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 21 - 30 of 85
Description
Healthcare operations have enjoyed reduced costs, improved patient safety, and
innovation in healthcare policy over a huge variety of applications by tackling prob-
lems via the creation and optimization of descriptive mathematical models to guide
decision-making. Despite these accomplishments, models are stylized representations
of real-world applications, reliant on accurate estimations from historical data to jus-
tify their underlying assumptions. To protect against unreliable estimations which
can adversely affect the decisions generated from applications dependent on fully-
realized models, techniques that are robust against misspecications are utilized while
still making use of incoming data for learning. Hence, new robust techniques are ap-
plied that (1) allow for the decision-maker to express a spectrum of pessimism against
model uncertainties while (2) still utilizing incoming data for learning. Two main ap-
plications are investigated with respect to these goals, the first being a percentile
optimization technique with respect to a multi-class queueing system for application
in hospital Emergency Departments. The second studies the use of robust forecasting
techniques in improving developing countries’ vaccine supply chains via (1) an inno-
vative outside of cold chain policy and (2) a district-managed approach to inventory
control. Both of these research application areas utilize data-driven approaches that
feature learning and pessimism-controlled robustness.
innovation in healthcare policy over a huge variety of applications by tackling prob-
lems via the creation and optimization of descriptive mathematical models to guide
decision-making. Despite these accomplishments, models are stylized representations
of real-world applications, reliant on accurate estimations from historical data to jus-
tify their underlying assumptions. To protect against unreliable estimations which
can adversely affect the decisions generated from applications dependent on fully-
realized models, techniques that are robust against misspecications are utilized while
still making use of incoming data for learning. Hence, new robust techniques are ap-
plied that (1) allow for the decision-maker to express a spectrum of pessimism against
model uncertainties while (2) still utilizing incoming data for learning. Two main ap-
plications are investigated with respect to these goals, the first being a percentile
optimization technique with respect to a multi-class queueing system for application
in hospital Emergency Departments. The second studies the use of robust forecasting
techniques in improving developing countries’ vaccine supply chains via (1) an inno-
vative outside of cold chain policy and (2) a district-managed approach to inventory
control. Both of these research application areas utilize data-driven approaches that
feature learning and pessimism-controlled robustness.
ContributorsBren, Austin (Author) / Saghafian, Soroush (Thesis advisor) / Mirchandani, Pitu (Thesis advisor) / Wu, Teresa (Committee member) / Pan, Rong (Committee member) / Arizona State University (Publisher)
Created2018
Description
Under different environmental conditions, the relationship between the design and operational variables of a system and the system’s performance is likely to vary and is difficult to be described by a single model. The environmental variables (e.g., temperature, humidity) are not controllable while the variables of the system (e.g. heating, cooling) are mostly controllable. This phenomenon has been widely seen in the areas of building energy management, mobile communication networks, and wind energy. To account for the complicated interaction between a system and the multivariate environment under which it operates, a Sparse Partitioned-Regression (SPR) model is proposed, which automatically searches for a partition of the environmental variables and fits a sparse regression within each subdivision of the partition. SPR is an innovative approach that integrates recursive partitioning and high-dimensional regression model fitting within a single framework. Moreover, theoretical studies of SPR are explicitly conducted to derive the oracle inequalities for the SPR estimators which could provide a bound for the difference between the risk of SPR estimators and Bayes’ risk. These theoretical studies show that the performance of SPR estimator is almost (up to numerical constants) as good as of an ideal estimator that can be theoretically achieved but is not available in practice. Finally, a Tree-Based Structure-Regularized Regression (TBSR) approach is proposed by considering the fact that the model performance can be improved by a joint estimation on different subdivisions in certain scenarios. It leverages the idea that models for different subdivisions may share some similarities and can borrow strength from each other. The proposed approaches are applied to two real datasets in the domain of building energy. (1) SPR is used in an application of adopting building design and operational variables, outdoor environmental variables, and their interactions to predict energy consumption based on the Department of Energy’s EnergyPlus data sets. SPR produces a high level of prediction accuracy and provides insights into the design, operation, and management of energy-efficient buildings. (2) TBSR is used in an application of predicting future temperature condition which could help to decide whether to activate or not the Heating, Ventilation, and Air Conditioning (HVAC) systems in an energy-efficient manner.
