Matching Items (135)
Description
Learning from high dimensional biomedical data attracts lots of attention recently. High dimensional biomedical data often suffer from the curse of dimensionality and have imbalanced class distributions. Both of these features of biomedical data, high dimensionality and imbalanced class distributions, are challenging for traditional machine learning methods and may affect the model performance. In this thesis, I focus on developing learning methods for the high-dimensional imbalanced biomedical data. In the first part, a sparse canonical correlation analysis (CCA) method is presented. The penalty terms is used to control the sparsity of the projection matrices of CCA. The sparse CCA method is then applied to find patterns among biomedical data sets and labels, or to find patterns among different data sources. In the second part, I discuss several learning problems for imbalanced biomedical data. Note that traditional learning systems are often biased when the biomedical data are imbalanced. Therefore, traditional evaluations such as accuracy may be inappropriate for such cases. I then discuss several alternative evaluation criteria to evaluate the learning performance. For imbalanced binary classification problems, I use the undersampling based classifiers ensemble (UEM) strategy to obtain accurate models for both classes of samples. A small sphere and large margin (SSLM) approach is also presented to detect rare abnormal samples from a large number of subjects. In addition, I apply multiple feature selection and clustering methods to deal with high-dimensional data and data with highly correlated features. Experiments on high-dimensional imbalanced biomedical data are presented which illustrate the effectiveness and efficiency of my methods.
ContributorsYang, Tao (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2013
Description
This dissertation constructs a new computational processing framework to robustly and precisely quantify retinotopic maps based on their angle distortion properties. More generally, this framework solves the problem of how to robustly and precisely quantify (angle) distortions of noisy or incomplete (boundary enclosed) 2-dimensional surface to surface mappings. This framework builds upon the Beltrami Coefficient (BC) description of quasiconformal mappings that directly quantifies local mapping (circles to ellipses) distortions between diffeomorphisms of boundary enclosed plane domains homeomorphic to the unit disk. A new map called the Beltrami Coefficient Map (BCM) was constructed to describe distortions in retinotopic maps. The BCM can be used to fully reconstruct the original target surface (retinal visual field) of retinotopic maps. This dissertation also compared retinotopic maps in the visual processing cascade, which is a series of connected retinotopic maps responsible for visual data processing of physical images captured by the eyes. By comparing the BCM results from a large Human Connectome project (HCP) retinotopic dataset (N=181), a new computational quasiconformal mapping description of the transformed retinal image as it passes through the cascade is proposed, which is not present in any current literature. The description applied on HCP data provided direct visible and quantifiable geometric properties of the cascade in a way that has not been observed before. Because retinotopic maps are generated from in vivo noisy functional magnetic resonance imaging (fMRI), quantifying them comes with a certain degree of uncertainty. To quantify the uncertainties in the quantification results, it is necessary to generate statistical models of retinotopic maps from their BCMs and raw fMRI signals. Considering that estimating retinotopic maps from real noisy fMRI time series data using the population receptive field (pRF) model is a time consuming process, a convolutional neural network (CNN) was constructed and trained to predict pRF model parameters from real noisy fMRI data
ContributorsTa, Duyan Nguyen (Author) / Wang, Yalin (Thesis advisor) / Lu, Zhong-Lin (Committee member) / Hansford, Dianne (Committee member) / Liu, Huan (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2022
Description
The ability to find evidence of life on early Earth and other planets is constrained by the current understanding of biosignatures and our ability to differentiate fossils from abiotic mimics. When organisms transition from the living realm to the fossil record, their morphological and chemical characteristics are modified, usually resulting in the loss of information. These modifications can happen during early and late diagenesis and differ depending on local geochemical properties. These post-depositional modifications need to be understood to better interpret the fossil record. Siliceous hot spring deposits (sinters) are of particular interest for biosignature research as they are early Earth analog environments and targets for investigating the presence of fossil life on Mars. As silica-supersaturated fluids flow from the vent to the distal apron, they precipitate non-crystalline opal-A that fossilizes microbial communities at a range in scales (μm-cm). Therefore, many studies have documented the ties between the active microbial communities and the morphological and chemical biosignatures in hot springs. However, far less attention has been placed on understanding preservation in systems with complex mineralogy or how post-depositional alteration affects the retention of biosignatures. Without this context, it can be challenging to recognize biosignatures in ancient rocks. This dissertation research aims to refine our current understanding of biosignature preservation and retention in sinters. Biosignatures of interest include organic matter, microfossils, and biofabrics. The complex nature of hot springs requires a comprehensive understanding of biosignature preservation that is representative of variable chemistries and post-depositional alterations. For this reason, this dissertation research chapters are field site-based. Chapter 2 investigates biosignature preservation in an unusual spring with mixed opal-A-calcite mineralogy at Lýsuhóll, Iceland. Chapter 3 tracks how silica diagenesis modifies microfossil morphology and associated organic matter at Puchuldiza, Chile. Chapter 4 studies the effects of acid fumarolic overprinting on biosignatures in Gunnuhver, Iceland. To accomplish this, traditional geologic methods (mapping, petrography, X-ray diffraction, bulk elemental analyses) were combined with high-spatial-resolution elemental mapping to better understand diagenetic effects in these systems. Preservation models were developed to predict the types and styles of biosignatures that can be present depending on the depositional and geochemical context. Recommendations are also made for the types of deposits that are most likely to preserve biosignatures.
