Matching Items (11)
Filtering by
- All Subjects: Health Sciences
- All Subjects: Transfer Learning
- Creators: Huberty, Jennifer
- Creators: Li, Jing
Description
Introduction: Less than half of U.S. adults meet the aerobic physical activity guidelines to exercise at least 150 minutes a week. An individual's decision to be physically active is influenced by their perceptions of physical activity. To address perceptions, interventions need to be implemented where adults spend one third of their day; the workplace. A number of physical activity interventions have been conducted and few have been successful at improving physical activity; therefore, there is a need to explore novel approaches to improve physical activity in the worksite. The purpose of this pilot study was to examine the impact of a seven-day gratitude intervention on perceptions of physical activity and happiness in the workplace. Methods: Full-time employees at two worksites participated in a seven-day online journaling study. Participants were randomized into the intervention (gratitude) or control group and were assessed for perceptions of physical activity and happiness at baseline, immediate post-test (day 7) and one-week follow-up (day 14). Results: Results of this study indicate that the seven-day gratitude intervention may not significantly improve perceptions of physical activity or increase happiness. Future research should consider assessing the individual's readiness for change at baseline, increasing the length of the intervention, testing participant level of gratitude at baseline and employing a larger sample size.
ContributorsRowedder, Lacey (Author) / Huberty, Jennifer (Thesis advisor) / Chisum, Jack (Committee member) / Lee, Chong (Committee member) / Arizona State University (Publisher)
Created2014
Description
Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test or target distribution, but we may have plenty of labeled data from one or multiple related sources with different distributions. Due to its capability of migrating knowledge from related domains, transfer learning has shown to be effective for cross-domain learning problems. In this dissertation, I carry out research along this direction with a particular focus on designing efficient and effective algorithms for BioImaging and Bilingual applications. Specifically, I propose deep transfer learning algorithms which combine transfer learning and deep learning to improve image annotation performance. Firstly, I propose to generate the deep features for the Drosophila embryo images via pretrained deep models and build linear classifiers on top of the deep features. Secondly, I propose to fine-tune the pretrained model with a small amount of labeled images. The time complexity and performance of deep transfer learning methodologies are investigated. Promising results have demonstrated the knowledge transfer ability of proposed deep transfer algorithms. Moreover, I propose a novel Robust Principal Component Analysis (RPCA) approach to process the noisy images in advance. In addition, I also present a two-stage re-weighting framework for general domain adaptation problems. The distribution of source domain is mapped towards the target domain in the first stage, and an adaptive learning model is proposed in the second stage to incorporate label information from the target domain if it is available. Then the proposed model is applied to tackle cross lingual spam detection problem at LinkedIn’s website. Our experimental results on real data demonstrate the efficiency and effectiveness of the proposed algorithms.
ContributorsSun, Qian (Author) / Ye, Jieping (Committee member) / Xue, Guoliang (Committee member) / Liu, Huan (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2015
Description
College students experience a considerable amount of stress. Unmanaged stress is associated with poor academic performance, health risk behaviors (i.e., inadequate sleep and physical activity, alcohol consumption, poor dietary behaviors), and poor mental health. Coping with stress has become a priority among universities. The most tested stress-related programs to date have been mindfulness-based and face-to-face. These programs demonstrated significant improvements in stress, mindfulness, and self-compassion among college students. However, they may be burdensome to students as studies report low attendance and low compliance due to class conflicts or not enough time. Few interventions have used more advanced technologies (i.e., mobile apps) as a mode of delivery. The purpose of this study is to report adherence to a consumer-based mindfulness meditation mobile application (i.e., Calm) and test its effects on stress, mindfulness, and self-compassion in college students. We will also explore what the relationship is between mindfulness and health behaviors.
College students were recruited using fliers on college campus and social media. Eligible participants were randomized to one of two groups: (1) Intervention - meditate using Calm, 10 min/day for eight weeks and (2) Control – no participation in mindfulness practices (received the Calm application after 12-weeks). Stress, mindfulness, and self-compassion and health behaviors (i.e., sleep disturbance, alcohol consumption, physical activity, fruit and vegetable consumption) were measured using self-report. Outcomes were measured at baseline and week eight.
Of the 109 students that enrolled in the study, 41 intervention and 47 control participants were included in analysis. Weekly meditation participation averaged 38 minutes with 54% of participants completing at least half (i.e., 30 minutes) of meditations. Significant changes between groups were found in stress, mindfulness, and self-compassion (all P<0.001) in favor of the intervention group. A significant negative association (p<.001) was found between total mindfulness and sleep disturbance.