ContributorsNing, Shuluo (Author) / Li, Jing (Thesis advisor) / Wu, Teresa (Committee member) / Pan, Rong (Committee member) / Rafi, Tanveer A (Committee member) / Arizona State University (Publisher)
Created2018
Description
In healthcare facilities, health information systems (HISs) are used to serve different purposes. The radiology department adopts multiple HISs in managing their operations and patient care. In general, the HISs that touch radiology fall into two categories: tracking HISs and archive HISs. Electronic Health Records (EHR) is a typical tracking HIS, which tracks the care each patient receives at multiple encounters and facilities. Archive HISs are typically specialized databases to store large-size data collected as part of the patient care. A typical example of an archive HIS is the Picture Archive and Communication System (PACS), which provides economical storage and convenient access to diagnostic images from multiple modalities. How to integrate such HISs and best utilize their data remains a challenging problem due to the disparity of HISs as well as high-dimensionality and heterogeneity of the data. My PhD dissertation research includes three inter-connected and integrated topics and focuses on designing integrated HISs and further developing statistical models and machine learning algorithms for process and patient care improvement.
Topic 1: Design of super-HIS and tracking of quality of care (QoC). My research developed an information technology that integrates multiple HISs in radiology, and proposed QoC metrics defined upon the data that measure various dimensions of care. The DDD assisted the clinical practices and enabled an effective intervention for reducing lengthy radiologist turnaround times for patients.
Topic 2: Monitoring and change detection of QoC data streams for process improvement. With the super-HIS in place, high-dimensional data streams of QoC metrics are generated. I developed a statistical model for monitoring high- dimensional data streams that integrated Singular Vector Decomposition (SVD) and process control. The algorithm was applied to QoC metrics data, and additionally extended to another application of monitoring traffic data in communication networks.
Topic 3: Deep transfer learning of archive HIS data for computer-aided diagnosis (CAD). The novelty of the CAD system is the development of a deep transfer learning algorithm that combines the ideas of transfer learning and multi- modality image integration under the deep learning framework. Our system achieved high accuracy in breast cancer diagnosis compared with conventional machine learning algorithms.
Topic 1: Design of super-HIS and tracking of quality of care (QoC). My research developed an information technology that integrates multiple HISs in radiology, and proposed QoC metrics defined upon the data that measure various dimensions of care. The DDD assisted the clinical practices and enabled an effective intervention for reducing lengthy radiologist turnaround times for patients.
Topic 2: Monitoring and change detection of QoC data streams for process improvement. With the super-HIS in place, high-dimensional data streams of QoC metrics are generated. I developed a statistical model for monitoring high- dimensional data streams that integrated Singular Vector Decomposition (SVD) and process control. The algorithm was applied to QoC metrics data, and additionally extended to another application of monitoring traffic data in communication networks.
Topic 3: Deep transfer learning of archive HIS data for computer-aided diagnosis (CAD). The novelty of the CAD system is the development of a deep transfer learning algorithm that combines the ideas of transfer learning and multi- modality image integration under the deep learning framework. Our system achieved high accuracy in breast cancer diagnosis compared with conventional machine learning algorithms.
ContributorsWang, Kun (Author) / Li, Jing (Thesis advisor) / Wu, Teresa (Committee member) / Pan, Rong (Committee member) / Zwart, Christine M. (Committee member) / Arizona State University (Publisher)
Created2018
Description
The recent technological advances enable the collection of various complex, heterogeneous and high-dimensional data in biomedical domains. The increasing availability of the high-dimensional biomedical data creates the needs of new machine learning models for effective data analysis and knowledge discovery. This dissertation introduces several unsupervised and supervised methods to help understand the data, discover the patterns and improve the decision making. All the proposed methods can generalize to other industrial fields.
