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 342
Filtering by
- All Subjects: Machine Learning
- All Subjects: Music Education
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
This philosophical inquiry explores the work of philosophers Gilles Deleuze and Félix Guattari and posits applications to music education. Through the concepts of multiplicities, becoming, bodies without organs, smooth spaces, maps, and nomads, Deleuze and Guattari challenge prior and current understandings of existence. In their writings on art, education, and how might one live, they assert a world consisting of variability and motion. Drawing on Deleuze and Guattari's emphasis on time and difference, I posit the following questions: Who and when are we? Where are we? When is music? When is education? Throughout this document, their philosophical figuration of a rhizome serves as a recurring theme, highlighting the possibilities of complexity, diverse connections, and continual processes. I explore the question "When and where are we?" by combining the work of Deleuze and Guattari with that of other authors. Drawing on these ideas, I posit an ontology of humans as inseparably cognitive, embodied, emotional, social, and striving multiplicities. Investigating the question "Where are we?" using Deleuze and Guattari's writings as well as that of contemporary place philosophers and other writers reveals that humans exist at the continually changing confluence of local and global places. In order to engage with the questions "When is music?" and "When is education?" I inquire into how humans as cognitive, embodied, emotional, social, and striving multiplicities emplaced in a glocalized world experience music and education. In the final chapters, a philosophy of music education consisting of the ongoing, interconnected processes of complicating, considering, and connecting is proposed. Complicating involves continually questioning how humans' multiple inseparable qualities and places integrate during musical and educative experiences. Considering includes imagining the multiple directions in which connections might occur as well as contemplating the quality of potential connections. Connecting involves assisting students in forming variegated connections between themselves, their multiple qualities, and their glocal environments. Considering a rhizomatic philosophy of music education includes continually engaging in the integrated processes of complicating, considering, and connecting. Through such ongoing practices, music educators can promote flourishing in the lives of students and the experiences of their multiple communities.
ContributorsRicherme, Lauren Kapalka (Author) / Stauffer, Sandra (Thesis advisor) / Gould, Elizabeth (Committee member) / Schmidt, Margaret (Committee member) / Sullivan, Jill (Committee member) / Tobias, Evan (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
ABSTRACT Two qualitative studies described the effects of parent's participation in the music therapy session on parent-child interaction during home-based musical experiences learned in music therapy session. Home-based musical play was based on two current programs: Sing & Grow (Abad & Williams, 2007; Nicolson, 2008 Abad, 2011; Williams, et al; 2012) and Musical Connection Programme(Warren & Nugent, 2010). The researcher utilized the core elements of these programs, such as session structures and parenting strategies for improving parent-child interaction during music therapy interventions. Several questions emerged as a result of these case studies as follows 1) does parent's participation affect parent-child interaction during music therapy interventions 2) does musical parenting strategies promote parent-child interaction while practicing musical play at home 3) does parent's interaction increase when they practice parental strategies listed on parent's self-check list. Music therapy session was provided once per week during an eight week period. The participants were referred by Arizona State University (ASU) music therapy clinic. Sessions took place either in the ASU music therapy treatment room or the participant's home. There were four participants- one diagnosed with Down syndrome and the other with Autism Spectrum Disorder (ASD) and two parents or caregivers (each subject was counted as one participant). The parent/caregiver filled out the parental self-checklist 3-4 times per week and the survey after the end of the program. The case study materials were gathered through with parent/caregiver. The case studies revealed that all of the parents responded that the parent's participation in music therapy helped to improve their interactions with their child. Furthermore, all parents became more responsive in interacting with their child through musical play, such as sing-a-long and movements. Second, musical parenting strategies encouraged parent-child interaction when practicing musical play at home. Third, the parent's self-checklist was shown to be effective material for increasing positive parent-child interaction. The self-checklist reminded the parents to practice using strategies in order to promote interaction with their child. Overall, it was found that the parent's participation in home-based musical play increased parent-child interaction and the musical parenting strategies enhanced parent-child interaction.