ContributorsJuarez Rivera, Marisol (Author) / Farmer, Jack D (Thesis advisor) / Hartnett, Hilairy E (Committee member) / Shock, Everett (Committee member) / Garcia-Pichel, Ferran (Committee member) / Trembath-Reichert, Elizabeth (Committee member) / Arizona State University (Publisher)
Created2021
Description
Retinotopic map, the map between visual inputs on the retina and neuronal activation in brain visual areas, is one of the central topics in visual neuroscience. For human observers, the map is typically obtained by analyzing functional magnetic resonance imaging (fMRI) signals of cortical responses to slowly moving visual stimuli on the retina. Biological evidences show the retinotopic mapping is topology-preserving/topological (i.e. keep the neighboring relationship after human brain process) within each visual region.
Unfortunately, due to limited spatial resolution and the signal-noise ratio of fMRI, state of art retinotopic map is not topological.
The topic was to model the topology-preserving condition mathematically, fix non-topological retinotopic map with numerical methods, and improve the quality of retinotopic maps.
The impose of topological condition, benefits several applications.
With the topological retinotopic maps, one may have a better insight on human retinotopic maps, including better cortical magnification factor quantification, more precise description of retinotopic maps, and potentially better exam ways of in Ophthalmology clinic.
ContributorsTu, Yanshuai (Author) / Wang, Yalin (Thesis advisor) / Lu, Zhong-Lin (Committee member) / Crook, Sharon (Committee member) / Yang, Yezhou (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2022
Description
I present results of field and laboratory experiments investigating the habitability of one of Earth’s driest environments: the Atacama Desert. This Desert, along the west coast of South America spanning Perú and Chile, is one of the driest places on Earth and has been exceedingly arid for millions of years. These conditions create the perfect natural laboratory for assessing life at the extremes of habitability. All known life needs water; however, the extraordinarily dry Atacama Desert is inhabited by well-adapted microorganisms capable of colonizing this hostile environment. I show field and laboratory evidence of an environmental process, water vapor adsorption, that provides a daily, sustainable input of water into the near (3 - 5 cm) subsurface through water vapor-soil particle interactions. I estimate that this water input may rival the yearly average input of rain in these soils (~2 mm).
I also demonstrate, for the first time, that water vapor adsorption is dependent on mineral composition via a series of laboratory water vapor adsorption experiments. The results of these experiments provide evidence that mineral composition, and ultimately soil composition, measurably and significantly affect the equilibrium soil water content. This suggests that soil microbial communities may be extremely heterogeneous in distribution depending on the distribution of adsorbent minerals.
Finally, I present changes in biologically relevant gasses (i.e., H2, CH4, CO, and CO2) over long-duration incubation experiments designed to assess the potential for biological activity in soils collected from a hyperarid region in the Atacama Desert. These long-duration experiments mimicked typical water availability conditions in the Atacama Desert; in other words, the incubations were performed without condensed water addition. The results suggest a potential for methane-production in the live experiments relative to the sterile controls, and thus, for biological activity in hyperarid soils. However, due to the extremely low biomass and extremely low rates of activity in these soils, the methods employed here were unable to provide robust evidence for activity. Overall, the hyperarid regions of the Atacama Desert are an important resource for researchers by providing a window into the environmental dynamics and subsequent microbial responses near the limit of habitability.
