Matching Items (12,012)
Filtering by
- Creators: Barrett, The Honors College
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
Random peptide microarrays are a powerful tool for both the treatment and diagnostics of infectious diseases. On the treatment side, selected random peptides on the microarray have either binding or lytic potency against certain pathogens cells, thus they can be synthesized into new antimicrobial agents, denoted as synbodies (synthetic antibodies). On the diagnostic side, serum containing specific infection-related antibodies create unique and distinct "pathogen-immunosignatures" on the random peptide microarray distinct from the healthy control serum, and this different mode of binding can be used as a more precise measurement than traditional ELISA tests. My thesis project is separated into these two parts: the first part falls into the treatment side and the second one focuses on the diagnostic side. My first chapter shows that a substitution amino acid peptide library helps to improve the activity of a recently reported synthetic antimicrobial peptide selected by the random peptide microarray. By substituting one or two amino acids of the original lead peptide, the new substitutes show changed hemolytic effects against mouse red blood cells and changed potency against two pathogens: Staphylococcus aureus and Pseudomonas aeruginosa. Two new substitutes are then combined together to form the synbody, which shows a significantly antimicrobial potency against Staphylococcus aureus (<0.5uM). In the second chapter, I explore the possibility of using the 10K Ver.2 random peptide microarray to monitor the humoral immune response of dengue. Over 2.5 billion people (40% of the world's population) live in dengue transmitting areas. However, currently there is no efficient dengue treatment or vaccine. Here, with limited dengue patient serum samples, we show that the immunosignature has the potential to not only distinguish the dengue infection from non-infected people, but also the primary dengue infection from the secondary dengue infections, dengue infection from West Nile Virus (WNV) infection, and even between different dengue serotypes. By further bioinformatic analysis, we demonstrate that the significant peptides selected to distinguish dengue infected and normal samples may indicate the epitopes responsible for the immune response.
ContributorsWang, Xiao (Author) / Johnston, Stephen Albert (Thesis advisor) / Blattman, Joseph (Committee member) / Arntzen, Charles (Committee member) / Arizona State University (Publisher)
Created2013
Description
Over 2 billion people are using online social network services, such as Facebook, Twitter, Google+, LinkedIn, and Pinterest. Users update their status, post their photos, share their information, and chat with others in these social network sites every day; however, not everyone shares the same amount of information. This thesis explores methods of linking publicly available data sources as a means of extrapolating missing information of Facebook. An application named "Visual Friends Income Map" has been created on Facebook to collect social network data and explore geodemographic properties to link publicly available data, such as the US census data. Multiple predictors are implemented to link data sets and extrapolate missing information from Facebook with accurate predictions. The location based predictor matches Facebook users' locations with census data at the city level for income and demographic predictions. Age and relationship based predictors are created to improve the accuracy of the proposed location based predictor utilizing social network link information. In the case where a user does not share any location information on their Facebook profile, a kernel density estimation location predictor is created. This predictor utilizes publicly available telephone record information of all people with the same surname of this user in the US to create a likelihood distribution of the user's location. This is combined with the user's IP level information in order to narrow the probability estimation down to a local regional constraint.
ContributorsMao, Jingxian (Author) / Maciejewski, Ross (Thesis advisor) / Farin, Gerald (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2012
Description
The object of this study is to charac terize the effect of focused ultrasound stimulation (FUS) on the rat ce rvix which has been observed to speed its ripening during pregnancy. Ce rvical ripening is required for successful fetal delivery. Timed-pregnant Sprague-Dawley rats (n=36) were used. On day 14 of gestation, the FUS system was placed on the body surface of the rat over the cervix and ultrasound energy was applied to cervix for variable times up to 1 hour in the control group, the FUS system was placed on rats but no energy was applied. Daily measurement of cervix light-induced florescence (LIF, photon counts of collagen x-bridge fluorescence) were made on days 16 of gestation and daily until spont-aneous delivery (day22) to estimate changes in cervical ripening. We found that pulses of 680 KHz ultrasound at 25 Hertz, 1 millisecond pulse duration at 1W/cm^2 applied for as little as 30 minutes would immediately afterwards show the cervix to hav e ripened to the degree seen just before delivery on day 22. Delivery times, fetal weights and viability were unaffected in the FUS-treated animals.
