Matching Items (95)
Filtering by
Description
Many learning models have been proposed for various tasks in visual computing. Popular examples include hidden Markov models and support vector machines. Recently, sparse-representation-based learning methods have attracted a lot of attention in the computer vision field, largely because of their impressive performance in many applications. In the literature, many of such sparse learning methods focus on designing or application of some learning techniques for certain feature space without much explicit consideration on possible interaction between the underlying semantics of the visual data and the employed learning technique. Rich semantic information in most visual data, if properly incorporated into algorithm design, should help achieving improved performance while delivering intuitive interpretation of the algorithmic outcomes. My study addresses the problem of how to explicitly consider the semantic information of the visual data in the sparse learning algorithms. In this work, we identify four problems which are of great importance and broad interest to the community. Specifically, a novel approach is proposed to incorporate label information to learn a dictionary which is not only reconstructive but also discriminative; considering the formation process of face images, a novel image decomposition approach for an ensemble of correlated images is proposed, where a subspace is built from the decomposition and applied to face recognition; based on the observation that, the foreground (or salient) objects are sparse in input domain and the background is sparse in frequency domain, a novel and efficient spatio-temporal saliency detection algorithm is proposed to identify the salient regions in video; and a novel hidden Markov model learning approach is proposed by utilizing a sparse set of pairwise comparisons among the data, which is easier to obtain and more meaningful, consistent than tradition labels, in many scenarios, e.g., evaluating motion skills in surgical simulations. In those four problems, different types of semantic information are modeled and incorporated in designing sparse learning algorithms for the corresponding visual computing tasks. Several real world applications are selected to demonstrate the effectiveness of the proposed methods, including, face recognition, spatio-temporal saliency detection, abnormality detection, spatio-temporal interest point detection, motion analysis and emotion recognition. In those applications, data of different modalities are involved, ranging from audio signal, image to video. Experiments on large scale real world data with comparisons to state-of-art methods confirm the proposed approaches deliver salient advantages, showing adding those semantic information dramatically improve the performances of the general sparse learning methods.
ContributorsZhang, Qiang (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2014
Description
In this thesis, the application of pixel-based vertical axes used within parallel coordinate plots is explored in an attempt to improve how existing tools can explain complex multivariate interactions across temporal data. Several promising visualization techniques are combined, such as: visual boosting to allow for quicker consumption of large data sets, the bond energy algorithm to find finer patterns and anomalies through contrast, multi-dimensional scaling, flow lines, user guided clustering, and row-column ordering. User input is applied on precomputed data sets to provide for real time interaction. General applicability of the techniques are tested against industrial trade, social networking, financial, and sparse data sets of varying dimensionality.
ContributorsHayden, Thomas (Author) / Maciejewski, Ross (Thesis advisor) / Wang, Yalin (Committee member) / Runger, George C. (Committee member) / Mack, Elizabeth (Committee member) / Arizona State University (Publisher)
Created2014
Description
Extraordinary medical advances have led to significant reductions in the burden of infectious diseases in humans. However, infectious diseases still account for more than 13 million annual deaths. This large burden is partly due to some pathogens having found suitable conditions to emerge and spread in denser and more connected host populations, and others having evolved to escape the pressures imposed by the rampant use of antimicrobials. It is then critical to improve our understanding of how diseases spread in these modern landscapes, characterized by new host population structures and socio-economic environments, as well as containment measures such as the deployment of drugs. Thus, the motivation of this dissertation is two-fold. First, we study, using both data-driven and modeling approaches, the the spread of infectious diseases in urban areas. As a case study, we use confirmed-cases data on sexually transmitted diseases (STDs) in the United States to assess the conduciveness of population size of urban areas and their socio-economic characteristics as predictors of STD incidence. We find that the scaling of STD incidence in cities is superlinear, and that the percent of African-Americans residing in cities largely determines these statistical patterns. Since disparities in access to health care are often exacerbated in urban areas, within this project we also develop two modeling frameworks to study the effect of health care disparities on epidemic outcomes. Discrepant results between the two approaches indicate that knowledge of the shape of the recovery period distribution, not just its mean and variance, is key for assessing the epidemiological impact of inequalities. The second project proposes to study, from a modeling perspective, the spread of drug resistance in human populations featuring vital dynamics, stochasticity and contact structure. We derive effective treatment regimes that minimize both the overall disease burden and the spread of resistance. Additionally, targeted treatment in structured host populations may lead to higher levels of drug resistance, and if drug-resistant strains are compensated, they can spread widely even when the wild-type strain is below its epidemic threshold.
