Theses and Dissertations
This collection includes both ASU Theses and Dissertations, submitted by graduate students, and the Barrett, Honors College theses submitted by undergraduate students.
Displaying 1 - 10 of 96
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
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
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
Description
Membrane proteins are a vital part of cellular structure. They are directly involved in many important cellular functions, such as uptake, signaling, respiration, and photosynthesis, among others. Despite their importance, however, less than 500 unique membrane protein structures have been determined to date. This is due to several difficulties with macromolecular crystallography, primarily the difficulty of growing large, well-ordered protein crystals. Since the first proof of concept for femtosecond nanocrystallography showing that diffraction patterns can be collected on extremely small crystals, thus negating the need to grow larger crystals, there have been many exciting advancements in the field. The technique has been proven to show high spatial resolution, thus making it a viable method for structural biology. However, due to the ultrafast nature of the technique, which allows for a lack of radiation damage in imaging, even more interesting experiments are possible, and the first temporal and spatial images of an undamaged structure could be acquired. This concept was denoted as time-resolved femtosecond nanocrystallography.
This dissertation presents on the first time-resolved data set of Photosystem II where structural changes can actually be seen without radiation damage. In order to accomplish this, new crystallization techniques had to be developed so that enough crystals could be made for the liquid jet to deliver a fully hydrated stream of crystals to the high-powered X-ray source. These changes are still in the preliminary stages due to the slightly lower resolution data obtained, but they are still a promising show of the power of this new technique. With further optimization of crystal growth methods and quality, injection technique, and continued development of data analysis software, it is only a matter of time before the ability to make movies of molecules in motion from X-ray diffraction snapshots in time exists. The work presented here is the first step in that process.
This dissertation presents on the first time-resolved data set of Photosystem II where structural changes can actually be seen without radiation damage. In order to accomplish this, new crystallization techniques had to be developed so that enough crystals could be made for the liquid jet to deliver a fully hydrated stream of crystals to the high-powered X-ray source. These changes are still in the preliminary stages due to the slightly lower resolution data obtained, but they are still a promising show of the power of this new technique. With further optimization of crystal growth methods and quality, injection technique, and continued development of data analysis software, it is only a matter of time before the ability to make movies of molecules in motion from X-ray diffraction snapshots in time exists. The work presented here is the first step in that process.
ContributorsKupitz, Christopher (Author) / Fromme, Petra (Thesis advisor) / Spence, John C. (Thesis advisor) / Redding, Kevin (Committee member) / Ros, Alexandra (Committee member) / Arizona State University (Publisher)
Created2014
Description
Twitter is a micro-blogging platform where the users can be social, informational or both. In certain cases, users generate tweets that have no "hashtags" or "@mentions"; we call it an orphaned tweet. The user will be more interested to find more "context" of an orphaned tweet presumably to engage with his/her friend on that topic. Finding context for an Orphaned tweet manually is challenging because of larger social graph of a user , the enormous volume of tweets generated per second, topic diversity, and limited information from tweet length of 140 characters. To help the user to get the context of an orphaned tweet, this thesis aims at building a hashtag recommendation system called TweetSense, to suggest hashtags as a context or metadata for the orphaned tweets. This in turn would increase user's social engagement and impact Twitter to maintain its monthly active online users in its social network. In contrast to other existing systems, this hashtag recommendation system recommends personalized hashtags by exploiting the social signals of users in Twitter. The novelty with this system is that it emphasizes on selecting the suitable candidate set of hashtags from the related tweets of user's social graph (timeline).The system then rank them based on the combination of features scores computed from their tweet and user related features. It is evaluated based on its ability to predict suitable hashtags for a random sample of tweets whose existing hashtags are deliberately removed for evaluation. I present a detailed internal empirical evaluation of TweetSense, as well as an external evaluation in comparison with current state of the art method.