ContributorsLuo, Daishen (Author) / Towe, Bruce C (Thesis advisor) / Wang, Xiao (Committee member) / Caplan, Michael (Committee member) / Arizona State University (Publisher)
Created2012
Description
This document presents a new implementation of the Smoothed Particles Hydrodynamics algorithm using DirectX 11 and DirectCompute. The main goal of this document is to present to the reader an alternative solution to the largely studied and researched problem of fluid simulation. Most other solutions have been implemented using the NVIDIA CUDA framework; however, the proposed solution in this document uses the Microsoft general-purpose computing on graphics processing units API. The implementation allows for the simulation of a large number of particles in a real-time scenario. The solution presented here uses the Smoothed Particles Hydrodynamics algorithm to calculate the forces within the fluid; this algorithm provides a Lagrangian approach for discretizes the Navier-Stockes equations into a set of particles. Our solution uses the DirectCompute compute shaders to evaluate each particle using the multithreading and multi-core capabilities of the GPU increasing the overall performance. The solution then describes a method for extracting the fluid surface using the Marching Cubes method and the programmable interfaces exposed by the DirectX pipeline. Particularly, this document presents a method for using the Geometry Shader Stage to generate the triangle mesh as defined by the Marching Cubes method. The implementation results show the ability to simulate over 64K particles at a rate of 900 and 400 frames per second, not including the surface reconstruction steps and including the Marching Cubes steps respectively.
ContributorsFigueroa, Gustavo (Author) / Farin, Gerald (Thesis advisor) / Maciejewski, Ross (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2012
Description
Sensitivity is a fundamental challenge for in vivo molecular magnetic resonance imaging (MRI). Here, I improve the sensitivity of metal nanoparticle contrast agents by strategically incorporating pure and doped metal oxides in the nanoparticle core, forming a soluble, monodisperse, contrast agent with adjustable T2 or T1 relaxivity (r2 or r1). I first developed a simplified technique to incorporate iron oxides in apoferritin to form "magnetoferritin" for nM-level detection with T2- and T2* weighting. I then explored whether the crystal could be chemically modified to form a particle with high r1. I first adsorbed Mn2+ ions to metal binding sites in the apoferritin pores. The strategic placement of metal ions near sites of water exchange and within the crystal oxide enhance r1, suggesting a mechanism for increasing relaxivity in porous nanoparticle agents. However, the Mn2+ addition was only possible when the particle was simultaneously filled with an iron oxide, resulting in a particle with a high r1 but also a high r2 and making them undetectable with conventional T1-weighting techniques. To solve this problem and decrease the particle r2 for more sensitive detection, I chemically doped the nanoparticles with tungsten to form a disordered W-Fe oxide composite in the apoferritin core. This configuration formed a particle with a r1 of 4,870mM-1s-1 and r2 of 9,076mM-1s-1. These relaxivities allowed the detection of concentrations ranging from 20nM - 400nM in vivo, both passively injected and targeted to the kidney glomerulus. I further developed an MRI acquisition technique to distinguish particles based on r2/r1, and show that three nanoparticles of similar size can be distinguished in vitro and in vivo with MRI. This work forms the basis for a new, highly flexible inorganic approach to design nanoparticle contrast agents for molecular MRI.
ContributorsClavijo Jordan, Maria Veronica (Author) / Bennett, Kevin M (Thesis advisor) / Kodibagkar, Vikram (Committee member) / Sherry, A Dean (Committee member) / Wang, Xiao (Committee member) / Yarger, Jeffery (Committee member) / Arizona State University (Publisher)
Created2012
Description
In blindness research, the corpus callosum (CC) is the most frequently studied sub-cortical structure, due to its important involvement in visual processing. While most callosal analyses from brain structural magnetic resonance images (MRI) are limited to the 2D mid-sagittal slice, we propose a novel framework to capture a complete set of 3D morphological differences in the corpus callosum between two groups of subjects. The CCs are segmented from whole brain T1-weighted MRI and modeled as 3D tetrahedral meshes. The callosal surface is divided into superior and inferior patches on which we compute a volumetric harmonic field by solving the Laplace's equation with Dirichlet boundary conditions. We adopt a refined tetrahedral mesh to compute the Laplacian operator, so our computation can achieve sub-voxel accuracy. Thickness is estimated by tracing the streamlines in the harmonic field. We combine areal changes found using surface tensor-based morphometry and thickness information into a vector at each vertex to be used as a metric for the statistical analysis. Group differences are assessed on this combined measure through Hotelling's T2 test. The method is applied to statistically compare three groups consisting of: congenitally blind (CB), late blind (LB; onset > 8 years old) and sighted (SC) subjects. Our results reveal significant differences in several regions of the CC between both blind groups and the sighted groups; and to a lesser extent between the LB and CB groups. These results demonstrate the crucial role of visual deprivation during the developmental period in reshaping the structural architecture of the CC.
ContributorsXu, Liang (Author) / Wang, Yalin (Thesis advisor) / Maciejewski, Ross (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
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
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2014
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