ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 87
Description
The increasing popularity of Twitter renders improved trustworthiness and relevance assessment of tweets much more important for search. However, given the limitations on the size of tweets, it is hard to extract measures for ranking from the tweet's content alone. I propose a method of ranking tweets by generating a reputation score for each tweet that is based not just on content, but also additional information from the Twitter ecosystem that consists of users, tweets, and the web pages that tweets link to. This information is obtained by modeling the Twitter ecosystem as a three-layer graph. The reputation score is used to power two novel methods of ranking tweets by propagating the reputation over an agreement graph based on tweets' content similarity. Additionally, I show how the agreement graph helps counter tweet spam. An evaluation of my method on 16~million tweets from the TREC 2011 Microblog Dataset shows that it doubles the precision over baseline Twitter Search and achieves higher precision than current state of the art method. I present a detailed internal empirical evaluation of RAProp in comparison to several alternative approaches proposed by me, as well as external evaluation in comparison to the current state of the art method.
ContributorsRavikumar, Srijith (Author) / Kambhampati, Subbarao (Thesis advisor) / Davulcu, Hasan (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Automating aspects of biocuration through biomedical information extraction could significantly impact biomedical research by enabling greater biocuration throughput and improving the feasibility of a wider scope. An important step in biomedical information extraction systems is named entity recognition (NER), where mentions of entities such as proteins and diseases are located within natural-language text and their semantic type is determined. This step is critical for later tasks in an information extraction pipeline, including normalization and relationship extraction. BANNER is a benchmark biomedical NER system using linear-chain conditional random fields and the rich feature set approach. A case study with BANNER locating genes and proteins in biomedical literature is described. The first corpus for disease NER adequate for use as training data is introduced, and employed in a case study of disease NER. The first corpus locating adverse drug reactions (ADRs) in user posts to a health-related social website is also described, and a system to locate and identify ADRs in social media text is created and evaluated. The rich feature set approach to creating NER feature sets is argued to be subject to diminishing returns, implying that additional improvements may require more sophisticated methods for creating the feature set. This motivates the first application of multivariate feature selection with filters and false discovery rate analysis to biomedical NER, resulting in a feature set at least 3 orders of magnitude smaller than the set created by the rich feature set approach. Finally, two novel approaches to NER by modeling the semantics of token sequences are introduced. The first method focuses on the sequence content by using language models to determine whether a sequence resembles entries in a lexicon of entity names or text from an unlabeled corpus more closely. The second method models the distributional semantics of token sequences, determining the similarity between a potential mention and the token sequences from the training data by analyzing the contexts where each sequence appears in a large unlabeled corpus. The second method is shown to improve the performance of BANNER on multiple data sets.
ContributorsLeaman, James Robert (Author) / Gonzalez, Graciela (Thesis advisor) / Baral, Chitta (Thesis advisor) / Cohen, Kevin B (Committee member) / Liu, Huan (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
The effect of earthquake-induced liquefaction on the local void ratio distribution of cohesionless soil is evaluated using x-ray computed tomography (CT) and an advanced image processing software package. Intact, relatively undisturbed specimens of cohesionless soil were recovered before and after liquefaction by freezing and coring soil deposits created by pluviation and by sedimentation through water. Pluviated soil deposits were liquefied in the small geotechnical centrifuge at the University of California at Davis shared-use National Science Foundation (NSF)-supported Network for Earthquake Engineering Simulation (NEES) facility. A soil deposit created by sedimentation through water was liquefied on a small shake table in the Arizona State University geotechnical laboratory. Initial centrifuge tests employed Ottawa 20-30 sand but this material proved to be too coarse to liquefy in the centrifuge. Therefore, subsequent centrifuge tests employed Ottawa F60 sand. The shake table test employed Ottawa 20-30 sand. Recovered cores were stabilized by impregnation with optical grade epoxy and sent to the University of Texas at Austin NSF-supported facility at the University of Texas at Austin for high-resolution CT scanning of geologic media. The local void ratio distribution of a CT-scanned core of Ottawa 20-30 sand evaluated using Avizo® Fire, a commercially available advanced program for image analysis, was compared to the local void ratio distribution established on the same core by analysis of optical images to demonstrate that analysis of the CT scans gave similar results to optical methods. CT scans were subsequently conducted on liquefied and not-liquefied specimens of Ottawa 20-30 sand and Ottawa F60 sand. The resolution of F60 specimens was inadequate to establish the local void ratio distribution. Results of the analysis of the Ottawa 20-30 specimens recovered from the model built for the shake table test showed that liquefaction can substantially influence the variability in local void ratio, increasing the degree of non-homogeneity in the specimen.
