Matching Items (147)
Description
Communicating with computers through thought has been a remarkable achievement in recent years. This was made possible by the use of Electroencephalography (EEG). Brain-computer interface (BCI) relies heavily on Electroencephalography (EEG) signals for communication between humans and computers. With the advent ofdeep learning, many studies recently applied these techniques to EEG data to perform various tasks like emotion recognition, motor imagery classification, sleep analysis, and many more.
Despite the rise of interest in EEG signal classification, very few studies have explored the MindBigData dataset, which collects EEG signals recorded at the stimulus of seeing a digit and thinking about it. This dataset takes us closer to realizing the idea of mind-reading or communication via thought. Thus classifying these signals into the respective digit that the user thinks about is a challenging task. This serves as a motivation to study this dataset and apply existing deep learning techniques to study it.
Given the recent success of transformer architecture in different domains like Computer Vision and Natural language processing, this thesis studies transformer architecture for EEG signal classification. Also, it explores other deep learning
techniques for the same. As a result, the proposed classification pipeline achieves comparable performance with the existing methods.
ContributorsMuglikar, Omkar Dushyant (Author) / Wang, Yalin (Thesis advisor) / Liang, Jianming (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2021
Description
Statistical Shape Modeling is widely used to study the morphometrics of deformable objects in computer vision and biomedical studies. There are mainly two viewpoints to understand the shapes. On one hand, the outer surface of the shape can be taken as a two-dimensional embedding in space. On the other hand, the outer surface along with its enclosed internal volume can be taken as a three-dimensional embedding of interests. Most studies focus on the surface-based perspective by leveraging the intrinsic features on the tangent plane. But a two-dimensional model may fail to fully represent the realistic properties of shapes with both intrinsic and extrinsic properties. In this thesis, severalStochastic Partial Differential Equations (SPDEs) are thoroughly investigated and several methods are originated from these SPDEs to try to solve the problem of both two-dimensional and three-dimensional shape analyses. The unique physical meanings of these SPDEs inspired the findings of features, shape descriptors, metrics, and kernels in this series of works. Initially, the data generation of high-dimensional shapes, here, the tetrahedral meshes, is introduced. The cerebral cortex is taken as the study target and an automatic pipeline of generating the gray matter tetrahedral mesh is introduced. Then, a discretized Laplace-Beltrami operator (LBO) and a Hamiltonian operator (HO) in tetrahedral domain with Finite Element Method (FEM) are derived. Two high-dimensional shape descriptors are defined based on the solution of the heat equation and Schrödinger’s equation. Considering the fact that high-dimensional shape models usually contain massive redundancies, and the demands on effective landmarks in many applications, a Gaussian process landmarking on tetrahedral meshes is further studied. A SIWKS-based metric space is used to define a geometry-aware Gaussian process. The study of the periodic potential diffusion process further inspired the idea of a new kernel call the geometry-aware convolutional kernel. A series of Bayesian learning methods are then introduced to tackle the problem of shape retrieval and classification. Experiments of every single item are demonstrated. From the popular SPDE such as the heat equation and Schrödinger’s equation to the general potential diffusion equation and the specific periodic potential diffusion equation, it clearly shows that classical SPDEs play an important role in discovering new features, metrics, shape descriptors and kernels. I hope this thesis could be an example of using interdisciplinary knowledge to solve problems.
ContributorsFan, Yonghui (Author) / Wang, Yalin (Thesis advisor) / Lepore, Natasha (Committee member) / Turaga, Pavan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
Graph matching is a fundamental but notoriously difficult problem due to its NP-hard nature, and serves as a cornerstone for a series of applications in machine learning and computer vision, such as image matching, dynamic routing, drug design, to name a few. Although there has been massive previous investigation on high-performance graph matching solvers, it still remains a challenging task to tackle the matching problem under real-world scenarios with severe graph uncertainty (e.g., noise, outlier, misleading or ambiguous link).In this dissertation, a main focus is to investigate the essence and propose solutions to graph matching with higher reliability under such uncertainty. To this end, the proposed research was conducted taking into account three perspectives related to reliable graph matching: modeling, optimization and learning. For modeling, graph matching is extended from typical quadratic assignment problem to a more generic mathematical model by introducing a specific family of separable function, achieving higher capacity and reliability. In terms of optimization, a novel high gradient-efficient determinant-based regularization technique is proposed in this research, showing high robustness against outliers. Then learning paradigm for graph matching under intrinsic combinatorial characteristics is explored. First, a study is conducted on the way of filling the gap between discrete problem and its continuous approximation under a deep learning framework. Then this dissertation continues to investigate the necessity of more reliable latent topology of graphs for matching, and propose an effective and flexible framework to obtain it. Coherent findings in this dissertation include theoretical study and several novel algorithms, with rich experiments demonstrating the effectiveness.
