Search Content

Application of Deep Learning Techniques for EEG Signal Classification

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…

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

Solving SPDEs for Multi-Dimensional Shape Analysis

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,…

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

Toward Reliable Graph Matching: from Deterministic Optimization to Combinatorial Learning

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…

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

Toward Reliable Graph Matching: from Deterministic Optimization to Combinatorial Learning

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…

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

A Continuous Learning Approach to Alzheimer’s Disease Progression Modeling and Domain Adaptation among Imaging Cohorts

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…

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

Deciphering the Role of Cortical Astrocytes in the Pathogenesis of C9orf72-Mediated ALS/FTD: Insights From a Patient-Derived In Vitro Model

Description

The GGGGCC (G4C2) hexanucleotide repeat expansion (HRE) in the C9orf72 gene is the most common genetic abnormality associated with both amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD), two devastatingly progressive neurodegenerative diseases. The discovery of this genetic link confirmed that ALS and FTD reside along a spectrum with clinical…

The GGGGCC (G4C2) hexanucleotide repeat expansion (HRE) in the C9orf72 gene is the most common genetic abnormality associated with both amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD), two devastatingly progressive neurodegenerative diseases. The discovery of this genetic link confirmed that ALS and FTD reside along a spectrum with clinical and pathological commonalities. Historically understood as diseases resulting in neuronal death, the role of non-neuronal cells like astrocytes is still wholly unresolved. With evidence of cortical neurodegeneration leading to cognitive impairments in C9orf72-ALS/FTD, there is a need to investigate the role of cortical astrocytes in this disease spectrum. Here, a patient-derived induced pluripotent stem cell (iPSC) cortical astrocyte model was developed to investigate consequences of C9orf72-HRE pathogenic features in this cell type. Although there were no significant C9orf72-HRE pathogenic features in cortical astrocytes, transcriptomic, proteomic and phosphoproteomic profiles elucidated global disease-related phenotypes. Specifically, aberrant expression of astrocytic-synapse proteins and secreted factors were identified. SPARCL1, a pro-synaptogenic secreted astrocyte factor was found to be selectively decreased in C9orf72-ALS/FTD iPSC-cortical astrocytes. This finding was further validated in human tissue analyses, indicating that cortical astrocytes in C9orf72-ALS/FTD exhibit a reactive transformation that is characterized by a decrease in SPARCL1 expression. Considering the evidence for substantial astrogliosis and synaptic failure leading to cognitive impairments in C9orf72-ALS/FTD, these findings represent a novel understanding of how cortical astrocytes may contribute to the cortical neurodegeneration in this disease spectrum.

ContributorsBustos, Lynette (Author) / Sattler, Rita (Thesis advisor) / Newbern, Jason (Committee member) / Zarnescu, Daniela (Committee member) / Brafman, David (Committee member) / Mehta, Shwetal (Committee member) / Arizona State University (Publisher)

Created2023

Guía para planificar acciones contra el calor para los vecindarios de la zona metropolitana de Phoenix: crear soluciones al calor urbano en el Valle del Sol

Description

En la zona metropolitana de Phoenix, el calor urbano está afectando la salud, la seguridad y la economía y se espera que estos impactos empeoren con el tiempo. Se prevé que el número de días por encima de 110˚F aumentará más del doble para el 2060. En mayo de 2017,…

En la zona metropolitana de Phoenix, el calor urbano está afectando la salud, la seguridad y la economía y se espera que estos impactos empeoren con el tiempo. Se prevé que el número de días por encima de 110˚F aumentará más del doble para el 2060. En mayo de 2017, The Nature Conservancy, el Departamento de Salud Pública del condado de Maricopa, Central Arizona Conservation Alliance, la Red de Investigación en Sostenibilidad sobre la Resiliencia Urbana a Eventos Extremos, el Centro de Investigación del Clima Urbano de Arizona State University y el Center for Whole Communities lanzaron un proceso participativo de planificación de acciones contra el calor para identificar tanto estrategias de mitigación como de adaptación a fin de reducir directamente el calor y mejorar la capacidad de los residentes para lidiar con el calor. Las organizaciones comunitarias con relaciones existentes en tres vecindarios seleccionados para la planificación de acciones contra el calor se unieron más tarde al equipo del proyecto: Phoenix Revitalization Corporation, RAILMesa y Puente Movement. Más allá de construir un plan de acción comunitario contra el calor y completar proyectos de demostración, este proceso participativo fue diseñado para desarrollar conciencia, iniciativa y cohesión social en las comunidades subrepresentadas. Asimismo el proceso de planificación de acciones contra el calor fue diseñado para servir como modelo para esfuerzos futuros de resiliencia al calor y crear una visión local, contextual y culturalmente apropiada de un futuro más seguro y saludable. El método iterativo de planificación y participación utilizado por el equipo del proyecto fortaleció las relaciones dentro y entre los vecindarios, las organizaciones comunitarias, los responsables de la toma de decisiones y el equipo núcleo, y combinó la sabiduría de la narración de historias y la evidencia científica para comprender mejor los desafíos actuales y futuros que enfrentan los residentes durante eventos de calor extremo. Como resultado de tres talleres en cada comunidad, los residentes presentaron ideas que quieren ver implementadas para aumentar su comodidad y seguridad térmica durante los días de calor extremo.