An eight-week consumer-based mindfulness meditation mobile application (i.e., Calm) was effective in reducing stress, improving mindfulness and self-compassion among undergraduate college students. Mobile applications may be a feasible, effective, and less burdensome way to reduce stress in college students.
College students were recruited using fliers on college campus and social media. Eligible participants were randomized to one of two groups: (1) Intervention - meditate using Calm, 10 min/day for eight weeks and (2) Control – no participation in mindfulness practices (received the Calm application after 12-weeks). Stress, mindfulness, and self-compassion and health behaviors (i.e., sleep disturbance, alcohol consumption, physical activity, fruit and vegetable consumption) were measured using self-report. Outcomes were measured at baseline and week eight.
Of the 109 students that enrolled in the study, 41 intervention and 47 control participants were included in analysis. Weekly meditation participation averaged 38 minutes with 54% of participants completing at least half (i.e., 30 minutes) of meditations. Significant changes between groups were found in stress, mindfulness, and self-compassion (all P<0.001) in favor of the intervention group. A significant negative association (p<.001) was found between total mindfulness and sleep disturbance.
An eight-week consumer-based mindfulness meditation mobile application (i.e., Calm) was effective in reducing stress, improving mindfulness and self-compassion among undergraduate college students. Mobile applications may be a feasible, effective, and less burdensome way to reduce stress in college students.
ContributorsGlissmann, Christine (Author) / Huberty, Jennifer (Thesis advisor) / Sebren, Ann (Committee member) / Larkey, Linda (Committee member) / Lee, Chong (Committee member) / Arizona State University (Publisher)
Created2018
Description
Transfer learning is a sub-field of statistical modeling and machine learning. It refers to methods that integrate the knowledge of other domains (called source domains) and the data of the target domain in a mathematically rigorous and intelligent way, to develop a better model for the target domain than a model using the data of the target domain alone. While transfer learning is a promising approach in various application domains, my dissertation research focuses on the particular application in health care, including telemonitoring of Parkinson’s Disease (PD) and radiomics for glioblastoma.
The first topic is a Mixed Effects Transfer Learning (METL) model that can flexibly incorporate mixed effects and a general-form covariance matrix to better account for similarity and heterogeneity across subjects. I further develop computationally efficient procedures to handle unknown parameters and large covariance structures. Domain relations, such as domain similarity and domain covariance structure, are automatically quantified in the estimation steps. I demonstrate METL in an application of smartphone-based telemonitoring of PD.
The second topic focuses on an MRI-based transfer learning algorithm for non-invasive surgical guidance of glioblastoma patients. Limited biopsy samples per patient create a challenge to build a patient-specific model for glioblastoma. A transfer learning framework helps to leverage other patient’s knowledge for building a better predictive model. When modeling a target patient, not every patient’s information is helpful. Deciding the subset of other patients from which to transfer information to the modeling of the target patient is an important task to build an accurate predictive model. I define the subset of “transferrable” patients as those who have a positive rCBV-cell density correlation, because a positive correlation is confirmed by imaging theory and the its respective literature.
The last topic is a Privacy-Preserving Positive Transfer Learning (P3TL) model. Although negative transfer has been recognized as an important issue by the transfer learning research community, there is a lack of theoretical studies in evaluating the risk of negative transfer for a transfer learning method and identifying what causes the negative transfer. My work addresses this issue. Driven by the theoretical insights, I extend Bayesian Parameter Transfer (BPT) to a new method, i.e., P3TL. The unique features of P3TL include intelligent selection of patients to transfer in order to avoid negative transfer and maintain patient privacy. These features make P3TL an excellent model for telemonitoring of PD using an At-Home Testing Device.
The first topic is a Mixed Effects Transfer Learning (METL) model that can flexibly incorporate mixed effects and a general-form covariance matrix to better account for similarity and heterogeneity across subjects. I further develop computationally efficient procedures to handle unknown parameters and large covariance structures. Domain relations, such as domain similarity and domain covariance structure, are automatically quantified in the estimation steps. I demonstrate METL in an application of smartphone-based telemonitoring of PD.