ContributorsYu, Tianshu (Author) / Li, Baoxin (Thesis advisor) / Wang, Yalin (Committee member) / Yang, Yezhou (Committee member) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021
Description
Graph matching is a fundamental but notoriously difficult problem due to its NP-hard nature, and serves as a cornerstone for a series of applications in machine learning and computer vision, such as image matching, dynamic routing, drug design, to name a few. Although there has been massive previous investigation on high-performance graph matching solvers, it still remains a challenging task to tackle the matching problem under real-world scenarios with severe graph uncertainty (e.g., noise, outlier, misleading or ambiguous link).In this dissertation, a main focus is to investigate the essence and propose solutions to graph matching with higher reliability under such uncertainty. To this end, the proposed research was conducted taking into account three perspectives related to reliable graph matching: modeling, optimization and learning. For modeling, graph matching is extended from typical quadratic assignment problem to a more generic mathematical model by introducing a specific family of separable function, achieving higher capacity and reliability. In terms of optimization, a novel high gradient-efficient determinant-based regularization technique is proposed in this research, showing high robustness against outliers. Then learning paradigm for graph matching under intrinsic combinatorial characteristics is explored. First, a study is conducted on the way of filling the gap between discrete problem and its continuous approximation under a deep learning framework. Then this dissertation continues to investigate the necessity of more reliable latent topology of graphs for matching, and propose an effective and flexible framework to obtain it. Coherent findings in this dissertation include theoretical study and several novel algorithms, with rich experiments demonstrating the effectiveness.
ContributorsYu, Tianshu (Author) / Li, Baoxin (Thesis advisor) / Wang, Yalin (Committee member) / Yang, Yezhou (Committee member) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021
Description
Alzheimer's disease (AD) is a neurodegenerative disease that damages the cognitive abilities of a patient. It is critical to diagnose AD early to begin treatment as soon as possible which can be done through biomarkers. One such biomarker is the beta-amyloid (Aβ) peptide which can be quantified using the centiloid (CL) scale. For identifying the Aβ biomarker, A deep learning model that can model AD progression by predicting the CL value for brain magnetic resonance images (MRIs) is proposed. Brain MRI images can be obtained through the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) datasets, however a single model cannot perform well on both datasets at once. Thus, A regularization-based continuous learning framework to perform domain adaptation on the previous model is also proposed which captures the latent information about the relationship between Aβ and AD progression within both datasets.
ContributorsTrinh, Matthew Brian (Author) / Wang, Yalin (Thesis advisor) / Liang, Jianming (Committee member) / Su, Yi (Committee member) / Arizona State University (Publisher)
Created2022
Description
The Population Receptive Field (pRF) model is widely used to predict the location (retinotopy) and size of receptive fields on the visual space. Doing so allows for the creation of a mapping from locations in the visual field to the associated groups of neurons in the cortical region (within the visual cortex of the brain). However, using the pRF model is very time consuming. Past research has focused on the creation of Convolutional Neural Networks (CNN) to mimic the pRF model in a fraction of the time, and they have worked well under highly controlled conditions. However, these models have not been thoroughly tested on real human data. This thesis focused on adapting one of these CNNs to accurately predict the retinotopy of a real human subject using a dataset from the Human Connectome Project. The results show promise towards creating a fully functioning CNN, but they also expose new challenges that must be overcome before the model could be used to predict the retinotopy of new human subjects.
ContributorsBurgard, Braeden (Author) / Wang, Yalin (Thesis director) / Ta, Duyan (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2022-05
Description
Heart disease is the leading cause of death in the developed world and often occurs following myocardial infarction. Apelin is an endogenous prepropeptide that has been studied for its role in improving cardiac contractility and vasodilation but suffers from a short half-life in the body. By encasing apelin in a nanoparticle patch, we were able to slowly release apelin to cardiac tissue and observe its effects for one month following induced myocardial infarction surgery in mice. This study demonstrates that the apelin nanoparticles can protect the heart from myocardial-induced heart failure, observing overall improved cardiac function and reduction of fibrotic scarring associated with post-myocardial infarction compared to a nontreated group.