ContributorsVijayakumar, Manikandan (Author) / Kambhampati, Subbarao (Thesis advisor) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2014
Description
The utilization of solar energy requires an efficient means of its storage as fuel. In bio-inspired artificial photosynthesis, light energy can be used to drive water oxidation, but catalysts that produce molecular oxygen from water are required. This dissertation demonstrates a novel complex utilizing earth-abundant Ni in combination with glycine as an efficient catalyst with a modest overpotential of 0.475 ± 0.005 V for a current density of 1 mA/cm2 at pH 11. The production of molecular oxygen at a high potential was verified by measurement of the change in oxygen concentration, yielding a Faradaic efficiency of 60 ± 5%. This Ni species can achieve a current density of 4 mA/cm2 that persists for at least 10 hours. Based upon the observed pH dependence of the current amplitude and oxidation/reduction peaks, the catalysis is an electron-proton coupled process. In addition, to investigate the binding of divalent metals to proteins, four peptides were designed and synthesized with carboxylate and histidine ligands. The binding of the metals was characterized by monitoring the metal-induced changes in circular dichroism spectra. Cyclic voltammetry demonstrated that bound copper underwent a Cu(I)/Cu(II) oxidation/reduction change at a potential of approximately 0.32 V in a quasi-reversible process. The relative binding affinity of Mn(II), Fe(II), Co(II), Ni(II) and Cu(II) to the peptides is correlated with the stability constants of the Irving-Williams series for divalent metal ions. A potential application of these complexes of transition metals with amino acids or peptides is in the development of artificial photosynthetic cells.
ContributorsWang, Dong (Author) / Allen, James P. (Thesis advisor) / Ghirlanda, Giovanna (Committee member) / Redding, Kevin (Committee member) / Arizona State University (Publisher)
Created2014
Description
Cyanovirin-N (CVN) is a cyanobacterial lectin with potent anti-HIV activity, mediated by binding to the N-linked oligosaccharide moiety of the envelope protein gp120. CVN offers a scaffold to develop multivalent carbohydrate-binding proteins with tunable specificities and affinities. I present here biophysical calculations completed on a monomeric-stabilized mutant of cyanovirin-N, P51G-m4-CVN, in which domain A binding activity is abolished by four mutations; with comparisons made to CVNmutDB, in which domain B binding activity is abolished. Using Monte Carlo calculations and docking simulations, mutations in CVNmutDB were considered singularly, and the mutations E41A/G and T57A were found to impact the affinity towards dimannose the greatest. 15N-labeled proteins were titrated with Manα(1-2)Manα, while following chemical shift perturbations in NMR spectra. The mutants, E41A/G and T57A, had a larger Kd than P51G-m4-CVN, matching the trends predicted by the calculations. We also observed that the N42A mutation affects the local fold of the binding pocket, thus removing all binding to dimannose. Characterization of the mutant N53S showed similar binding affinity to P51G-m4-CVN. Using biophysical calculations allows us to study future iterations of models to explore affinities and specificities. In order to further elucidate the role of multivalency, I report here a designed covalent dimer of CVN, Nested cyanovirin-N (Nested CVN), which has four binding sites. Nested CVN was found to have comparable binding affinity to gp120 and antiviral activity to wt CVN. These results demonstrate the ability to create a multivalent, covalent dimer that has comparable results to that of wt CVN.
WW domains are small modules consisting of 32-40 amino acids that recognize proline-rich peptides and are found in many signaling pathways. We use WW domain sequences to explore protein folding by simulations using Zipping and Assembly Method. We identified five crucial contacts that enabled us to predict the folding of WW domain sequences based on those contacts. We then designed a folded WW domain peptide from an unfolded WW domain sequence by introducing native contacts at those critical positions.
WW domains are small modules consisting of 32-40 amino acids that recognize proline-rich peptides and are found in many signaling pathways. We use WW domain sequences to explore protein folding by simulations using Zipping and Assembly Method. We identified five crucial contacts that enabled us to predict the folding of WW domain sequences based on those contacts. We then designed a folded WW domain peptide from an unfolded WW domain sequence by introducing native contacts at those critical positions.
ContributorsWoodrum, Brian William (Author) / Ghirlanda, Giovanna (Thesis advisor) / Redding, Kevin (Committee member) / Wang, Xu (Committee member) / Arizona State University (Publisher)
Created2014