The second topic focuses on an MRI-based transfer learning algorithm for non-invasive surgical guidance of glioblastoma patients. Limited biopsy samples per patient create a challenge to build a patient-specific model for glioblastoma. A transfer learning framework helps to leverage other patient’s knowledge for building a better predictive model. When modeling a target patient, not every patient’s information is helpful. Deciding the subset of other patients from which to transfer information to the modeling of the target patient is an important task to build an accurate predictive model. I define the subset of “transferrable” patients as those who have a positive rCBV-cell density correlation, because a positive correlation is confirmed by imaging theory and the its respective literature.
The last topic is a Privacy-Preserving Positive Transfer Learning (P3TL) model. Although negative transfer has been recognized as an important issue by the transfer learning research community, there is a lack of theoretical studies in evaluating the risk of negative transfer for a transfer learning method and identifying what causes the negative transfer. My work addresses this issue. Driven by the theoretical insights, I extend Bayesian Parameter Transfer (BPT) to a new method, i.e., P3TL. The unique features of P3TL include intelligent selection of patients to transfer in order to avoid negative transfer and maintain patient privacy. These features make P3TL an excellent model for telemonitoring of PD using an At-Home Testing Device.
ContributorsYoon, Hyunsoo (Author) / Li, Jing (Thesis advisor) / Wu, Teresa (Committee member) / Yan, Hao (Committee member) / Hu, Leland S. (Committee member) / Arizona State University (Publisher)
Created2018
Description
Transfer learning refers to statistical machine learning methods that integrate the knowledge of one domain (source domain) and the data of another domain (target domain) in an appropriate way, in order to develop a model for the target domain that is better than a model using the data of the target domain alone. Transfer learning emerged because classic machine learning, when used to model different domains, has to take on one of two mechanical approaches. That is, it will either assume the data distributions of the different domains to be the same and thereby developing one model that fits all, or develop one model for each domain independently. Transfer learning, on the other hand, aims to mitigate the limitations of the two approaches by accounting for both the similarity and specificity of related domains. The objective of my dissertation research is to develop new transfer learning methods and demonstrate the utility of the methods in real-world applications. Specifically, in my methodological development, I focus on two different transfer learning scenarios: spatial transfer learning across different domains and temporal transfer learning along time in the same domain. Furthermore, I apply the proposed spatial transfer learning approach to modeling of degenerate biological systems.Degeneracy is a well-known characteristic, widely-existing in many biological systems, and contributes to the heterogeneity, complexity, and robustness of biological systems. In particular, I study the application of one degenerate biological system which is to use transcription factor (TF) binding sites to predict gene expression across multiple cell lines. Also, I apply the proposed temporal transfer learning approach to change detection of dynamic network data. Change detection is a classic research area in Statistical Process Control (SPC), but change detection in network data has been limited studied. I integrate the temporal transfer learning method called the Network State Space Model (NSSM) and SPC and formulate the problem of change detection from dynamic networks into a covariance monitoring problem. I demonstrate the performance of the NSSM in change detection of dynamic social networks.
ContributorsZou, Na (Author) / Li, Jing (Thesis advisor) / Baydogan, Mustafa (Committee member) / Borror, Connie (Committee member) / Montgomery, Douglas C. (Committee member) / Wu, Teresa (Committee member) / Arizona State University (Publisher)
Created2015
Description
Physical activity, sedentary behaviors, and sleep are often associated with cardiometabolic biomarkers commonly found in metabolic syndrome. These relationships are well studied, and yet there are still questions on how each activity may affect cardiometabolic biomarkers. The objective of this study was to examine data from the BeWell24 studies to evaluate the relationship between objectively measured physical activity and sedentary behaviors and cardiometabolic biomarkers in middle age adults, while also determining if sleep quality and duration mediates this relationship. A group of inactive participants (N = 29, age = 52.1 ± 8.1 years, 38% female) with increased risk for cardiometabolic disease were recruited to participate in BeWell24, a trial testing the impact of a lifestyle-based, multicomponent smartphone application targeting sleep, sedentary, and more active behaviors. During baseline, interim (4 weeks), and posttest visits (8 weeks), biomarker measurements were collected for weight (kg), waist circumference (cm), glucose (mg/dl), insulin (uU/ml), lipids (mg/dl), diastolic and systolic blood pressures (mm Hg), and C reactive protein (mg/L). Participants wore validated wrist and thigh sensors for one week intervals at each time point to measure sedentary behavior, physical activity, and sleep outcomes. Long bouts of sitting time (>30 min) significantly affected triglycerides (beta = .15 (±.07), p<.03); however, no significant mediation effects for sleep quality or duration were present. No other direct effects were observed between physical activity measurements and cardiometabolic biomarkers. The findings of this study suggest that reductions in long bouts of sitting time may support reductions in triglycerides, yet these effects were not mediated by sleep-related improvements.