ContributorsGlaser, Donald M (Author) / Hartnett, Hilairy E (Thesis advisor) / Anbar, Ariel (Committee member) / Shock, Everett (Committee member) / Arizona State University (Publisher)
Created2022
Description
Neural tissue is a delicate system comprised of neurons and their synapses, glial cells for support, and vasculature for oxygen and nutrient delivery. This complexity ultimately gives rise to the human brain, a system researchers have become increasingly interested in replicating for artificial intelligence purposes. Some have even gone so far as to use neuronal cultures as computing hardware, but utilizing an environment closer to a living brain means having to grapple with the same issues faced by clinicians and researchers trying to treat brain disorders. Most outstanding among these are the problems that arise with invasive interfaces. Optical techniques that use fluorescent dyes and proteins have emerged as a solution for noninvasive imaging with single-cell resolution in vitro and in vivo, but feeding in information in the form of neuromodulation still requires implanted electrodes. The implantation process of these electrodes damages nearby neurons and their connections, causes hemorrhaging, and leads to scarring and gliosis that diminish efficacy. Here, a new approach for noninvasive neuromodulation with high spatial precision is described. It makes use of a combination of ultrasound, high frequency acoustic energy that can be focused to submillimeter regions at significant depths, and electric fields, an effective tool for neuromodulation that lacks spatial precision when used in a noninvasive manner. The hypothesis is that, when combined in a specific manner, these will lead to nonlinear effects at neuronal membranes that cause cells only in the region of overlap to be stimulated. Computational modeling confirmed this combination to be uniquely stimulating, contingent on certain physical effects of ultrasound on cell membranes. Subsequent in vitro experiments led to inconclusive results, however, leaving the door open for future experimentation with modified configurations and approaches. The specific combination explored here is also not the only untested technique that may achieve a similar goal.
ContributorsNester, Elliot (Author) / Wang, Yalin (Thesis advisor) / Muthuswamy, Jitendran (Committee member) / Towe, Bruce (Committee member) / Arizona State University (Publisher)
Created2022
Description
Beta-Amyloid(Aβ) plaques and tau protein tangles in the brain are now widely recognized as the defining hallmarks of Alzheimer’s disease (AD), followed by structural atrophy detectable on brain magnetic resonance imaging (MRI) scans. However, current methods to detect Aβ/tau pathology are either invasive (lumbar puncture) or quite costly and not widely available (positron emission tomography (PET)). And one of the particular neurodegenerative regions is the hippocampus to which the influence of Aβ/tau on has been one of the research projects focuses in the AD pathophysiological progress.
In this dissertation, I proposed three novel machine learning and statistical models to examine subtle aspects of the hippocampal morphometry from MRI that are associated with Aβ /tau burden in the brain, measured using PET images. The first model is a novel unsupervised feature reduction model to generate a low-dimensional representation of hippocampal morphometry for each individual subject, which has superior performance in predicting Aβ/tau burden in the brain. The second one is an efficient federated group lasso model to identify the hippocampal subregions where atrophy is strongly associated with abnormal Aβ/Tau. The last one is a federated model for imaging genetics, which can identify genetic and transcriptomic influences on hippocampal morphometry. Finally, I stated the results of these three models that have been published or submitted to peer-reviewed conferences and journals.
ContributorsWu, Jianfeng (Author) / Wang, Yalin (Thesis advisor) / Li, Baoxin (Committee member) / Liang, Jianming (Committee member) / Wang, Junwen (Committee member) / Wu, Teresa (Committee member) / Arizona State University (Publisher)
Created2022
Description
Structural Magnetic Resonance Imaging analysis is a vital component in the study of Alzheimer’s Disease pathology and several techniques exist as part of the existing research conducted. In particular, volumetric approaches in this field are known to be beneficial due to the increased capability to express morphological characteristics when compared to manifold methods. To aid in the improvement of the field, this paper aims to propose an intrinsic volumetric conic system that can be applied to bounded volumetric meshes to enable a more effective study of subjects. The computation of the metric involves the use of heat kernel theory and conformal parameterization on genus-0 surfaces extended to a volumetric domain. Additionally, this paper also explores the use of the ’TetCNN’ architecture on the classification of hippocampal tetrahedral meshes to detect features that correspond to Alzheimer’s indicators. The model tested was able to achieve remarkable results with a measured classification accuracy of above 90% in the task of differentiating between subjects diagnosed with Alzheimer’s and normal control subjects.
