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 309
Filtering by
- All Subjects: Machine Learning
- All Subjects: Language
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
Description
The purpose of this study was to examine the attitudes and opinions of Navajo students toward the Navajo language and culture programs within the schools they were attending. Although in the final year of the No Child Left Behind, a majority of the 265 schools on and near the Navajo reservation have not been making Adequate Yearly Progress, a concern for the parents, teachers, administrators, school board members, and the Navajo Nation. The study entailed conducting a survey at five schools; three of which were not meeting the requirements of the No Child Left Behind. The purpose of the survey instrument (27 questions) administered to the students at the five schools was to examine their attitudes and opinions as to participating in Navajo language and culture programs, to determine if the programs assisted them in their academic achievements, and to examine whether these programs actually made a difference for schools in their Adequate Yearly Progress requirement Approximately 87% of 99 Navajo students, 55 boys and 58 girls, ages 9 through 14, Grades 3 through 8, who lived off the reservation in Flagstaff, Arizona and Gallup, New Mexico, and took the survey knew and spoke Navajo, but less fluently and not to a great extent. However, the students endorsed learning Navajo and strongly agreed that the Navajo language and culture should be part of the curriculum. Historically there have been schools such as the Rock Point Community School, Rough Rock Demonstration School, Borrego Pass Community School, and Ramah Community School that have been successful in their implementation of bilingual programs. The question presently facing Navajo educators is what type of programs would be successful within the context of the No Child Left Behind federal legislation. Can there be replications of successful Navajo language and culture programs into schools that are not making Adequate Yearly Progress?
ContributorsTsosie, David J (Author) / Spencer, Dee A. (Thesis advisor) / Appleton, Nicholas A. (Committee member) / Koerperich, Robbie (Committee member) / Arizona State University (Publisher)
Created2013
Description
This work presents two complementary studies that propose heuristic methods to capture characteristics of data using the ensemble learning method of random forest. The first study is motivated by the problem in education of determining teacher effectiveness in student achievement. Value-added models (VAMs), constructed as linear mixed models, use students’ test scores as outcome variables and teachers’ contributions as random effects to ascribe changes in student performance to the teachers who have taught them. The VAMs teacher score is the empirical best linear unbiased predictor (EBLUP). This approach is limited by the adequacy of the assumed model specification with respect to the unknown underlying model. In that regard, this study proposes alternative ways to rank teacher effects that are not dependent on a given model by introducing two variable importance measures (VIMs), the node-proportion and the covariate-proportion. These VIMs are novel because they take into account the final configuration of the terminal nodes in the constitutive trees in a random forest. In a simulation study, under a variety of conditions, true rankings of teacher effects are compared with estimated rankings obtained using three sources: the newly proposed VIMs, existing VIMs, and EBLUPs from the assumed linear model specification. The newly proposed VIMs outperform all others in various scenarios where the model was misspecified. The second study develops two novel interaction measures. These measures could be used within but are not restricted to the VAM framework. The distribution-based measure is constructed to identify interactions in a general setting where a model specification is not assumed in advance. In turn, the mean-based measure is built to estimate interactions when the model specification is assumed to be linear. Both measures are unique in their construction; they take into account not only the outcome values, but also the internal structure of the trees in a random forest. In a separate simulation study, under a variety of conditions, the proposed measures are found to identify and estimate second-order interactions.
ContributorsValdivia, Arturo (Author) / Eubank, Randall (Thesis advisor) / Young, Dennis (Committee member) / Reiser, Mark R. (Committee member) / Kao, Ming-Hung (Committee member) / Broatch, Jennifer (Committee member) / Arizona State University (Publisher)
Created2013
Description
In order to adapt to a new culture and new language, children of immigrant families are faced daily with the responsibility of being the intermediaries between the family and the host culture through their language proficiency (Weisskirch & Alva, 2002). This thesis looks into the experiences of English-Spanish bilingual children as they bridge the gap between the family and the non-Spanish speaking community through their interpreting/translating skills. With an emphasis on children of Mexican-origin, the goal is to further understand and illuminate how these children manage this communication in an adult society, their feelings and thoughts about their experiences, and the child's perceptions about the influence that this experience may or may not have on their future. A sample of seventeen children agreed to participate in a semi-structured face-to-face interview to share their experiences. The data from these interviews were analyzed using a thematic analysis approach (Braun & Clarke, 2006). A priori themes of circumstantial bilingual and adaptive parentification were the initial focus of the research while being open to emerging themes. The children's accounts of their experiences indicated primarily that the Mexican-origin values of familism and respeto (respect) were a significant influence on them when they interpreted/translated for their family. With these traditional cultural values and norms as the groundwork, the sub-themes of normalcy and stress emerged as supportive elements of the circumstantial bilingual experience. Furthermore, the theme of adaptive parentification and the sub-themes of choice, expectation/responsibility to assist, and equality to parents offered further insight on how adaptive parentification can result as the roles of these children change. There was an emergent theme, identity negotiation, which increases our understanding of what the circumstantial bilingual child encounters as the attempt is made to negotiate his identity as an individual who has to mediate language between two opposing cultures. Due to the language brokering responsibility that are bestowed upon these children, it is concluded that communicative support by the parents is a necessary component of the parent-child relationship in order to nurture and develop these children as they negotiate and create their identity to become the successful leaders of tomorrow.