ContributorsGutierrez, Angel (Author) / Kavazanjian, Edward (Thesis advisor) / Houston, Sandra (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2013
Description
Heating of asphalt during production and construction causes the volatilization and oxidation of binders used in mixes. Volatilization and oxidation causes degradation of asphalt pavements by increasing the stiffness of the binders, increasing susceptibility to cracking and negatively affecting the functional and structural performance of the pavements. Degradation of asphalt binders by volatilization and oxidation due to high production temperature occur during early stages of pavement life and are known as Short Term Aging (STA). Elevated temperatures and increased exposure time to elevated temperatures causes increased STA of asphalt. The objective of this research was to investigate how elevated mixing temperatures and exposure time to elevated temperatures affect aging and stiffening of binders, thus influencing properties of the asphalt mixtures. The study was conducted in two stages. The first stage evaluated STA effect of asphalt binders. It involved aging two Performance Graded (PG) virgin asphalt binders, PG 76-16 and PG 64-22 at two different temperatures and durations, then measuring their viscosities. The second stage involved evaluating the effects of elevated STA temperature and time on properties of the asphalt mixtures. It involved STA of asphalt mixtures produced in the laboratory with the PG 64-22 binder at mixing temperatures elevated 25OF above standard practice; STA times at 2 and 4 hours longer than standard practices, and then compacted in a gyratory compactor. Dynamic modulus (E*) and Indirect Tensile Strength (IDT) were measured for the aged mixtures for each temperature and duration to determine the effect of different aging times and temperatures on the stiffness and fatigue properties of the aged asphalt mixtures. The binder test results showed that in all cases, there was increased viscosity. The results showed the highest increase in viscosity resulted from increased aging time. The results also indicated that PG 64-22 was more susceptible to elevated STA temperature and extended time than the PG 76-16 binders. The asphalt mixture test results confirmed the expected outcome that increasing the STA and mixing temperature by 25oF alters the stiffness of mixtures. Significant change in the dynamic modulus mostly occurred at four hour increase in STA time regardless of temperature.
ContributorsLolly, Rubben (Author) / Kaloush, Kamil (Thesis advisor) / Bearup, Wylie (Committee member) / Zapata, Claudia (Committee member) / Mamlouk, Michael (Committee member) / Arizona State University (Publisher)
Created2013
Description
Unsaturated soil mechanics is becoming a part of geotechnical engineering practice, particularly in applications to moisture sensitive soils such as expansive and collapsible soils and in geoenvironmental applications. The soil water characteristic curve, which describes the amount of water in a soil versus soil suction, is perhaps the most important soil property function for application of unsaturated soil mechanics. The soil water characteristic curve has been used extensively for estimating unsaturated soil properties, and a number of fitting equations for development of soil water characteristic curves from laboratory data have been proposed by researchers. Although not always mentioned, the underlying assumption of soil water characteristic curve fitting equations is that the soil is sufficiently stiff so that there is no change in total volume of the soil while measuring the soil water characteristic curve in the laboratory, and researchers rarely take volume change of soils into account when generating or using the soil water characteristic curve. Further, there has been little attention to the applied net normal stress during laboratory soil water characteristic curve measurement, and often zero to only token net normal stress is applied. The applied net normal stress also affects the volume change of the specimen during soil suction change. When a soil changes volume in response to suction change, failure to consider the volume change of the soil leads to errors in the estimated air-entry value and the slope of the soil water characteristic curve between the air-entry value and the residual moisture state. Inaccuracies in the soil water characteristic curve may lead to inaccuracies in estimated soil property functions such as unsaturated hydraulic conductivity. A number of researchers have recently recognized the importance of considering soil volume change in soil water characteristic curves. The study of correct methods of soil water characteristic curve measurement and determination considering soil volume change, and impacts on the unsaturated hydraulic conductivity function was of the primary focus of this study. Emphasis was placed upon study of the effect of volume change consideration on soil water characteristic curves, for expansive clays and other high volume change soils. The research involved extensive literature review and laboratory soil water characteristic curve testing on expansive soils. The effect of the initial state of the specimen (i.e. slurry versus compacted) on soil water characteristic curves, with regard to volume change effects, and effect of net normal stress on volume change for determination of these curves, was studied for expansive clays. Hysteresis effects were included in laboratory measurements of soil water characteristic curves as both wetting and drying paths were used. Impacts of soil water characteristic curve volume change considerations on fluid flow computations and associated suction-change induced soil deformations were studied through numerical simulations. The study includes both coupled and uncoupled flow and stress-deformation analyses, demonstrating that the impact of volume change consideration on the soil water characteristic curve and the estimated unsaturated hydraulic conductivity function can be quite substantial for high volume change soils.
