Computer Sciences Commons^™

On Performance Optimization And Prediction Of Parallel Computing Frameworks In Big Data Systems, Haifa Alquwaiee

Dissertations

A wide spectrum of big data applications in science, engineering, and industry generate large datasets, which must be managed and processed in a timely and reliable manner for knowledge discovery. These tasks are now commonly executed in big data computing systems exemplified by Hadoop based on parallel processing and distributed storage and management. For example, many companies and research institutions have developed and deployed big data systems on top of NoSQL databases such as HBase and MongoDB, and parallel computing frameworks such as MapReduce and Spark, to ensure timely data analyses and efficient result delivery for decision making and business …

Private And Federated Deep Learning: System, Theory, And Applications For Social Good, Han Hu

Dissertations

During the past decade, drug abuse continues to accelerate towards becoming the most severe public health problem in the United States. The ability to detect drug­abuse risk behavior at a population scale, such as among the population of Twitter users, can help to monitor the trend of drug­abuse incidents. However, traditional methods do not effectively detect drug­abuse risk behavior in tweets, mainly due to the sparsity of such tweets and the noisy nature of tweets. In the first part of this dissertation work, the task of classifying tweets as containing drug­abuse risk behavior or not, is studied. Millions of public …

A Practical Approach To Automated Software Correctness Enhancement, Aleksandr Zakharchenko

Dissertations

To repair an incorrect program does not mean to make it correct; it only means to make it more-correct, in some sense, than it is. In the absence of a concept of relative correctness, i.e. the property of a program to be more-correct than another with respect to a specification, the discipline of program repair has resorted to various approximations of absolute (traditional) correctness, with varying degrees of success. This shortcoming is concealed by the fact that most program repair tools are tested on basic cases, whence making them absolutely correct is not clearly distinguishable from making them relatively more-correct. …

Parameter Estimation And Inference Of Spatial Autoregressive Model By Stochastic Gradient Descent, Gan Luan

Dissertations

Stochastic gradient descent (SGD) is a popular iterative method for model parameter estimation in large-scale data and online learning settings since it goes through the data in only one pass. While SGD has been well studied for independent data, its application to spatially-correlated data largely remains unexplored. This dissertation develops SGD-based parameter estimation and statistical inference algorithms for the spatial autoregressive (SAR) model, a common model for spatial lattice data.

This research contains three parts. (I) The first part concerns SGD estimation and inference for the SAR mean regression model. A new SGD algorithm based on maximum likelihood estimator (MLE) …

Scalable Scientific Data Management On High-Performance Computing Systems, Zhenbo Qiao

Dissertations

As high-performance computing (HPC) is being scaled up to exascale to accommodate new modeling and simulation needs, I/O has continued to be a major bottleneck in the end-to-end scientific processes. To bridge the widening gap between compute and I/O, and enable data to be more efficiently stored and analyzed, simulation outputs need to be refactored, reduced, and appropriately mapped to storage tiers. Also, a major question that the community is striving to answer is how to co-design data storage and complex physics-rich analytics in a way that the time to knowledge can be minimized in post-processing. As HPC storage systems …

Machine Learning And Computer Vision In Solar Physics, Haodi Jiang

Dissertations

In the recent decades, the difficult task of understanding and predicting violent solar eruptions and their terrestrial impacts has become a strategic national priority, as it affects the life of human beings, including communication, transportation, the power grid, national defense, space travel, and more. This dissertation explores new machine learning and computer vision techniques to tackle this difficult task. Specifically, the dissertation addresses four interrelated problems in solar physics: magnetic flux tracking, fibril tracing, Stokes inversion and vector magnetogram generation.

First, the dissertation presents a new deep learning method, named SolarUnet, to identify and track solar magnetic flux elements in …

On Non-Linear Network Embedding Methods, Huong Yen Le

Dissertations

As a linear method, spectral clustering is the only network embedding algorithm that offers both a provably fast computation and an advanced theoretical understanding. The accuracy of spectral clustering depends on the Cheeger ratio defined as the ratio between the graph conductance and the 2nd smallest eigenvalue of its normalizedLaplacian. In several graph families whose Cheeger ratio reaches its upper bound of Theta(n), the approximation power of spectral clustering is proven to perform poorly. Moreover, recent non-linear network embedding methods have surpassed spectral clustering by state-of-the-art performance with little to no theoretical understanding to back them.

