Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Data mining (2)
- Virtualization (2)
- AADL (1)
- Adaptive algorithms (1)
- Architecture (1)
-
- Bison (1)
- Classification (1)
- Cluster computing (1)
- Computer Science Education (1)
- Concept-Forest (1)
- Debugging (1)
- Dependability (1)
- Destinations (1)
- Epilepsy (1)
- Extensible languages (1)
- Eye tracking (1)
- GPGPU (1)
- Genetic algorithms (1)
- Grammarware (1)
- Grid computing (1)
- Heuristics (1)
- ICA (1)
- IELR(1) (1)
- Information Retrieval (1)
- Kprobes (1)
- Learning classifier systems (1)
- Linux (1)
- Machine learning (1)
- Marketing (1)
- Network Optimization (1)
Articles 1 - 13 of 13
Full-Text Articles in Entire DC Network
A Framework For Virtual Device Driver Development And Virtual Device-Based Performance Modeling, Zachary Jones
A Framework For Virtual Device Driver Development And Virtual Device-Based Performance Modeling, Zachary Jones
All Dissertations
Operating system virtualization tools such as VMWare, XEN, and Linux KVM export only minimally capable SVGA graphics adapters. This paper describes the design and implementation of system
that virtualizes high-performance graphics cards of arbitrary design to support the construction of authentic device drivers. Drivers written for the virtual cards can be used verbatim, without special function calls or kernel modifications, as drivers for real cards, should real cards of the same design exist. While this allows for arbitrary design, it is not able to model performance characteristics. We describe a new kernel system that allows for arbitrarily changing the performance …
Evolutionary Strategies For Data Mining, Rose Lowe
Evolutionary Strategies For Data Mining, Rose Lowe
All Dissertations
Learning classifier systems (LCS) have been successful in generating rules for solving classification problems in data mining. The rules are of the form IF condition THEN action. The condition encodes the features of the input space and the action encodes the class label. What is lacking in those systems is the ability to express each feature using a function that is appropriate for that feature. The genetic algorithm is capable of doing this but cannot because only one type of membership function
is provided. Thus, the genetic algorithm learns only the shape and placement of the membership function, and in …
Batch Testing, Adaptive Algorithms, And Heuristic Applications For Stable Marriage Problems, John Dabney
Batch Testing, Adaptive Algorithms, And Heuristic Applications For Stable Marriage Problems, John Dabney
All Dissertations
In this dissertation we focus on different variations of the stable matching (marriage) problem, initially posed by Gale and Shapley in 1962. In this problem, preference lists are used to match n men with n women in such a way that no (man, woman) pair exists that would both prefer each other over their current partners. These two would be considered a blocking pair, preventing a matching from being considered stable. In our research, we study three different versions of this problem.
First, we consider batch testing of stable marriage solutions. Gusfield and Irving presented an open problem in their …
Approximation Algorithms For Network Interdiction And Fortification Problems, Adam Whitley
Approximation Algorithms For Network Interdiction And Fortification Problems, Adam Whitley
All Dissertations
This dissertation discusses algorithms and results on several NP–hard graph problems which can all be classified as network interdiction and network fortification problems.
The first problem studied, the multiway cut problem, is a generalization of the well–studied s–t min–cut problem, in which we must remove a minimum–cost subset of edges from a graph so that r > 2 designated terminals become disconnected from each other. We investigate an approximation algorithm for general r with a relatively simple analysis guaranteeing an approximation ratio ≤ 1.4647 − epsilonr, where epsilonr is a small constant related to the number of terminals …
A Reasoning Framework For Dependability In Software Architectures, Tacksoo Im
A Reasoning Framework For Dependability In Software Architectures, Tacksoo Im
All Dissertations
The degree to which a software system possesses specified levels of software quality attributes, such as performance and modifiability, often have more influence on the success and failure of those systems than the functional requirements. One method of improving the level of a software quality that a product possesses is to reason about the structure of the software architecture in terms of how well the structure supports the quality. This is accomplished by reasoning through software quality attribute scenarios while designing the software architecture of the system.
As society relies more heavily on software systems, the dependability of those systems …
Debugging Techniques For Locating Defects In Software Architectures, Kyungsoo Im
Debugging Techniques For Locating Defects In Software Architectures, Kyungsoo Im
All Dissertations
The explicit design of the architecture for a software product is a well established part of development projects. As the software architecture descriptions are becoming larger and more complex, there is more likelihood of defects being present in the software architecture. Studies have shown that a defect in the software architecture that has propagated to the development phase is very expensive to fix. To prevent such propagation of defects, this research proposes to provide debugging support for software architecture design.
Debugging is commonly used in programming languages to effectively find the cause of a failure and locate the error to …
A Computational Framework To Support The Automated Analysis Of Routine Electroencephalographic Data, William Pressly, Jr.
A Computational Framework To Support The Automated Analysis Of Routine Electroencephalographic Data, William Pressly, Jr.