ContributorsBani Hashem, Elham (Author) / Houston, Sandra L. (Thesis advisor) / Kavazanjian, Edward (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2013
Description
Data mining is increasing in importance in solving a variety of industry problems. Our initiative involves the estimation of resource requirements by skill set for future projects by mining and analyzing actual resource consumption data from past projects in the semiconductor industry. To achieve this goal we face difficulties like data with relevant consumption information but stored in different format and insufficient data about project attributes to interpret consumption data. Our first goal is to clean the historical data and organize it into meaningful structures for analysis. Once the preprocessing on data is completed, different data mining techniques like clustering is applied to find projects which involve resources of similar skillsets and which involve similar complexities and size. This results in "resource utilization templates" for groups of related projects from a resource consumption perspective. Then project characteristics are identified which generate this diversity in headcounts and skillsets. These characteristics are not currently contained in the data base and are elicited from the managers of historical projects. This represents an opportunity to improve the usefulness of the data collection system for the future. The ultimate goal is to match the product technical features with the resource requirement for projects in the past as a model to forecast resource requirements by skill set for future projects. The forecasting model is developed using linear regression with cross validation of the training data as the past project execution are relatively few in number. Acceptable levels of forecast accuracy are achieved relative to human experts' results and the tool is applied to forecast some future projects' resource demand.
ContributorsBhattacharya, Indrani (Author) / Sen, Arunabha (Thesis advisor) / Kempf, Karl G. (Thesis advisor) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Contemporary online social platforms present individuals with social signals in the form of news feed on their peers' activities. On networks such as Facebook, Quora, network operator decides how that information is shown to an individual. Then the user, with her own interests and resource constraints selectively acts on a subset of items presented to her. The network operator again, shows that activity to a selection of peers, and thus creating a behavioral loop. That mechanism of interaction and information flow raises some very interesting questions such as: can network operator design social signals to promote a particular activity like sustainability, public health care awareness, or to promote a specific product? The focus of my thesis is to answer that question. In this thesis, I develop a framework to personalize social signals for users to guide their activities on an online platform. As the result, we gradually nudge the activity distribution on the platform from the initial distribution p to the target distribution q. My work is particularly applicable to guiding collaborations, guiding collective actions, and online advertising. In particular, I first propose a probabilistic model on how users behave and how information flows on the platform. The main part of this thesis after that discusses the Influence Individuals through Social Signals (IISS) framework. IISS consists of four main components: (1) Learner: it learns users' interests and characteristics from their historical activities using Bayesian model, (2) Calculator: it uses gradient descent method to compute the intermediate activity distributions, (3) Selector: it selects users who can be influenced to adopt or drop specific activities, (4) Designer: it personalizes social signals for each user. I evaluate the performance of IISS framework by simulation on several network topologies such as preferential attachment, small world, and random. I show that the framework gradually nudges users' activities to approach the target distribution. I use both simulation and mathematical method to analyse convergence properties such as how fast and how close we can approach the target distribution. When the number of activities is 3, I show that for about 45% of target distributions, we can achieve KL-divergence as low as 0.05. But for some other distributions KL-divergence can be as large as 0.5.
ContributorsLe, Tien D (Author) / Sundaram, Hari (Thesis advisor) / Davulcu, Hasan (Thesis advisor) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2014
Description
This thesis presents a probabilistic evaluation of multiple laterally loaded drilled pier foundation design approaches using extensive data from a geotechnical investigation for a high voltage electric transmission line. A series of Monte Carlo simulations provide insight about the computed level of reliability considering site standard penetration test blow count value variability alone (i.e., assuming all other aspects of the design problem do not contribute error or bias). Evaluated methods include Eurocode 7 Geotechnical Design procedures, the Federal Highway Administration drilled shaft LRFD design method, the Electric Power Research Institute transmission foundation design procedure and a site specific variability based approach previously suggested by the author of this thesis and others. The analysis method is defined by three phases: a) Evaluate the spatial variability of an existing subsurface database. b) Derive theoretical foundation designs from the database in accordance with the various design methods identified. c) Conduct Monti Carlo Simulations to compute the reliability of the theoretical foundation designs. Over several decades, reliability-based foundation design (RBD) methods have been developed and implemented to varying degrees for buildings, bridges, electric systems and other structures. In recent years, an effort has been made by researchers, professional societies and other standard-developing organizations to publish design guidelines, manuals and standards concerning RBD for foundations. Most of these approaches rely on statistical methods for quantifying load and resistance probability distribution functions with defined reliability levels. However, each varies with regard to the influence of site-specific variability on resistance. An examination of the influence of site-specific variability is required to provide direction for incorporating the concept into practical RBD design methods. Recent surveys of transmission line engineers by the Electric Power Research Institute (EPRI) demonstrate RBD methods for the design of transmission line foundations have not been widely adopted. In the absence of a unifying design document with established reliability goals, transmission line foundations have historically performed very well, with relatively few failures. However, such a track record with no set reliability goals suggests, at least in some cases, a financial premium has likely been paid.