ContributorsLanich, Boyd (Author) / Buman, Matthew (Thesis advisor) / Ainsworth, Barbara (Committee member) / Huberty, Jennifer (Committee member) / Arizona State University (Publisher)
Created2017
Description
Hepatocellular carcinoma (HCC) is a malignant tumor and seventh most common cancer in human. Every year there is a significant rise in the number of patients suffering from HCC. Most clinical research has focused on HCC early detection so that there are high chances of patient's survival. Emerging advancements in functional and structural imaging techniques have provided the ability to detect microscopic changes in tumor micro environment and micro structure. The prime focus of this thesis is to validate the applicability of advanced imaging modality, Magnetic Resonance Elastography (MRE), for HCC diagnosis. The research was carried out on three HCC patient's data and three sets of experiments were conducted. The main focus was on quantitative aspect of MRE in conjunction with Texture Analysis, an advanced imaging processing pipeline and multi-variate analysis machine learning method for accurate HCC diagnosis. We analyzed the techniques to handle unbalanced data and evaluate the efficacy of sampling techniques. Along with this we studied different machine learning algorithms and developed models using them. Performance metrics such as Prediction Accuracy, Sensitivity and Specificity have been used for evaluation for the final developed model. We were able to identify the significant features in the dataset and also the selected classifier was robust in predicting the response class variable with high accuracy.
ContributorsBansal, Gaurav (Author) / Wu, Teresa (Thesis advisor) / Mitchell, Ross (Thesis advisor) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2013
Description
Myeloproliferative neoplasm (MPN) patients suffer from fatigue and a reduced overall quality of life, both of which are not resolved with current pharmacologic therapy. The purpose of this study was to examine the effects of a 12-week online-streamed yoga intervention on fatigue and QoL in MPN patients as compared to a wait-list control group as well as to determine the feasibility of remotely collecting blood and saliva samples in a national sample. MPN patients were asked to complete 60 min/week of online yoga for 12 weeks. MPN fatigue and QoL were assessed online with single-item questions taken from the MPN SAF (fatigue and QoL) and NIH PROMIS (QoL) at baseline, week 7, and week 12. The practicality of the blood and saliva measures were defined as >70% completion rate at both baseline and week 12. Fidelity of the intervention (i.e., weekly yoga participation) was assessed via both self-report (i.e., daily log) and objective measurement (i.e., Clicky). Of the 62 MPN patients that enrolled in the study, 48 completed the intervention with 27 participating in the yoga group and 21 participating in the wait-list control group. Weekly yoga participation averaged ~41 min/week as measured objectively, whereas self-report yoga participation averaged ~56 min/week. The blood draw was determined to be practical with a 92.6% completion rate at baseline and a 70.4% completion rate at week 12. There were no significant differences from baseline to week 12 in MPN SAF fatigue (ES=0.18; p=0.724) or MPN SAF QoL (ES=-0.53; p=0.19), however, NIH PROMIS QoL was significantly improved from baseline to week 12 (ES=0.7; p=0.031) when compared to the control group. This study builds upon the findings from a prior feasibility study in demonstrating the feasibility of online yoga as well as its preliminary effects of improving total symptom burden, fatigue, pain, depression, anxiety, and sleep disturbance in MPN patients. Given the effects of yoga demonstrated both in the feasibility study and the current pilot study, a future randomized controlled trial with a larger sample size is warranted in order to further investigate the effectiveness of online yoga for MPN patient symptom burden and QoL.
ContributorsEckert, Ryan (Author) / Huberty, Jennifer (Thesis advisor) / Mesa, Ruben (Committee member) / Gowin, Krisstina (Committee member) / Dueck, Amylou (Committee member) / Kosiorek, Heidi (Committee member) / Larkey, Linda (Committee member) / Arizona State University (Publisher)
Created2017
Description
Background: Although childhood engagement in physical activity has received growing attention, most children still do not meet the recommended daily 60 minutes of moderate to vigorous physical activity [MVPA]. Children of ethnic minorities are less likely to meet the guidelines. Interventions have been implemented in various settings to increase child physical activity levels, yet these efforts have not yielded consistent results. The purpose of this study was to assess the preliminary effects of a community-based intervention on light physical activity and MVPA among 6-11 year old children. Methods: The present study was part of a larger study called Athletes for Life [AFL], a family-based, nutrition-education and physical activity intervention. The present study focused on physical activity data from the first completed cohort of participants (n=29). This study was a randomized control trial in which participating children were randomized into a control (n=14) or intervention (n=15) group. Participants wore accelerometers at two time points. Intervention strategies were incorporated to increase child habitual physical activity. Analyses of covariance were performed to test for post 12-week differences between both groups on the average minutes of light physical activity and MVPA minutes per day.