The first topic of this dissertation focuses on the data clustering. Data clustering is often the first step for analyzing a dataset without the label information. Clustering high-dimensional data with mixed categorical and numeric attributes remains a challenging, yet important task. A clustering algorithm based on tree ensembles, CRAFTER, is proposed to tackle this task in a scalable manner.
The second part of this dissertation aims to develop data representation methods for genome sequencing data, a special type of high-dimensional data in the biomedical domain. The proposed data representation method, Bag-of-Segments, can summarize the key characteristics of the genome sequence into a small number of features with good interpretability.
The third part of this dissertation introduces an end-to-end deep neural network model, GCRNN, for time series classification with emphasis on both the accuracy and the interpretation. GCRNN contains a convolutional network component to extract high-level features, and a recurrent network component to enhance the modeling of the temporal characteristics. A feed-forward fully connected network with the sparse group lasso regularization is used to generate the final classification and provide good interpretability.
The last topic centers around the dimensionality reduction methods for time series data. A good dimensionality reduction method is important for the storage, decision making and pattern visualization for time series data. The CRNN autoencoder is proposed to not only achieve low reconstruction error, but also generate discriminative features. A variational version of this autoencoder has great potential for applications such as anomaly detection and process control.
The first topic of this dissertation focuses on the data clustering. Data clustering is often the first step for analyzing a dataset without the label information. Clustering high-dimensional data with mixed categorical and numeric attributes remains a challenging, yet important task. A clustering algorithm based on tree ensembles, CRAFTER, is proposed to tackle this task in a scalable manner.
The second part of this dissertation aims to develop data representation methods for genome sequencing data, a special type of high-dimensional data in the biomedical domain. The proposed data representation method, Bag-of-Segments, can summarize the key characteristics of the genome sequence into a small number of features with good interpretability.
The third part of this dissertation introduces an end-to-end deep neural network model, GCRNN, for time series classification with emphasis on both the accuracy and the interpretation. GCRNN contains a convolutional network component to extract high-level features, and a recurrent network component to enhance the modeling of the temporal characteristics. A feed-forward fully connected network with the sparse group lasso regularization is used to generate the final classification and provide good interpretability.
The last topic centers around the dimensionality reduction methods for time series data. A good dimensionality reduction method is important for the storage, decision making and pattern visualization for time series data. The CRNN autoencoder is proposed to not only achieve low reconstruction error, but also generate discriminative features. A variational version of this autoencoder has great potential for applications such as anomaly detection and process control.
ContributorsLin, Sangdi (Author) / Runger, George C. (Thesis advisor) / Kocher, Jean-Pierre A (Committee member) / Pan, Rong (Committee member) / Escobedo, Adolfo R. (Committee member) / Arizona State University (Publisher)
Created2018
Description
With the development of computer and sensing technology, rich datasets have become available in many fields such as health care, manufacturing, transportation, just to name a few. Also, data come from multiple heterogeneous sources or modalities. This is a common phenomenon in health care systems. While multi-modality data fusion is a promising research area, there are several special challenges in health care applications. (1) The integration of biological and statistical model is a big challenge; (2) It is commonplace that data from various modalities is not available for every patient due to cost, accessibility, and other reasons. This results in a special missing data structure in which different modalities may be missed in “blocks”. Therefore, how to train a predictive model using such a dataset poses a significant challenge to statistical learning. (3) It is well known that different modality data may contain different aspects of information about the response. The current studies cannot afford to solve this problem. My dissertation includes new statistical learning model development to address each of the aforementioned challenges as well as application case studies using real health care datasets, included in three chapters (Chapter 2, 3, and 4), respectively. Collectively, it is expected that my dissertation could provide a new sets of statistical learning models, algorithms, and theory contributed to multi-modality heterogeneous data fusion driven by the unique challenges in this area. Also, application of these new methods to important medical problems using real-world datasets is expected to provide solutions to these problems, and therefore contributing to the application domains.