ContributorsHeim, Zackary (Author) / Houston, Sandra (Thesis advisor) / Witczak, Matthew (Committee member) / Kavazanjian, Edward (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2014
Description
Most data cleaning systems aim to go from a given deterministic dirty database to another deterministic but clean database. Such an enterprise pre–supposes that it is in fact possible for the cleaning process to uniquely recover the clean versions of each dirty data tuple. This is not possible in many cases, where the most a cleaning system can do is to generate a (hopefully small) set of clean candidates for each dirty tuple. When the cleaning system is required to output a deterministic database, it is forced to pick one clean candidate (say the "most likely" candidate) per tuple. Such an approach can lead to loss of information. For example, consider a situation where there are three equally likely clean candidates of a dirty tuple. An appealing alternative that avoids such an information loss is to abandon the requirement that the output database be deterministic. In other words, even though the input (dirty) database is deterministic, I allow the reconstructed database to be probabilistic. Although such an approach does avoid the information loss, it also brings forth several challenges. For example, how many alternatives should be kept per tuple in the reconstructed database? Maintaining too many alternatives increases the size of the reconstructed database, and hence the query processing time. Second, while processing queries on the probabilistic database may well increase recall, how would they affect the precision of the query processing? In this thesis, I investigate these questions. My investigation is done in the context of a data cleaning system called BayesWipe that has the capability of producing multiple clean candidates per each dirty tuple, along with the probability that they are the correct cleaned version. I represent these alternatives as tuples in a tuple disjoint probabilistic database, and use the Mystiq system to process queries on it. This probabilistic reconstruction (called BayesWipe–PDB) is compared to a deterministic reconstruction (called BayesWipe–DET)—where the most likely clean candidate for each tuple is chosen, and the rest of the alternatives discarded.
ContributorsRihan, Preet Inder Singh (Author) / Kambhampati, Subbarao (Thesis advisor) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2013
Description
As the size and scope of valuable datasets has exploded across many industries and fields of research in recent years, an increasingly diverse audience has sought out effective tools for their large-scale data analytics needs. Over this period, machine learning researchers have also been very prolific in designing improved algorithms which are capable of finding the hidden structure within these datasets. As consumers of popular Big Data frameworks have sought to apply and benefit from these improved learning algorithms, the problems encountered with the frameworks have motivated a new generation of Big Data tools to address the shortcomings of the previous generation. One important example of this is the improved performance in the newer tools with the large class of machine learning algorithms which are highly iterative in nature. In this thesis project, I set about to implement a low-rank matrix completion algorithm (as an example of a highly iterative algorithm) within a popular Big Data framework, and to evaluate its performance processing the Netflix Prize dataset. I begin by describing several approaches which I attempted, but which did not perform adequately. These include an implementation of the Singular Value Thresholding (SVT) algorithm within the Apache Mahout framework, which runs on top of the Apache Hadoop MapReduce engine. I then describe an approach which uses the Divide-Factor-Combine (DFC) algorithmic framework to parallelize the state-of-the-art low-rank completion algorithm Orthogoal Rank-One Matrix Pursuit (OR1MP) within the Apache Spark engine. I describe the results of a series of tests running this implementation with the Netflix dataset on clusters of various sizes, with various degrees of parallelism. For these experiments, I utilized the Amazon Elastic Compute Cloud (EC2) web service. In the final analysis, I conclude that the Spark DFC + OR1MP implementation does indeed produce competitive results, in both accuracy and performance. In particular, the Spark implementation performs nearly as well as the MATLAB implementation of OR1MP without any parallelism, and improves performance to a significant degree as the parallelism increases. In addition, the experience demonstrates how Spark's flexible programming model makes it straightforward to implement this parallel and iterative machine learning algorithm.
ContributorsKrouse, Brian (Author) / Ye, Jieping (Thesis advisor) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2014