Computer Sciences Commons^™

Generalized Techniques For Using System Execution Traces To Support Software Performance Analysis, Thelge Manjula Peiris

Open Access Dissertations

This dissertation proposes generalized techniques to support software performance analysis using system execution traces in the absence of software development artifacts such as source code. The proposed techniques do not require modifications to the source code, or to the software binaries, for the purpose of software analysis (non-intrusive). The proposed techniques are also not tightly coupled to the architecture specific details of the system being analyzed. This dissertation extends the current techniques of using system execution traces to evaluate software performance properties, such as response times, service times. The dissertation also proposes a novel technique to auto-construct a dataflow model …

Neural Decomposition Of Time-Series Data For Effective Generalization, Luke Godfrey

Graduate Theses and Dissertations

We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used to perform a Fourier-like decomposition of training samples into a sum of sinusoids, augmented by units with nonperiodic activation functions to capture linear trends and other nonperiodic components. We show how careful weight initialization can be combined with regularization to form a simple model that generalizes well. Our method generalizes effectively on the Mackey-Glass series, a dataset of unemployment rates as reported by the U.S. Department of Labor Statistics, a time-series of monthly international …

Evaluating The Intrinsic Similarity Between Neural Networks, Stephen Charles Ashmore

Graduate Theses and Dissertations

We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still generalize differently. FBA enables a diversity of applications, including visualization and canonicalization of neural networks, ensembles, and cross-over between unrelated neural networks in evolutionary optimization. We describe the FBA algorithm, and describe implementations for three applications: genetic algorithms, visualization, and ensembles. We demonstrate FBA's usefulness by comparing a …

3d Reconstruction Of Close Range Objects Using Free And Open Source Software And Raspberry Pi Technologies, Juan Lorenzo Monrreal

Theses and Dissertations

Existing 3D rendering open source software along with Raspberry Pi technology can be used to create an affordable method and workflow for time efficient, accurate and quality scans for 3D printing. The emergence of technology spurs a technological community working to progress in a collaborative effort. This brings a potential to the possibility of efficient and economical solutions to emerging problems, in this case, the ability to render three dimensional scans using free and open source software as well as Raspberry Pi technology. The focus of this paper will be divided into three different aspects including the background needed to …

Automatic User Profile Construction For A Personalized News Recommender System Using Twitter, Shiva Theja Reddy Gopidi

Graduate Theses and Dissertations

Modern society has now grown accustomed to reading online or digital news. However, the huge corpus of information available online poses a challenge to users when trying to find relevant articles. A hybrid system “Personalized News Recommender Using Twitter’ has been developed to recommend articles to a user based on the popularity of the articles and also the profile of the user. The hybrid system is a fusion of a collaborative recommender system developed using tweets from the “Twitter” public timeline and a content recommender system based the user’s past interests summarized in their conceptual user profile. In previous work, …

Interpretation At The Controller's Edge: The Role Of Graphical User Interfaces In Virtual Archaeology, Tyler Duane Johnson

Graduate Theses and Dissertations

The important role of graphical user interfaces (GUIs) as a medium of interaction with technology is well established in the world of media design, but has not received significant attention in the field of virtual archaeology. GUIs provide interactive capabilities and contextual information for 3D content such as structure-from-motion (SFM) models, and can represent the difference between "raw data" and thoughtful, skilled scholarly publications. This project explores the implications of a GUI created with the game engine Unity 3D (Unity) for a series of SFM models recorded at a structure known as the Area B House at the ancient central …

Use Of A Simulated Directional Social Network To Compare Measures Of User Influence, Jose G. Villarreal Jr.

Theses and Dissertations - UTB/UTPA

This paper proposes a new method for measuring user influence in directional social networks, derived from the works of Reilly et al. and Cha et al. The method being proposed in this paper considers an element from each of the two works. The first is the ratio of ‘messages forwarded’ over ‘messages posted’. The second element is the size of the audience. The second part of this study entails modeling and simulating an online social network. Using a data sample from the Twitter network to implement the simulation, it is going to allow us to compare the methods that are …

Efficient Query Processing Over Uncertain Road Networks, Bamikole A. Ogundele

Theses and Dissertations - UTB/UTPA

One of the fundamental problems on spatial road networks has been the shortest traveling time query, with applications such as location-based services (LBS) and trip planning. Algorithms have been made for the shortest time queries in deterministic road networks, in which vertices and edges are known with certainty. Emerging technologies are available and make it easier to acquire information about the traffic. In this paper, we consider uncertain road networks, in which speeds of vehicles are imprecise and probabilistic. We will focus on one important query type, continuous probabilistic shortest traveling time query (CPSTTQ), which retrieves sets of objects that …

Sensitivity Of Mixed Models To Computational Algorithms Of Time Series Data, Gunaime Nevine

Doctoral Dissertations

Statistical analysis is influenced by implementation of the algorithms used to execute the computations associated with various statistical techniques. Over many years; very important criteria for model comparison has been studied and examined, and two algorithms on a single dataset have been performed numerous times. The goal of this research is not comparing two or more models on one dataset, but comparing models with numerical algorithms that have been used to solve them on the same dataset.

In this research, different models have been broadly applied in modeling and their contrasting which are affected by the numerical algorithms in different …