ContributorsCayetano, Catalina (Author) / Mean, Lindsey (Thesis advisor) / Waldron, Vincent (Committee member) / Gaffney, Cynthia (Committee member) / Arizona State University (Publisher)
Created2013
Description
The purpose of this study is to investigate the literacy practices of three members of Alcoholics Anonymous (A.A.) and to explore how they use these practices to support and maintain their recovery in their lives. This study also aims to examine how each participant used specialist language, enacted certain identities and acquired the secondary Discourse in A.A. through literacy use. This dissertation study is the result of in-depth interviewing in which each participant was interviewed three times for 90-minutes. These interviews were then transcribed and analyzed using discourse analysis. Study results are presented in three chapters, each one designated to one of the participants. Within these chapters is a life history (chronology) of the participant leading up to the point in which they got sober. The chapters also include a thematic discourse analysis of the interview transcripts across themes of literacy practice and topics in A.A. A conclusion is then presented to investigate how literacy was used from a sociocultural perspective in the study. Due to the emotionally charged nature of this dissertation, it has been formatted to present the stories of the participants first, leaving the theoretical framework, literature review and research methods to be included as appendices to the main text.
ContributorsClausen, Jennifer Ann (Author) / Marsh, Josephine (Thesis advisor) / Hayes, Elisabeth (Committee member) / Serafini, Frank (Committee member) / Arizona State University (Publisher)
Created2013
Description
This study investigates the effectiveness of the use of Concept-Based Instruction (CBI) to facilitate the acquisition of Spanish mood distinctions by second semester second language learners of Spanish. The study focuses on the development of Spanish mood choice and the types of explanations (Rule-of-Thumb vs. Concept-based) used by five students before and after being exposed to Concept-Based Instruction regarding the choice of Spanish mood following various modalities .The students in this study were presented with a pedagogical treatment on Spanish mood choice that included general theoretical concepts based on Gal'perin's (1969, 1992) didactic models and acts of verbalization, which form part of a Concept-Based pedagogical approach. In order to ascertain the effectiveness of the use of concept-based tools to promote the ability to use Spanish mood appropriately over time, a pre and post-test was administered to the group in which students were asked to respond to prompts containing modalities that elicit the indicative and subjunctive moods, indicate their level of confidence in their response, and verbalize in writing a reason for their choice. The development of these abilities in learners exposed to CBI was assessed by comparing pre and post-test scores examining both forms and explanations for the indicative and subjunctive modality prompts given. Results showed that students continued to rely on Rule-of-Thumb explanations of mood choice but they did expand their use of conceptually-based reasoning. Although the quantitative and qualitative analyses of the results indicate that most students did improve their ability to make appropriate mood choices (forms and explanations) after the CBI treatment, the increased use of conceptually-based explanations for their mood choices led to both correct and incorrect responses.
ContributorsBeus, Eric (Author) / Lafford, Barbara (Thesis advisor) / Beas, Omar (Committee member) / Cerron-Palomino, Alvaro (Committee member) / Arizona State University (Publisher)
Created2013
Description
Image understanding has been playing an increasingly crucial role in vision applications. Sparse models form an important component in image understanding, since the statistics of natural images reveal the presence of sparse structure. Sparse methods lead to parsimonious models, in addition to being efficient for large scale learning. In sparse modeling, data is represented as a sparse linear combination of atoms from a "dictionary" matrix. This dissertation focuses on understanding different aspects of sparse learning, thereby enhancing the use of sparse methods by incorporating tools from machine learning. With the growing need to adapt models for large scale data, it is important to design dictionaries that can model the entire data space and not just the samples considered. By exploiting the relation of dictionary learning to 1-D subspace clustering, a multilevel dictionary learning algorithm is developed, and it is shown to outperform conventional sparse models in compressed recovery, and image denoising. Theoretical aspects of learning such as algorithmic stability and generalization are considered, and ensemble learning is incorporated for effective large scale learning. In addition to building strategies for efficiently implementing 1-D subspace clustering, a discriminative clustering approach is designed to estimate the unknown mixing process in blind source separation. By exploiting the non-linear relation between the image descriptors, and allowing the use of multiple features, sparse methods can be made more effective in recognition problems. The idea of multiple kernel sparse representations is developed, and algorithms for learning dictionaries in the feature space are presented. Using object recognition experiments on standard datasets it is shown that the proposed approaches outperform other sparse coding-based recognition frameworks. Furthermore, a segmentation technique based on multiple kernel sparse representations is developed, and successfully applied for automated brain tumor identification. Using sparse codes to define the relation between data samples can lead to a more robust graph embedding for unsupervised clustering. By performing discriminative embedding using sparse coding-based graphs, an algorithm for measuring the glomerular number in kidney MRI images is developed. Finally, approaches to build dictionaries for local sparse coding of image descriptors are presented, and applied to object recognition and image retrieval.