ContributorsPatterson-Lomba, Oscar (Author) / Castillo-Chavez, Carlos (Thesis advisor) / Towers, Sherry (Thesis advisor) / Chowell-Puente, Gerardo (Committee member) / Arizona State University (Publisher)
Created2014
Description
Urban scaling analysis has introduced a new scientific paradigm to the study of cities. With it, the notions of size, heterogeneity and structure have taken a leading role. These notions are assumed to be behind the causes for why cities differ from one another, sometimes wildly. However, the mechanisms by which size, heterogeneity and structure shape the general statistical patterns that describe urban economic output are still unclear. Given the rapid rate of urbanization around the globe, we need precise and formal mathematical understandings of these matters. In this context, I perform in this dissertation probabilistic, distributional and computational explorations of (i) how the broadness, or narrowness, of the distribution of individual productivities within cities determines what and how we measure urban systemic output, (ii) how urban scaling may be expressed as a statistical statement when urban metrics display strong stochasticity, (iii) how the processes of aggregation constrain the variability of total urban output, and (iv) how the structure of urban skills diversification within cities induces a multiplicative process in the production of urban output.
ContributorsGómez-Liévano, Andrés (Author) / Lobo, Jose (Thesis advisor) / Muneepeerakul, Rachata (Thesis advisor) / Bettencourt, Luis M. A. (Committee member) / Chowell-Puente, Gerardo (Committee member) / Arizona State University (Publisher)
Created2014
Description
Sparse learning is a powerful tool to generate models of high-dimensional data with high interpretability, and it has many important applications in areas such as bioinformatics, medical image processing, and computer vision. Recently, the a priori structural information has been shown to be powerful for improving the performance of sparse learning models. A graph is a fundamental way to represent structural information of features. This dissertation focuses on graph-based sparse learning. The first part of this dissertation aims to integrate a graph into sparse learning to improve the performance. Specifically, the problem of feature grouping and selection over a given undirected graph is considered. Three models are proposed along with efficient solvers to achieve simultaneous feature grouping and selection, enhancing estimation accuracy. One major challenge is that it is still computationally challenging to solve large scale graph-based sparse learning problems. An efficient, scalable, and parallel algorithm for one widely used graph-based sparse learning approach, called anisotropic total variation regularization is therefore proposed, by explicitly exploring the structure of a graph. The second part of this dissertation focuses on uncovering the graph structure from the data. Two issues in graphical modeling are considered. One is the joint estimation of multiple graphical models using a fused lasso penalty and the other is the estimation of hierarchical graphical models. The key technical contribution is to establish the necessary and sufficient condition for the graphs to be decomposable. Based on this key property, a simple screening rule is presented, which reduces the size of the optimization problem, dramatically reducing the computational cost.
ContributorsYang, Sen (Author) / Ye, Jieping (Thesis advisor) / Wonka, Peter (Thesis advisor) / Wang, Yalin (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2014
Description
The increased number of novel pathogens that potentially threaten the human population has motivated the development of mathematical and computational modeling approaches for forecasting epidemic impact and understanding key environmental characteristics that influence the spread of diseases. Yet, in the case that substantial uncertainty surrounds the transmission process during a rapidly developing infectious disease outbreak, complex mechanistic models may be too difficult to be calibrated quick enough for policy makers to make informed decisions. Simple phenomenological models that rely on a small number of parameters can provide an initial platform for assessing the epidemic trajectory, estimating the reproduction number and quantifying the disease burden from the early epidemic phase.
Chapter 1 provides background information and motivation for infectious disease forecasting and outlines the rest of the thesis.
In chapter 2, logistic patch models are used to assess and forecast the 2013-2015 West Africa Zaire ebolavirus epidemic. In particular, this chapter is concerned with comparing and contrasting the effects that spatial heterogeneity has on the forecasting performance of the cumulative infected case counts reported during the epidemic.
In chapter 3, two simple phenomenological models inspired from population biology are used to assess the Research and Policy for Infectious Disease Dynamics (RAPIDD) Ebola Challenge; a simulated epidemic that generated 4 infectious disease scenarios. Because of the nature of the synthetically generated data, model predictions are compared to exact epidemiological quantities used in the simulation.