Results: The accelerometer data demonstrated no significant difference in light physical activity or MVPA mean minutes per day between the groups. Few children reported engaging in activities sufficient for meeting the physical activity guidelines outside the AFL program. Of the 119 total distributed child physical activity tracker sheets (7 per family), 55 were returned. Of the 55 returned physical activity tracker sheets, parents reported engaging in physical activity with their children only 7 times outside of the program over seven weeks.
Conclusion: The combined intervention strategies implemented throughout the 12-week study did not appear to be effective at increasing habitual mean minutes per day spent engaging in light and MVPA among children beyond the directed program. Methodological limitations and low adherence to intervention strategies may partially explain these findings. Further research is needed to test successful strategies within community programs to increase habitual light physical activity and MVPA among 6-11 year old children.
Results: The accelerometer data demonstrated no significant difference in light physical activity or MVPA mean minutes per day between the groups. Few children reported engaging in activities sufficient for meeting the physical activity guidelines outside the AFL program. Of the 119 total distributed child physical activity tracker sheets (7 per family), 55 were returned. Of the 55 returned physical activity tracker sheets, parents reported engaging in physical activity with their children only 7 times outside of the program over seven weeks.
Conclusion: The combined intervention strategies implemented throughout the 12-week study did not appear to be effective at increasing habitual mean minutes per day spent engaging in light and MVPA among children beyond the directed program. Methodological limitations and low adherence to intervention strategies may partially explain these findings. Further research is needed to test successful strategies within community programs to increase habitual light physical activity and MVPA among 6-11 year old children.
ContributorsQuezada, Blanca (Author) / Crespo, Noe (Thesis advisor) / Huberty, Jennifer (Committee member) / Vega-Lopez, Sonia (Committee member) / Arizona State University (Publisher)
Created2015
Description
Deep learning is a sub-field of machine learning in which models are developed to imitate the workings of the human brain in processing data and creating patterns for decision making. This dissertation is focused on developing deep learning models for medical imaging analysis of different modalities for different tasks including detection, segmentation and classification. Imaging modalities including digital mammography (DM), magnetic resonance imaging (MRI), positron emission tomography (PET) and computed tomography (CT) are studied in the dissertation for various medical applications. The first phase of the research is to develop a novel shallow-deep convolutional neural network (SD-CNN) model for improved breast cancer diagnosis. This model takes one type of medical image as input and synthesizes different modalities for additional feature sources; both original image and synthetic image are used for feature generation. This proposed architecture is validated in the application of breast cancer diagnosis and proved to be outperforming the competing models. Motivated by the success from the first phase, the second phase focuses on improving medical imaging synthesis performance with advanced deep learning architecture. A new architecture named deep residual inception encoder-decoder network (RIED-Net) is proposed. RIED-Net has the advantages of preserving pixel-level information and cross-modality feature transferring. The applicability of RIED-Net is validated in breast cancer diagnosis and Alzheimer’s disease (AD) staging. Recognizing medical imaging research often has multiples inter-related tasks, namely, detection, segmentation and classification, my third phase of the research is to develop a multi-task deep learning model. Specifically, a feature transfer enabled multi-task deep learning model (FT-MTL-Net) is proposed to transfer high-resolution features from segmentation task to low-resolution feature-based classification task. The application of FT-MTL-Net on breast cancer detection, segmentation and classification using DM images is studied. As a continuing effort on exploring the transfer learning in deep models for medical application, the last phase is to develop a deep learning model for both feature transfer and knowledge from pre-training age prediction task to new domain of Mild cognitive impairment (MCI) to AD conversion prediction task. It is validated in the application of predicting MCI patients’ conversion to AD with 3D MRI images.
ContributorsGao, Fei (Author) / Wu, Teresa (Thesis advisor) / Li, Jing (Committee member) / Yan, Hao (Committee member) / Patel, Bhavika (Committee member) / Arizona State University (Publisher)
Created2019