ContributorsLiu, Xiaonan (Ph.D.) (Author) / Li, Jing (Thesis advisor) / Wu, Teresa (Committee member) / Pan, Rong (Committee member) / Fatyga, Mirek (Committee member) / Arizona State University (Publisher)
Created2019
Description
Image-based process monitoring has recently attracted increasing attention due to the advancement of the sensing technologies. However, existing process monitoring methods fail to fully utilize the spatial information of images due to their complex characteristics including the high dimensionality and complex spatial structures. Recent advancement of the unsupervised deep models such as a generative adversarial network (GAN) and generative adversarial autoencoder (AAE) has enabled to learn the complex spatial structures automatically. Inspired by this advancement, we propose an anomaly detection framework based on the AAE for unsupervised anomaly detection for images. AAE combines the power of GAN with the variational autoencoder, which serves as a nonlinear dimension reduction technique with regularization from the discriminator. Based on this, we propose a monitoring statistic efficiently capturing the change of the image data. The performance of the proposed AAE-based anomaly detection algorithm is validated through a simulation study and real case study for rolling defect detection.
ContributorsYeh, Huai-Ming (Author) / Yan, Hao (Thesis advisor) / Pan, Rong (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2019
Description
Spousal loss is a common, significant life event that can negatively affect multiple facets of individual health and psychological adjustment. Social support is one factor that is shown to improve adjustment following spousal loss, but much less is known regarding which facet of social support is most predictive of positive adjustment outcomes following spousal loss. This study examined the course of changes in mental health and well-being following spousal loss and which facets of social support are associated with better outcomes following spousal loss. Latent growth curve modeling was applied to data from 265 widowed individuals, ages 65 and older, across four assessments (baseline, and 6-, 18-, and 48- months following spousal loss). I examined the following research questions: (1) adjustment following spousal loss will follow a trajectory of an increase in depressive symptoms and anxiety and decrease in well-being with a leveling-off over time, with between-person differences, and (2) emotional support and instrumental support given will lead to more positive adjustment outcomes over time. Depressive symptoms followed the hypothesized trajectory but anxiety and well-being showed relative stability before and after spousal loss. Instrumental support was the most beneficial facet of social support, such that receiving more instrumental support was associated with lower levels of depressive symptoms and anxiety 6-months following spousal loss. Giving more instrumental support led to an increase in well-being following spousal loss. Instrumental support given and received led to increases in well-being as a function of spousal loss. The discussion focuses on whether and how these findings can help to identify ways through which support and help can be given to individuals to improve adjustment to spousal loss and fully recover.
ContributorsSullivan, Colleen Elizabeth (Author) / Infurna, Frank (Thesis director) / Luthar, Suniya (Committee member) / Davis, Mary (Committee member) / Department of Psychology (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
Effortful Control (EC) is a person's ability to self-regulate when presented with an environmental stimulus (Rothbart, et al., 2003). It has been well-established that high levels of EC are associated with multiple positive social and academic outcomes in adolescence (Spinrad et al., 2009). Research suggests that parents have a strong impact on numerous child outcomes, such as EC, through both genetic and environmental pathways. Past research has also examined how parents diagnosed with psychopathology contribute to maladaptive outcomes in their children, including poor regulation, through both genetic and environmental processes (Ellis, et al., 1997). However, less is known about the longitudinal effects of parent dysfunction on the child's environment and regulatory abilities and potential mediators of those effects. The current study tested the hypotheses that parent Alcohol Use Disorder (AUD) would specifically predict early adversity, biological mother conscientiousness, and child EC longitudinally and that early adversity and biological mother conscientiousness would predict child EC. Participants were from a longitudinal study of familial alcoholism (N = 195). Regression analyses indicated that parent AUD was not specifically associated with child EC or with biological mother conscientiousness. However, parent AUD was related to higher levels of early adversity. Additionally, biological mother conscientiousness was associated with higher levels of child EC and early adversity was associated with lower levels of child EC when controlling for earlier EC. Given these findings, future research should test mediation models in which parent AUD predicts child EC indirectly through early adversity.