In chapter 4, these models are applied to the 1904 Plague epidemic that occurred in Bombay. This chapter provides evidence that these simple models may be applicable to infectious diseases no matter the disease transmission mechanism.
Chapter 5, uses the patch models from chapter 2 to explore how migration in the 1904 Plague epidemic changes the final epidemic size.
The final chapter is an interdisciplinary project concerning within-host dynamics of cereal yellow dwarf virus-RPV, a plant pathogen from a virus group that infects over 150 grass species. Motivated by environmental nutrient enrichment due to anthropological activities, mathematical models are employed to investigate the relevance of resource competition to pathogen and host dynamics.
Chapter 1 provides background information and motivation for infectious disease forecasting and outlines the rest of the thesis.
In chapter 2, logistic patch models are used to assess and forecast the 2013-2015 West Africa Zaire ebolavirus epidemic. In particular, this chapter is concerned with comparing and contrasting the effects that spatial heterogeneity has on the forecasting performance of the cumulative infected case counts reported during the epidemic.
In chapter 3, two simple phenomenological models inspired from population biology are used to assess the Research and Policy for Infectious Disease Dynamics (RAPIDD) Ebola Challenge; a simulated epidemic that generated 4 infectious disease scenarios. Because of the nature of the synthetically generated data, model predictions are compared to exact epidemiological quantities used in the simulation.
In chapter 4, these models are applied to the 1904 Plague epidemic that occurred in Bombay. This chapter provides evidence that these simple models may be applicable to infectious diseases no matter the disease transmission mechanism.
Chapter 5, uses the patch models from chapter 2 to explore how migration in the 1904 Plague epidemic changes the final epidemic size.
The final chapter is an interdisciplinary project concerning within-host dynamics of cereal yellow dwarf virus-RPV, a plant pathogen from a virus group that infects over 150 grass species. Motivated by environmental nutrient enrichment due to anthropological activities, mathematical models are employed to investigate the relevance of resource competition to pathogen and host dynamics.
ContributorsPell, Bruce (Author) / Kuang, Yang (Thesis advisor) / Chowell-Puente, Gerardo (Committee member) / Nagy, John (Committee member) / Kostelich, Eric (Committee member) / Gardner, Carl (Committee member) / Arizona State University (Publisher)
Created2016
Description
While techniques for reading DNA in some capacity has been possible for decades,
the ability to accurately edit genomes at scale has remained elusive. Novel techniques
have been introduced recently to aid in the writing of DNA sequences. While writing
DNA is more accessible, it still remains expensive, justifying the increased interest in
in silico predictions of cell behavior. In order to accurately predict the behavior of
cells it is necessary to extensively model the cell environment, including gene-to-gene
interactions as completely as possible.
Significant algorithmic advances have been made for identifying these interactions,
but despite these improvements current techniques fail to infer some edges, and
fail to capture some complexities in the network. Much of this limitation is due to
heavily underdetermined problems, whereby tens of thousands of variables are to be
inferred using datasets with the power to resolve only a small fraction of the variables.
Additionally, failure to correctly resolve gene isoforms using short reads contributes
significantly to noise in gene quantification measures.
This dissertation introduces novel mathematical models, machine learning techniques,
and biological techniques to solve the problems described above. Mathematical
models are proposed for simulation of gene network motifs, and raw read simulation.
Machine learning techniques are shown for DNA sequence matching, and DNA
sequence correction.
Results provide novel insights into the low level functionality of gene networks. Also
shown is the ability to use normalization techniques to aggregate data for gene network
inference leading to larger data sets while minimizing increases in inter-experimental
noise. Results also demonstrate that high error rates experienced by third generation
sequencing are significantly different than previous error profiles, and that these errors can be modeled, simulated, and rectified. Finally, techniques are provided for amending this DNA error that preserve the benefits of third generation sequencing.
the ability to accurately edit genomes at scale has remained elusive. Novel techniques
have been introduced recently to aid in the writing of DNA sequences. While writing
DNA is more accessible, it still remains expensive, justifying the increased interest in
in silico predictions of cell behavior. In order to accurately predict the behavior of
cells it is necessary to extensively model the cell environment, including gene-to-gene
interactions as completely as possible.