Como se muestra a continuación, las ideas de los residentes se interceptaron en torno a conceptos similares, pero las soluciones específicas variaron entre los vecindarios. Por ejemplo, a todos los vecindarios les gustaría agregar sombra a sus corredores peatonales, pero variaron las preferencias para la ubicación de las mejoras para dar sombra. Algunos vecindarios priorizaron las rutas de transporte público, otros priorizaron las rutas utilizadas por los niños en su camino a la escuela y otros quieren paradas de descanso con sombra en lugares clave. Surgieron cuatro temas estratégicos generales en los tres vecindarios: promover y educar; mejorar la comodidad/capacidad de afrontamiento; mejorar la seguridad; fortalecer la capacidad. Estos temas señalan que existen serios desafíos de seguridad contra el calor en la vida diaria de los residentes y que la comunidad, los negocios y los sectores responsables de la toma de decisión deben abordar esos desafíos.

Los elementos del plan de acción contra el calor están diseñados para incorporarse a otros esfuerzos para aliviar el calor, crear ciudades resilientes al clima y brindar salud y seguridad pública. Los socios de implementación del plan de acción contra el calor provienen de la región de la zona metropolitana de Phoenix, y se brindan recomendaciones para apoyar la transformación a una ciudad más fresca.

Para ampliar la escala de este enfoque, los miembros del equipo del proyecto recomiendan a) compromiso continuo e inversiones en estos vecindarios para implementar el cambio señalado como vital por los residentes, b) repetir el proceso de planificación de acción contra el calor con líderes comunitarios en otros vecindarios, y c) trabajar con las ciudades, los planificadores urbanos y otras partes interesadas para institucionalizar este proceso, apoyando las políticas y el uso de las métricas propuestas para crear comunidades más frescas.

ContributorsMesserschmidt, Maggie (Contributor) / Guardaro, Melissa (Contributor) / White, Jessica R. (Contributor) / Berisha, Vjollca (Contributor) / Hondula, David M. (Contributor) / Feagan, Mathieu (Contributor) / Grimm, Nancy (Contributor) / Beule, Stacie (Contributor) / Perea, Masavi (Contributor) / Ramirez, Maricruz (Contributor) / Olivas, Eva (Contributor) / Bueno, Jessica (Contributor) / Crummey, David (Contributor) / Winkle, Ryan (Contributor) / Rothballer, Kristin (Contributor) / Mocine-McQueen, Julian (Contributor) / Maurer, Maria (Artist) / Coseo, Paul (Artist) / Crank, Peter J (Designer) / Broadbent, Ashley (Designer) / McCauley, Lisa (Designer) / Nature's Cooling Systems Project (Contributor) / Nature Conservancy (U.S.) (Contributor) / Phoenix Revitalization Corporation (Contributor) / Puente Movement (Contributor) / Maricopa County (Ariz.). Department of Public Health (Contributor) / Central Arizona Conservation Alliance (Contributor) / Arizona State University. Urban Climate Research Center (Contributor) / Arizona State University. Urban Resilience to Extremes Sustainability Research Network (Contributor) / Center for Whole Communities (Contributor) / RAILmesa (Contributor) / Vitalyst Health Foundation (Funder)

Created2022

Heat Mitigation Solutions Guide for Mobile Homes

Description

According to the Centers for Disease Control and Prevention (CDC), more people die in the U.S. from heat than from all other natural disasters combined. According to the Environmental Protection Agency (EPA), more than 1,300 deaths per year in the United States are due to extreme heat. Arizona, California and…

According to the Centers for Disease Control and Prevention (CDC), more people die in the U.S. from heat than from all other natural disasters combined. According to the Environmental Protection Agency (EPA), more than 1,300 deaths per year in the United States are due to extreme heat. Arizona, California and Texas are the three states with the highest burden, accounting for 43% of all heat-related deaths according to the CDC.

Although only 5% of housing in Maricopa County, Arizona, is mobile homes, approximately 30% of indoor heat-related deaths occur in these homes. Thus, the residents of mobile homes in Maricopa County are disproportionately affected by heat. Mobile home residents are extremely exposed to heat due to the high density of mobile home parks, poor construction of dwellings, lack of vegetation, socio-demographic features and not being eligible to get utility and financial assistance.

