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 569
Filtering by
- All Subjects: Machine Learning
- All Subjects: Health
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 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
Bully victimization has been associated with blunted cardiovascular responses to stress as well as elevated responses to stress. The difference between these altered physiological responses to stress is largely unknown. This study explored several possible moderators to the relationship between chronic stress and future cardiac output (an indicator of increased stress) in response to future stressors. These moderators include the difference between social and physical stressors and individual levels of loneliness. Participants were administered measures of loneliness and victimization history, and led to anticipate either a "social" (recorded speech) or "non-social" (pain tolerance test ) stressor, neither of which occurred. EKG and impedance cardiography were measured throughout the session. When anticipating both stressors, loneliness and victimization were associated with increased CO. A regression revealed a three-way interaction, with change in cardiac output depending on victimization history, loneliness, and condition in the physical stressor condition. Loneliness magnified the CO output levels of non-bullied individuals when facing a physical stressor. These results suggest that non- bullied participants high in loneliness are more stressed out when facing stressors, particularly stressors that are physically threatening in nature.
ContributorsHaneline, Magen (Author) / Newman, Matt (Thesis advisor) / Salerno, Jessica (Committee member) / Miller, Paul (Committee member) / Arizona State University (Publisher)
Created2013
Description
Purpose: This study examines the role of social support on adjustment to widowhood. Past research has indicated that the role of social support on adjustment to widowhood remains inconclusive, and needs further examination. This study examines the varying coping trajectories of middle-aged and retired bereaved spouses. Additionally, this study examines how bereavement stage may also influence one's adaptation to widowhood. Methods: This study used in-depth and semi-structured interviews as a means of understanding the role of social support on adjustment to widowhood. Participants were recruited through two hospice services available in a major metropolitan area in the United States. Convenient and purposive samplings are used in this study; this study will execute a grounded theory approach in order to determine the inconclusive role of social support on adjustment to widowhood. This study is contrasting between two stages- life course stages (middle aged versus retirement aged people) and bereavement stages (a year or less time following the death of a spouse versus three or more years following the death of a spouse). As a means of reducing bias and subjectivity, all data collected during the interview will be transcribed immediately. Results: Middle-aged bereaved spouses reported higher levels of motivation for adjusting positively and quickly towards widowhood due to their concern for protecting the well-being of their surviving young children compared to retired bereaved spouses. Differences between middle-aged widows and widowers have been found in this study; middle-aged widowers have a higher linkage to negative health behaviors. Retired bereaved spouses may fare better depending upon their housing location. Living in a retirement center may lower negative effects of bereavement on retired spouses' health. Conclusions: Types of social support received and expected varied between middle-aged widows and widowers. Gender norms may influence the type of social support widows and widowers receive. Middle-aged widowers are less likely to receive emotional support which may explain their higher linkage to negative health behaviors. Bereavement stage and housing location may be the key factors that influence widowhood trajectories of retired bereaved spouses. Living in a retirement center may lower the negative effects of bereavement on overall health.
ContributorsRafieei, Noshin (Author) / Kronenfeld, Jennie (Thesis advisor) / Haas, Steven (Committee member) / Damgaard, Anni (Committee member) / Arizona State University (Publisher)
Created2013
Description
Research has demonstrated that temperature and relative humidity substantially influence overall perceptions of indoor air quality (Fang, Clausen, & Fanger, 1998). This finding places temperature quality as a high priority, especially for vulnerable adults over 60. Temperature extremes and fluctuation, as well as the perception of those conditions, affect physical performance, thermal comfort and health of older adults (Chatonnet & Cabanac, 1965, pp. 185-6; Fumiharu, Watanabe, Park, Shephard, & Aoyagi, 2005; Heijs & Stringer, 1988). The American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) and the International Organization for Standardization (ISO) have developed thermal-comfort standards for working-age, healthy individuals. None of these standards address the physiological and psychological needs of older adults (ASHRAE Standard 55, 2010; ISO-7730, 2005). This dissertation investigates the impacts of thermal conditions on self-reported health and perceived comfort for older adults, hypothesizing that warmer and more-table indoor thermal conditions will increase the health and perceived comfort of these adults. To this end, a new set of thermal comfort metrics was designed and tested to address the thermal preferences of older adults. The SENIOR COMFORT Metrics 2013 outlined new thresholds for optimal indoor high and low temperatures and set limits on thermal variability over time based on the ASHRAE-55 2010 model. This study was conducted at Sunnyslope Manor, a multi-unit, public-housing complex in the North Phoenix. Nearly 60% (76 of 118) of the residents (aged 62-82) were interviewed using a 110-question, self-reporting survey in 73 apartment units. A total of 40 questions and 20 sub-questions addressing perceptions of comfort, pain, sleep patterns, injuries, and mood were extracted from this larger health condition survey to assess health and thermal comfort. Indoor environmental thermal measurements included temperature in three locations: kitchen, living area, and bedroom and data were recorded every 15 minutes over 5 full days and 448 points. Study results start to indicate that older adults for Sunnyslope Manor preferred temperatures between 76 and 82.5 degrees Fahrenheit and that lower temperatures as outlined by ASHRAE-55 2010 increases the rate of injuries and mood changes in older adults among other findings.
ContributorsFonseca, Ernesto (Author) / Bryan, Harvey (Thesis advisor) / Ahrentzen, Sherry (Committee member) / Shea, Kimberly (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
Description
In 1890, the State of Nevada built the Stewart Indian School on a parcel of land three miles south of Carson City, Nevada, and then sold the campus to the federal government. The Stewart Indian School operated as the only non-reservation Indian boarding school in Nevada until 1980 when the federal government closed the campus. Faced with the challenge of assimilating Native peoples into Anglo society after the conclusion of the Indian wars and the confinement of Indian nations on reservations, the federal government created boarding schools. Policymakers believed that in one generation they could completely eliminate Indian culture by removing children from their homes and educating them in boarding schools. The history of the Stewart Indian School from 1890 to 1940 is the story of a dynamic and changing institution. Only Washoe, Northern Paiute, and Western Shoshone students attended Stewart for the first decade, but over the next forty years, children from over sixty tribal groups enrolled at the school. They arrived from three dozen reservations and 335 different hometowns across the West. During this period, Stewart evolved from a repressive and exploitive institution, into a school that embodied the reform agenda of the Indian New Deal in the 1930s. This dissertation uses archival and ethnographic material to explain how the federal government's agenda failed. Rather than destroying Native culture, Stewart students and Nevada's Indian communities used the skills taught at the school to their advantage and became tribal leaders during the 1930s. This dissertation explores the individual and collective bodies of Stewart students. The body is a social construction constantly being fashioned by the intersectional forces of race, class, and gender. Each chapter explores the different ways the Stewart Indian School and the federal government tried to transform the students' bodies through their physical appearance, the built environment, health education, vocational training, and extracurricular activities such as band and sports.
ContributorsThompson, Bonnie (Author) / Iverson, Peter (Thesis advisor) / Gray, Susan (Thesis advisor) / Green, Monica (Committee member) / Arizona State University (Publisher)
Created2013