ContributorsChoi, Yoon Kyoung (Author) / Crowe, Barbara J. (Thesis advisor) / Rio, Robin (Committee member) / Sullivan, Jill (Committee member) / Arizona State University (Publisher)
Created2013
Description
This mixed methods research study explores the experiences of Board Certified music therapists who completed a university-affiliated (UA) internship as part of their education and clinical training in music therapy. The majority of music therapy students complete a national roster (NR) internship as the final stage in clinical training. Limited data and research is available on the UA internship model. This research seeks to uncover themes identified by former university-affiliated interns regarding: (1) on-site internship supervision; (2) university support and supervision during internship; and (3) self-identified perceptions of professional preparedness following internship completion. The quantitative data was useful in creating a profile of interns interviewed. The qualitative data provided a context for understanding responses and experiences. Fourteen Board Certified music therapists were interviewed (N=14) and asked to reflect on their experiences during their university-affiliated internship. Commonalities discovered among former university-affiliated interns included: (1) the desire for peer supervision opportunities in internship; (2) an overall perception of being professionally prepared to sit for the Board Certification exam following internship; (3) a sense of readiness to enter the professional world after internship; and (4) a current or future desire to supervise university-affiliated interns.
ContributorsEubanks, Kymla (Author) / Rio, Robin (Thesis advisor) / Crowe, Barbara (Committee member) / Sullivan, Jill (Committee member) / Arizona State University (Publisher)
Created2013
Description
Jazz continues, into its second century, as one of the most important musics taught in public middle and high schools. Even so, research related to how students learn, especially in their earliest interactions with jazz culture, is limited. Weaving together interviews and observations of junior and senior high school jazz players and teachers, private studio instructors, current university students majoring in jazz, and university and college jazz faculty, I developed a composite sketch of a secondary school student learning to play jazz. Using arts-based educational research methods, including the use of narrative inquiry and literary non-fiction, the status of current jazz education and the experiences by novice jazz learners is explored. What emerges is a complex story of students and teachers negotiating the landscape of jazz in and out of early twenty-first century public schools. Suggestions for enhancing jazz experiences for all stakeholders follow, focusing on access and the preparation of future jazz teachers.
ContributorsKelly, Keith B (Author) / Stauffer, Sandra (Thesis advisor) / Tobias, Evan (Committee member) / Kocour, Michael (Committee member) / Sullivan, Jill (Committee member) / Schmidt, Margaret (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
The purpose of this study was to compare perceptions of success and failure, attributions of success and failure, predictions of future success, and reports of out-of-class engagement in composition among middle school band students composing in open task conditions (n = 32) and closed task conditions (n = 31). Two intact band classes at the same middle school were randomly assigned to treatment groups. Both treatment groups composed music once a week for eight weeks during their regular band time. In Treatment A (n = 32), the open task group, students were told to compose music however they wished. In Treatment B (n = 31), the closed task group, students were given specific, structured composition assignments to complete each week. At the end of each session, students were asked to complete a Composing Diary in which they reported what they did each week. Their responses were coded for evidence of perceptions of success and failure as well as out-of-class engagement in composing. At the end of eight weeks, students were given three additional measures: the Music Attributions Survey to measure attributions of success and failure on 11 different subscales; the Future Success survey to measure students' predictions of future success; and the Out-of-Class Engagement Letter to measure students' engagement with composition outside of the classroom. Results indicated that students in the open task group and students in the closed task group behaved similarly. There were no significant differences between treatment groups in terms of perceptions of success or failure as composers, predictions of future success composing music, and reports of out-of-class engagement in composition. Students who felt they failed at composing made similar attributions for their failure in both treatment groups. Students who felt they succeeded also made similar attributions for their success in both treatment groups, with one exception. Successful students in the closed task group rated Peer Influence significantly higher than the successful students in the open task group. The findings of this study suggest that understanding individual student's attributions and offering a variety of composing tasks as part of music curricula may help educators meet students' needs.
ContributorsSchwartz, Emily, 1985- (Author) / Stauffer, Sandra L (Thesis advisor) / Tobias, Evan (Committee member) / Schmidt, Margaret (Committee member) / Broatch, Jennifer (Committee member) / Sullivan, Jill (Committee member) / Arizona State University (Publisher)
Created2014