All Dissertations
Epilepsy is a condition in which a patient has multiple unprovoked seizures which are not precipitated by another medical condition. It is a common neurological disorder that afflicts 1% of the population of the US, and is sometimes hard to diagnose if seizures are infrequent. Routine Electroencephalography (rEEG), where the electrical potentials of the brain are recorded on the scalp of a patient, is one of the main tools for diagnosing because rEEG can reveal indicators of epilepsy when patients are in a non-seizure state. Interpretation of rEEG is difficult and studies have shown that 20-30% of patients at specialized …
Event-Driven Similarity And Classification Of Scanpaths, Thomas Grindinger
Event-Driven Similarity And Classification Of Scanpaths, Thomas Grindinger
All Dissertations
Eye tracking experiments often involve recording the pattern of deployment of visual attention over the stimulus as viewers perform a given task (e.g., visual search). It is useful in training applications, for example, to make available an expert's sequence of eye movements, or scanpath, to novices for their inspection and subsequent learning. It may also be potentially useful to be able to assess the conformance of the novice's scanpath to that of the expert. A computational tool is proposed that provides a framework for performing such classification, based on the use of a probabilistic machine learning algorithm. The approach was …
Pslr(1): Pseudo-Scannerless Minimal Lr(1) For The Deterministic Parsing Of Composite Languages, Joel Denny
Pslr(1): Pseudo-Scannerless Minimal Lr(1) For The Deterministic Parsing Of Composite Languages, Joel Denny
All Dissertations
Composite languages are composed of multiple sub-languages. Examples include the parser specification languages read by parser generators like Yacc, modern extensible languages with complex layers of domain-specific sub-languages, and even traditional programming languages like C and C++. In this dissertation, we describe PSLR(1), a new scanner-based LR(1) parser generation system that automatically eliminates scanner conflicts typically caused by language composition. The fundamental premise of PSLR(1) is the pseudo-scanner, a scanner that only recognizes tokens accepted by the current parser state. However, use of the pseudo-scanner raises several unique challenges, for which we describe a novel set of solutions. One major …
Virtual Organization Clusters: Self-Provisioned Clouds On The Grid, Michael Murphy
Virtual Organization Clusters: Self-Provisioned Clouds On The Grid, Michael Murphy
All Dissertations
Virtual Organization Clusters (VOCs) provide a novel architecture for overlaying dedicated cluster systems on existing grid infrastructures. VOCs provide customized, homogeneous execution environments on a per-Virtual Organization basis, without the cost of physical cluster construction or the overhead of per-job containers. Administrative access and overlay network capabilities are granted to Virtual Organizations (VOs) that choose to implement VOC technology, while the system remains completely transparent to end users and non-participating VOs. Unlike alternative systems that require explicit leases, VOCs are autonomically self-provisioned according to configurable usage policies. As a grid computing architecture, VOCs are designed to be technology agnostic and …
Architecture Optimization, Training Convergence And Network Estimation Robustness Of A Fully Connected Recurrent Neural Network, Xiaoyu Wang
All Dissertations
Recurrent neural networks (RNN) have been rapidly developed in recent years. Applications of RNN can be found in system identification, optimization, image processing, pattern reorganization, classification, clustering, memory association, etc.
In this study, an optimized RNN is proposed to model nonlinear dynamical systems. A fully connected RNN is developed first which is modified from a fully forward connected neural network (FFCNN) by accommodating recurrent connections among its hidden neurons. In addition, a destructive structure optimization algorithm is applied and the extended Kalman filter (EKF) is adopted as a network's training algorithm. These two algorithms can seamlessly work together to generate …
Creating A Biomedical Ontology Indexed Search Engine To Improve The Semantic Relevance Of Retreived Medical Text, William Taylor Ii
Creating A Biomedical Ontology Indexed Search Engine To Improve The Semantic Relevance Of Retreived Medical Text, William Taylor Ii
All Dissertations
Medical Subject Headings (MeSH) is a controlled vocabulary used by the National Library of Medicine to index medical articles, abstracts, and journals contained within the MEDLINE database. Although MeSH imposes uniformity and consistency in the indexing process, it has been proven that using MeSH indices only result in a small increase in precision over free-text indexing. Moreover, studies have shown that the use of controlled vocabularies in the indexing process is not an effective method to increase semantic relevance in information retrieval.
To address the need for semantic relevance, we present an ontology-based information retrieval system for the MEDLINE collection …
Examining The Behavioral Intentions Of Older Adults As Virtual Tourists In The Context Of A Second Life Destination, Dorinda Christian
Examining The Behavioral Intentions Of Older Adults As Virtual Tourists In The Context Of A Second Life Destination, Dorinda Christian
All Dissertations
ABSTRACT
Tourism opportunities are being promoted heavily on the web, yet one of the largest and most lucrative markets, older adults are least likely to use the internet. In an effort to explore barriers to and potential acceptance of technology for tourism experiences, this study followed closely ten older adults through a learning process with technology. Qualitative methodology was used to explore in-depth the experience of these older adults being exposed to online virtual world technology for the first time and exploring the process by which technology acceptance takes place. The findings indicate that online virtual world such as Second …