ContributorsRuof, Ariana Kelsey (Author) / Chassin, Laurie (Thesis director) / Elam, Kit (Committee member) / Davis, Mary (Committee member) / Department of Psychology (Contributor) / Sanford School of Social and Family Dynamics (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
The rates of anxiety, depression, and attempted suicide for transgender individuals are extremely elevated relative to the general population. Yet, little research has been conducted about the transgender population regarding social transition (an individual presenting as their authentic/true gender, one different than the gender they were assigned at birth, in the context of everyday life) and parental acceptance. Both of which have been shown to impact the mental health of transgender individuals. The purposes of this study were: (1) To characterize a sample of transgender adults on their age of awareness of their authentic gender identity and their age of social transition. (2) Examine whether age of social transition, (3) parental acceptance, and (4) the gap in time between age of awareness and age of social transition (awareness-transition gap) were related to mental health. (5) Examine whether parental acceptance was related to age of social transition or to awareness-transition gap. (6) Examine whether age of social transition or awareness-transition gap interact with parental acceptance as correlates of mental health. The sample consisted of 115 transgender adults, ages 18 to 64. Measures were separated into 7 subheadings: demographics, transgender
on-cisgender identity, age of awareness, age of social transition, primary caregiver acceptance, secondary caregiver acceptance, and mental health. Hypotheses were partially supported for age of social transition with mental health, parental acceptance with mental health, and awareness-transition gap with parental acceptance. This study investigated under studied concepts of social transition and parental acceptance that appear to have an effect on the mental health of transgender adults.
on-cisgender identity, age of awareness, age of social transition, primary caregiver acceptance, secondary caregiver acceptance, and mental health. Hypotheses were partially supported for age of social transition with mental health, parental acceptance with mental health, and awareness-transition gap with parental acceptance. This study investigated under studied concepts of social transition and parental acceptance that appear to have an effect on the mental health of transgender adults.
ContributorsRosenberg, Beth Ann (Author) / Gonzales, Nancy (Thesis director) / Saenz, Delia (Committee member) / Davis, Mary (Committee member) / Department of Psychology (Contributor) / Sanford School of Social and Family Dynamics (Contributor) / College of Public Service and Community Solutions (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
The goal of my study is to test the overarching hypothesis that art therapy is effective because it targets emotional dysregulation that often accompanies significant health stressors. By reducing the salience of illness-related stressors, art therapy may improve overall mood and recovery, particularly in patients with cancer. After consulting the primary literature and review papers to develop psychological and neural mechanisms at work in art therapy, I created a hypothetical experimental procedure to test these hypotheses to explain why art therapy is helpful to patients with chronic illness. Studies found that art therapy stimulates activity of multiple brain regions involved in memory retrieval and the arousal of emotions. I hypothesize that patients with chronic illness have a reduced capacity for emotion regulation, or difficulty recognizing, expressing or altering illness-related emotions (Gross & Barrett, 2011). Further I hypothesize that art therapy improves mood and therapeutic outcomes by acting on the emotion-processing regions of the limbic system, and thereby facilitating the healthy expression of emotion, emotional processing, and reappraisal. More mechanistically, I propose art therapy reduces the perception or salience of stressors by reducing amygdala activity leading to decreased activation of the hypothalamic-pituitary-adrenal (HPA) axis. The art therapy literature and my hypothesis about its mechanisms of action became the basis of my proposed study. To assess the effectiveness of art therapy in alleviating symptoms of chronic disease, I am specifically targeting patients with cancer who exhibit a lack of emotional regulation. Saliva is collected 3 times a week on the day of intervention: morning after waking, afternoon, and evening. Stress levels are tested using one-hour art therapy sessions over the course of 3 months. The Perceived Stress Scale (PSS) assesses an individual's perceived stress and feelings in past and present situations, for the control and intervention group. To measure improvement in overall mood, 10 one-hour art sessions are performed on patients over 10 weeks. A one-hour discussion analyzing the participants' artwork follows each art session. The Spielberger State-Trait Anxiety Inventory (STAI) assesses overall mood for the intervention and control groups. I created rationale and predictions based on the intended results of each experiment.
ContributorsAluri, Bineetha C. (Author) / Orchinik, Miles (Thesis director) / Davis, Mary (Committee member) / Essary, Alison (Committee member) / School of Life Sciences (Contributor) / School for the Science of Health Care Delivery (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05