Significant algorithmic advances have been made for identifying these interactions,
but despite these improvements current techniques fail to infer some edges, and
fail to capture some complexities in the network. Much of this limitation is due to
heavily underdetermined problems, whereby tens of thousands of variables are to be
inferred using datasets with the power to resolve only a small fraction of the variables.
Additionally, failure to correctly resolve gene isoforms using short reads contributes
significantly to noise in gene quantification measures.
This dissertation introduces novel mathematical models, machine learning techniques,
and biological techniques to solve the problems described above. Mathematical
models are proposed for simulation of gene network motifs, and raw read simulation.
Machine learning techniques are shown for DNA sequence matching, and DNA
sequence correction.
Results provide novel insights into the low level functionality of gene networks. Also
shown is the ability to use normalization techniques to aggregate data for gene network
inference leading to larger data sets while minimizing increases in inter-experimental
noise. Results also demonstrate that high error rates experienced by third generation
sequencing are significantly different than previous error profiles, and that these errors can be modeled, simulated, and rectified. Finally, techniques are provided for amending this DNA error that preserve the benefits of third generation sequencing.
ContributorsFaucon, Philippe Christophe (Author) / Liu, Huan (Thesis advisor) / Wang, Xiao (Committee member) / Crook, Sharon M (Committee member) / Wang, Yalin (Committee member) / Sarjoughian, Hessam S. (Committee member) / Arizona State University (Publisher)
Created2017
Description
Alzheimer’s Disease (AD), a neurodegenerative disease is a progressive disease that affects the brain gradually with time and worsens. Reliable and early diagnosis of AD and its prodromal stages (i.e. Mild Cognitive Impairment(MCI)) is essential. Fluorodeoxyglucose (FDG) positron emission tomography (PET) measures the decline in the regional cerebral metabolic rate for glucose, offering a reliable metabolic biomarker even on presymptomatic AD patients. PET scans provide functional information that is unique and unavailable using other types of imaging. The computational efficacy of FDG-PET data alone, for the classification of various Alzheimer’s Diagnostic categories (AD, MCI (LMCI, EMCI), Control) has not been studied. This serves as motivation to correctly classify the various diagnostic categories using FDG-PET data. Deep learning has recently been applied to the analysis of structural and functional brain imaging data. This thesis is an introduction to a deep learning based classification technique using neural networks with dimensionality reduction techniques to classify the different stages of AD based on FDG-PET image analysis.
This thesis develops a classification method to investigate the performance of FDG-PET as an effective biomarker for Alzheimer's clinical group classification. This involves dimensionality reduction using Probabilistic Principal Component Analysis on max-pooled data and mean-pooled data, followed by a Multilayer Feed Forward Neural Network which performs binary classification. Max pooled features result into better classification performance compared to results on mean pooled features. Additionally, experiments are done to investigate if the addition of important demographic features such as Functional Activities Questionnaire(FAQ), gene information helps improve performance. Classification results indicate that our designed classifiers achieve competitive results, and better with the additional of demographic features.
This thesis develops a classification method to investigate the performance of FDG-PET as an effective biomarker for Alzheimer's clinical group classification. This involves dimensionality reduction using Probabilistic Principal Component Analysis on max-pooled data and mean-pooled data, followed by a Multilayer Feed Forward Neural Network which performs binary classification. Max pooled features result into better classification performance compared to results on mean pooled features. Additionally, experiments are done to investigate if the addition of important demographic features such as Functional Activities Questionnaire(FAQ), gene information helps improve performance. Classification results indicate that our designed classifiers achieve competitive results, and better with the additional of demographic features.
ContributorsSingh, Shibani (Author) / Wang, Yalin (Thesis advisor) / Li, Baoxin (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2017
Description
Large-scale $\ell_1$-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. In many applications, it remains challenging to apply the sparse learning model to large-scale problems that have massive data samples with high-dimensional features. One popular and promising strategy is to scaling up the optimization problem in parallel. Parallel solvers run multiple cores on a shared memory system or a distributed environment to speed up the computation, while the practical usage is limited by the huge dimension in the feature space and synchronization problems.
