliable algorithms for environments suffering from adversarial interference. This term captures any type of channel disruption outside the control of the algorithm designer-from contention with unrelated devices to malicious jamming. …
-
Improving Bluetooth-based Indoor Positioning Using Vision and Artificial Networks
… vision systems, and Artificial Neural Networks (ANNs) to improve the accuracy of the position solutions in indoor environments for pedestrian applications. BLE technology faces challenges related to the Received Signal Strength Indicator (RSSI) fluctuations caused by human body …
-
Self-stabilizing wormhole routing
… This permits messages to wind through the entire network from source to destination, resembling a worm. Wormhole routing is a lightweight and efficient method of routing messages between parallel processors; Our purpose is to modify existing wormhole routing algorithms in familiar topologies to …
-
Automated posture analysis for detecting learner's affective state
… Using Gaussian Mixtures and feed-forward Neural Network algorithms, the system classifies the postures in real time. It achieves an overall accuracy of 87.6% when it is tested with children's postures that were not included in the training set. Also, the children's posture sequences were …
Page 1 of 3