We researched numerous solutions across different domains that could help build the heat resilience of mobile home residents. As a result we found 50 different solutions for diverse stakeholders, budgets and available resources. The goal of this toolbox is to present these solutions and to explain how to apply them in order to get the most optimal result and build About this Solutions Guide People who live in mobile homes are 6 to 8 times more likely to die of heat-associated deaths. heat resilience for mobile home residents. These solutions were designed as a coordinated set of actions for everyone — individual households, mobile home residents, mobile home park owners, cities and counties, private businesses and nonprofits serving mobile home parks, and other stakeholders — to be able to contribute to heat mitigation for mobile home residents.

When we invest in a collective, coordinated suite of solutions that are designed specifically to address the heat vulnerability of mobile homes residents, we can realize a resilience dividend in maintaining affordable, feasible, liveable housing for the 20 million Americans who choose mobile homes and manufactured housing as their place to live and thrive.

ContributorsVarfalameyeva, Katsiaryna (Author) / Solís, Patricia (Author) / Phillips, Lora A. (Author) / Charley, Elisha (Author) / Hondula, David M. (Author) / Kear, Mark (Author)

Created2021

Dynamic Routing Algorithm for Unity Traffic Simulator based on Real Traffic Data

Description

The purpose of the overall project is to create a simulated environment similar to Google map and traffic but simplified for education purposes. Students can choose different traffic patterns and program a car to navigate through the traffic dynamically based on the changing traffic. The environment used in the project…

The purpose of the overall project is to create a simulated environment similar to Google map and traffic but simplified for education purposes. Students can choose different traffic patterns and program a car to navigate through the traffic dynamically based on the changing traffic. The environment used in the project is ASU VIPLE (Visual IoT/Robotics Programming Language Environment). It is a visual programming environment for Computer Science education. VIPLE supports a number of devices and platforms, including a traffic simulator developed using Unity game engine. This thesis focuses on creating realistic traffic data for the traffic simulator and implementing dynamic routing algorithm in VIPLE. The traffic data is generated from the recorded real traffic data published at Arizona Maricopa County website. Based on the generated traffic data, VIPLE programs are developed to implement the traffic simulation based on dynamic changing traffic data.

ContributorsZhang, Zhemin (Author) / Chen, Yinong (Thesis advisor) / Wang, Yalin (Thesis advisor) / De Luca, Gennaro (Committee member) / Arizona State University (Publisher)

Created2022

Characterizing Brain Aging Trajectories in Older Adults with Autism Spectrum Disorder using a Novel Graph Theory Measure

Description

Little is known about how cognitive and brain aging patterns differ in older adults with autism spectrum disorder (ASD). However, recent evidence suggests that individuals with ASD may be at greater risk of pathological aging conditions than their neurotypical (NT) counterparts. A growing body of research indicates that older adults…

Little is known about how cognitive and brain aging patterns differ in older adults with autism spectrum disorder (ASD). However, recent evidence suggests that individuals with ASD may be at greater risk of pathological aging conditions than their neurotypical (NT) counterparts. A growing body of research indicates that older adults with ASD may experience accelerated cognitive decline and neurodegeneration as they age, although studies are limited by their cross-sectional design in a population with strong age-cohort effects. Studying aging in ASD and identifying biomarkers to predict atypical aging is important because the population of older individuals with ASD is growing. Understanding the unique challenges faced as autistic adults age is necessary to develop treatments to improve quality of life and preserve independence. In this study, a longitudinal design was used to characterize cognitive and brain aging trajectories in ASD as a function of autistic trait severity. Principal components analysis (PCA) was used to derive a cognitive metric that best explains performance variability on tasks measuring memory ability and executive function. The slope of the integrated persistent feature (SIP) was used to quantify functional connectivity; the SIP is a novel, threshold-free graph theory metric which summarizes the speed of information diffusion in the brain. Longitudinal mixed models were using to predict cognitive and brain aging trajectories (measured via the SIP) as a function of autistic trait severity, sex, and their interaction. The sensitivity of the SIP was also compared with traditional graph theory metrics. It was hypothesized that older adults with ASD would experience accelerated cognitive and brain aging and furthermore, age-related changes in brain network topology would predict age-related changes in cognitive performance. For both cognitive and brain aging, autistic traits and sex interacted to predict trajectories, such that older men with high autistic traits were most at risk for poorer outcomes. In men with autism, variability in SIP scores across time points trended toward predicting cognitive aging trajectories. Findings also suggested that autistic traits are more sensitive to differences in brain aging than diagnostic group and that the SIP is more sensitive to brain aging trajectories than other graph theory metrics. However, further research is required to determine how physiological biomarkers such as the SIP are associated with cognitive outcomes.

ContributorsSullivan, Georgia (Author) / Braden, Blair (Thesis advisor) / Kodibagkar, Vikram (Thesis advisor) / Schaefer, Sydney (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)

Created2022

Filtering by