In this dissertation, I carry out the research along the direction with particular focuses on scaling up the optimization of sparse learning for supervised and unsupervised learning problems. For the supervised learning, I firstly propose an asynchronous parallel solver to optimize the large-scale sparse learning model in a multithreading environment. Moreover, I propose a distributed framework to conduct the learning process when the dataset is distributed stored among different machines. Then the proposed model is further extended to the studies of risk genetic factors for Alzheimer's Disease (AD) among different research institutions, integrating a group feature selection framework to rank the top risk SNPs for AD. For the unsupervised learning problem, I propose a highly efficient solver, termed Stochastic Coordinate Coding (SCC), scaling up the optimization of dictionary learning and sparse coding problems. The common issue for the medical imaging research is that the longitudinal features of patients among different time points are beneficial to study together. To further improve the dictionary learning model, I propose a multi-task dictionary learning method, learning the different task simultaneously and utilizing shared and individual dictionary to encode both consistent and changing imaging features.
In this dissertation, I carry out the research along the direction with particular focuses on scaling up the optimization of sparse learning for supervised and unsupervised learning problems. For the supervised learning, I firstly propose an asynchronous parallel solver to optimize the large-scale sparse learning model in a multithreading environment. Moreover, I propose a distributed framework to conduct the learning process when the dataset is distributed stored among different machines. Then the proposed model is further extended to the studies of risk genetic factors for Alzheimer's Disease (AD) among different research institutions, integrating a group feature selection framework to rank the top risk SNPs for AD. For the unsupervised learning problem, I propose a highly efficient solver, termed Stochastic Coordinate Coding (SCC), scaling up the optimization of dictionary learning and sparse coding problems. The common issue for the medical imaging research is that the longitudinal features of patients among different time points are beneficial to study together. To further improve the dictionary learning model, I propose a multi-task dictionary learning method, learning the different task simultaneously and utilizing shared and individual dictionary to encode both consistent and changing imaging features.
ContributorsLi, Qingyang (Author) / Ye, Jieping (Thesis advisor) / Xue, Guoliang (Thesis advisor) / He, Jingrui (Committee member) / Wang, Yalin (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2017
Description
The rapid development in acquiring multimodal neuroimaging data provides opportunities to systematically characterize human brain structures and functions. For example, in the brain magnetic resonance imaging (MRI), a typical non-invasive imaging technique, different acquisition sequences (modalities) lead to the different descriptions of brain functional activities, or anatomical biomarkers. Nowadays, in addition to the traditional voxel-level analysis of images, there is a trend to process and investigate the cross-modality relationship in a high dimensional level of images, e.g. surfaces and networks.
In this study, I aim to achieve multimodal brain image fusion by referring to some intrinsic properties of data, e.g. geometry of embedding structures where the commonly used image features reside. Since the image features investigated in this study share an identical embedding space, i.e. either defined on a brain surface or brain atlas, where a graph structure is easy to define, it is straightforward to consider the mathematically meaningful properties of the shared structures from the geometry perspective.
I first introduce the background of multimodal fusion of brain image data and insights of geometric properties playing a potential role to link different modalities. Then, several proposed computational frameworks either using the solid and efficient geometric algorithms or current geometric deep learning models are be fully discussed. I show how these designed frameworks deal with distinct geometric properties respectively, and their applications in the real healthcare scenarios, e.g. to enhanced detections of fetal brain diseases or abnormal brain development.
In this study, I aim to achieve multimodal brain image fusion by referring to some intrinsic properties of data, e.g. geometry of embedding structures where the commonly used image features reside. Since the image features investigated in this study share an identical embedding space, i.e. either defined on a brain surface or brain atlas, where a graph structure is easy to define, it is straightforward to consider the mathematically meaningful properties of the shared structures from the geometry perspective.
I first introduce the background of multimodal fusion of brain image data and insights of geometric properties playing a potential role to link different modalities. Then, several proposed computational frameworks either using the solid and efficient geometric algorithms or current geometric deep learning models are be fully discussed. I show how these designed frameworks deal with distinct geometric properties respectively, and their applications in the real healthcare scenarios, e.g. to enhanced detections of fetal brain diseases or abnormal brain development.
ContributorsZhang, Wen (Author) / Wang, Yalin (Thesis advisor) / Liu, Huan (Committee member) / Li, Baoxin (Committee member) / Braden, B. Blair (Committee member) / Arizona State University (Publisher)
Created2020