ContributorsGeorge, John Varghese (Author) / Wang, Yalin (Thesis advisor) / Hansford, Dianne (Committee member) / Gupta, Vikash (Committee member) / Arizona State University (Publisher)
Created2023
Description
Dissolved inorganic carbon (DIC) and dissolved organic carbon (DOC) are crucial nutrients for autotrophic and heterotrophic microbial life, respectively, in hydrothermal systems. Biogeochemical processes that control amounts of DIC and DOC in Yellowstone hot springs can be investigated by measuring carbon abundances and respective isotopic values. A decade and a half of field work in 10 regions within Yellowstone National Park and subsequent geochemical lab analyses reveal that sulfate-dominant acidic regions have high DOC (Up to 57 ppm C) and lower DIC (up to 50 ppm C) compared to neutral-chloride regions with low DOC (< 2 ppm C) and higher DIC (up to 100 ppm C). Abundances and isotopic data suggest that sedimentary rock erosion by acidic hydrothermal fluids, fresh snow-derived meteoric water, and exogenous carbon input allowed by local topography may affect DOC levels. Evaluating the isotopic compositions of DIC and DOC in hydrothermal fluids gives insight on the geology and microbial life in the subsurface between different regions. DIC δ13C values range from -4‰ to +5‰ at pH 5-9 and from -10‰ to +3‰ at pH 2-5 with several springs lower than -10‰. DOC δ13C values parkwide range from -10‰ to -30‰. Within this range, neutral-chloride regions in the Lower Geyser Basin have lighter isotopes than sulfate-dominant acidic regions. In hot springs with elevated levels of DOC, the range only varies between -20‰ and -26‰ which may be caused by local exogenous organic matter runoff. Combining other geochemical measurements, such as differences in chloride and sulfate concentrations, demonstrates that some regions contain mixtures of multiple fluids moving through the complex hydrological system in the subsurface. The mixing of these fluids may account for increased levels of DOC in meteoric sulfate-dominant acidic regions. Ultimately, the foundational values of dissolved carbon and their isotopic composition is provided in a parkwide study, so results can be combined with future studies that apply different sequencing analyses to understand specific biogeochemical cycling and microbial communities that occur in individual hot springs.
ContributorsBarnes, Tanner (Author) / Shock, Everett (Thesis advisor) / Meyer-Dombard, D'Arcy (Committee member) / Hartnett, Hilairy (Committee member) / Arizona State University (Publisher)
Created2023
Description
As air quality standards become more stringent to combat poor air quality, there is a greater need for more effective pollutant control measures and increased air monitoring network coverage. Polluted air, in the form of aerosols and gases, can impact respiratory and cardiovascular health, visibility, the climate, and material weathering. This work demonstrates how traditional networks can be used to study generational events, how these networks can be supplemented with low-cost sensors, and the effectiveness of several control measures. First, an existing network was used to study the effect of COVID-19 travel restrictions on air quality in Maricopa County, Arizona, which would not have been possible without the historical record that a traditional network provides. Although this study determined that decreases in CO and NO2 were not unique to the travel restrictions, it was limited to only three locations due to network sparseness. The second part of this work expanded the traditional NO2 monitoring network using low-cost sensors, that were first collocated with a reference monitor to evaluate their performance and establish a robust calibration. The sensors were then deployed to the field to varying results; their calibration was further improved by cycling the sensors between deployment and reference locations throughout the summer. This calibrated NO2 data, along with volatile organic compound data, were combined to enhance the understanding of ozone formation in Maricopa County, especially during wildfire season. In addition to being in non-attainment for ozone standards, Maricopa County fails to meet particulate matter under 10 μm (PM10) standards. A large portion of PM10 emissions is attributed to fugitive dust that is either windblown or kicked up by vehicles. The third part of this work demonstrated that Enzyme Induced Carbonate Precipitation (EICP) treatments aggregate soil particles and prevent fugitive dust emissions. The final part of the work examined tire wear PM10 emissions, as vehicles are another significant contributor to PM10. Observations showed a decrease in tire wear PM10 during winter with little change when varying the highway surface type.
ContributorsMiech, Jason Andrew (Author) / Herckes, Pierre (Thesis advisor) / Fraser, Matthew P (Committee member) / Shock, Everett (Committee member) / Arizona State University (Publisher)
Created2023