ContributorsHenderson, Adam (Author) / Chen, Qiang (Thesis director) / Zhu, Wuqiang (Committee member) / Barrett, The Honors College (Contributor) / College of Health Solutions (Contributor)
Created2022-05
Description
Weight stigma is present in many aspects of society, and especially in medicine. Weight stigma has detrimental effects on individuals physical and mental health, as well as patient-physician interactions. Application of weight-neutral healthcare ideologies such as Health at Every Size (HAES) are promising ways of decreasing weight stigma within the medical field without reducing the focus on improving patient health. Most widely applicable interventions include changing the focus of interactions from weight to health-promoting behaviors and lab values, improving provider education, and improving the general population's awareness of the problem.
ContributorsBrouhard, Mya (Author) / Chen, Qiang (Thesis director) / Parker, Lynn (Committee member) / Barrett, The Honors College (Contributor) / School of Life Sciences (Contributor) / Department of Psychology (Contributor)
Created2024-05
Description
Platelet Rich Plasma (PRP) is an emerging procedure in regenerative medicine that offers a non-surgical minimally invasive way for tissue repair and regeneration. PRP has many different bioactive molecules that are able to influence and help achieve greater recovery and regenerative outcomes. Diet has many effects on platelets and looking at the mechanism in which platelet function and aggregation are affected with different diets shows how they are able to affect PRP therapy. Looking at these mechanisms allows for better physician recommendations for preprocedural diets to optimize efficacy. This paper conducts a systematic review to investigate the influence that diet can have on PRP outcomes. It was shown that high fat diets lower the efficacy of treatment while the Mediterranean diet helps promote platelet function and help efficacy. The future is to look at more diets while also integrating lifestyle choice before treatment for optimal outcomes.
ContributorsLaguna, Sebastian (Author) / Chen, Qiang (Thesis director) / Goyle, Ashu (Committee member) / Barrett, The Honors College (Contributor) / School of Life Sciences (Contributor) / Dean, W.P. Carey School of Business (Contributor)
Created2024-05
Description
Coccidioidomycosis, or valley fever (VF), is a fungal infection caused by Coccidioides that is highly endemic in southern Arizona and central California. The antibody response to infection in combination with clinical presentation and radiographic findings are often used to diagnose disease, as a highly sensitive and specific antigen-based assay has yet to be developed and commercialized. In this dissertation, a panel of monoclonal antibodies (mAbs) was generated in an attempt to identify circulating antigen in VF-positive patients. Despite utilizing a mixture of antigens, almost all mAbs obtained were against chitinase 1 (CTS1), a protein previously identified as a main component in serodiagnostic reagents. While CTS1 was undoubtedly a dominant seroreactive antigen, it was not successfully detected in circulation in patient samples prompting a shift toward further understanding the importance of CTS1 in antibody-based diagnostic assays. Interestingly, depletion of this antigen from diagnostic antigen preparations resulted in complete loss of patient IgG reactivity by immunodiffusion. This finding encouraged the development of a rapid, 10-minute point-of-care test in lateral flow assay (LFA) format to exclusively detect anti-CTS1 antibodies from human and non-human animal patients with coccidioidal infection. A CTS1 LFA was developed that demonstrated 92.9% sensitivity and 97.7% specificity when compared to current quantitative serologic assays (complement fixation and immunodiffusion). A commercially available LFA that utilizes a proprietary mixture of antigens was shown to be less sensitive (64.3%) and less specific (79.1%). This result provides evidence that a single antigen can be used to detect antibodies consistently and accurately from patients with VF. The LFA presented here shows promise as a helpful tool to rule-in or rule-out a diagnosis of VF such that patients may avoid unnecessary antibacterial treatments, improving healthcare efficiency.
ContributorsGrill, Francisca J (Author) / Lake, Douglas F (Thesis advisor) / Magee, D Mitch (Committee member) / Grys, Thomas (Committee member) / Chen, Qiang (Committee member) / Arizona State University (Publisher)
Created2023