ContributorsJayaraman Thiagarajan, Jayaraman (Author) / Spanias, Andreas (Thesis advisor) / Frakes, David (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
With the increase in computing power and availability of data, there has never been a greater need to understand data and make decisions from it. Traditional statistical techniques may not be adequate to handle the size of today's data or the complexities of the information hidden within the data. Thus knowledge discovery by machine learning techniques is necessary if we want to better understand information from data. In this dissertation, we explore the topics of asymmetric loss and asymmetric data in machine learning and propose new algorithms as solutions to some of the problems in these topics. We also studied variable selection of matched data sets and proposed a solution when there is non-linearity in the matched data. The research is divided into three parts. The first part addresses the problem of asymmetric loss. A proposed asymmetric support vector machine (aSVM) is used to predict specific classes with high accuracy. aSVM was shown to produce higher precision than a regular SVM. The second part addresses asymmetric data sets where variables are only predictive for a subset of the predictor classes. Asymmetric Random Forest (ARF) was proposed to detect these kinds of variables. The third part explores variable selection for matched data sets. Matched Random Forest (MRF) was proposed to find variables that are able to distinguish case and control without the restrictions that exists in linear models. MRF detects variables that are able to distinguish case and control even in the presence of interaction and qualitative variables.
ContributorsKoh, Derek (Author) / Runger, George C. (Thesis advisor) / Wu, Tong (Committee member) / Pan, Rong (Committee member) / Cesta, John (Committee member) / Arizona State University (Publisher)
Created2013
Description
Effective modeling of high dimensional data is crucial in information processing and machine learning. Classical subspace methods have been very effective in such applications. However, over the past few decades, there has been considerable research towards the development of new modeling paradigms that go beyond subspace methods. This dissertation focuses on the study of sparse models and their interplay with modern machine learning techniques such as manifold, ensemble and graph-based methods, along with their applications in image analysis and recovery. By considering graph relations between data samples while learning sparse models, graph-embedded codes can be obtained for use in unsupervised, supervised and semi-supervised problems. Using experiments on standard datasets, it is demonstrated that the codes obtained from the proposed methods outperform several baseline algorithms. In order to facilitate sparse learning with large scale data, the paradigm of ensemble sparse coding is proposed, and different strategies for constructing weak base models are developed. Experiments with image recovery and clustering demonstrate that these ensemble models perform better when compared to conventional sparse coding frameworks. When examples from the data manifold are available, manifold constraints can be incorporated with sparse models and two approaches are proposed to combine sparse coding with manifold projection. The improved performance of the proposed techniques in comparison to sparse coding approaches is demonstrated using several image recovery experiments. In addition to these approaches, it might be required in some applications to combine multiple sparse models with different regularizations. In particular, combining an unconstrained sparse model with non-negative sparse coding is important in image analysis, and it poses several algorithmic and theoretical challenges. A convex and an efficient greedy algorithm for recovering combined representations are proposed. Theoretical guarantees on sparsity thresholds for exact recovery using these algorithms are derived and recovery performance is also demonstrated using simulations on synthetic data. Finally, the problem of non-linear compressive sensing, where the measurement process is carried out in feature space obtained using non-linear transformations, is considered. An optimized non-linear measurement system is proposed, and improvements in recovery performance are demonstrated in comparison to using random measurements as well as optimized linear measurements.
ContributorsNatesan Ramamurthy, Karthikeyan (Author) / Spanias, Andreas (Thesis advisor) / Tsakalis, Konstantinos (Committee member) / Karam, Lina (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud.
ContributorsIslam, Gazi (Author) / Li, Baoxin (Thesis advisor) / Liang, Jianming (Thesis advisor) / Dinu, Valentin (Committee member) / Greenes, Robert (Committee member) / Smith, Marshall (Committee member) / Kahol, Kanav (Committee member) / Patel, Vimla L. (Committee member) / Arizona State University (Publisher)
Created2013