The dissertation includes work …

Exploring, Understanding, Then Designing: Twitter Users’ Sharing Behavior For Minor Safety Incidents, Mashael Yousef Almoqbel

Dissertations

Social media has become an integral part of human lives. Social media users resort to these platforms for various reasons. Users of these platforms spend a lot of time creating, reading, and sharing content, therefore, providing a wealth of available information for everyone to use. The research community has taken advantage of this and produced many publications that allow us to better understand human behavior. An important subject that is sometimes discussed and shared on social media is public safety. In the past, Twitter users have used the platform to share incidents, share information about incidents, victims and perpetrators, and …

Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue

Dissertations

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …

Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie

Dissertations

This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.

In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.

In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …

Data-Driven Learning For Robot Physical Intelligence, Leidi Zhao

Dissertations

The physical intelligence, which emphasizes physical capabilities such as dexterous manipulation and dynamic mobility, is essential for robots to physically coexist with humans. Much research on robot physical intelligence has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this dissertation, a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation is proposed. This method tackles …

Participatory Learning: Measuring Learning And Educational Technology Acceptance, Erick Sanchez Suasnabar

Dissertations

Participatory Learning (PL) integrates several learning approaches, engaging students throughout the entire assignment process for both online and face-to-face courses. Beyond simply providing a solution, students also craft a problem (problem-based learning), grade each other (peer assessment and feedback), evaluate themselves (self-assessment), and can view others’ work (learning by example). This dissertation research explores the resulting learning effects. Contributions to both educational and Information Systems research include extending an early PL model and experiments that applied the PL approach to examinations, by validating and testing new constructs based on user activity and critical thinking. In addition, the study explores a …

Designing Collaborative Lifelogging To Facilitate Learning In Collaborative Physical-Recreation Communities, Sayed Mousa Ahmadi Olounabadi

Dissertations

Since the 1940s, researchers have envisioned lifelogging as the systematic capture and utilization of lived experiences for augmenting learning, performance, and community Unfortunately, this vision was never actualized since few, if any, systems support lifelogging in the term's original sense. Technologies that emerged through the Quantified-Self (QS) movement allowed users to monitor and track almost every life aspect. However, the decontextualized self-tracking data QS systems produced are unsuitable for supporting learning and community engagement, and therefore have not made lifelogging a reality yet. Central to this dissertation is understanding how to augment learning and community through lifelogging. This is particularly …

Reserve Price Optimization In Display Advertising, Achir Kalra

Dissertations

Display advertising is the main type of online advertising, and it comes in the form of banner ads and rich media on publishers' websites. Publishers sell ad impressions, where an impression is one display of an ad in a web page. A common way to sell ad impressions is through real-time bidding (RTB). In 2019, advertisers in the United States spent nearly 60 billion U.S. dollars on programmatic digital display advertising. By 2022, expenditures are expected to increase to nearly 95 billion U.S. dollars. In general, the remaining impressions are sold directly by the publishers. The only way for publishers …

Advances In Deep Learning With Applications To Computer Vision And Astronomy, Zhihang Hu

Dissertations

Deep Learning has spanned a variety of applications in computer vision as well as computational astronomy. These two aspects obtained similar data structure, therefore, their solutions can be transferable between each other. This dissertation look into two video-related tasks in computer vision and propose a novel problem in computational astronomy.

Specifically, acquiring an in-depth understanding of videos has been a cornerstone problem in computer vision. This problem has been studied by various researchers from different perspectives, among which video prediction has attracted much attention. Video prediction aims to generate the pixels of future frames given a sequence of context frames. …

Novel Statistical Modeling Methods For Traffic Video Analysis, Hang Shi

Dissertations

Video analysis is an active and rapidly expanding research area in computer vision and artificial intelligence due to its broad applications in modern society. Many methods have been proposed to analyze the videos, but many challenging factors remain untackled. In this dissertation, four statistical modeling methods are proposed to address some challenging traffic video analysis problems under adverse illumination and weather conditions.

First, a new foreground detection method is presented to detect the foreground objects in videos. A novel Global Foreground Modeling (GFM) method, which estimates a global probability density function for the foreground and applies the Bayes decision rule …

Methods For Extending Biomedical Reference Ontologies And Interface Terminologies For Ehrr Text Annotation, Vipina Kuttichi Keloth

Dissertations

Biomedical ontologies and terminologies are a cornerstone in various electronic health record systems (EHRs) for encoding information related to diseases, diagnoses, treatments, etc. Ontologies in general represent entities (concepts) and events along with all interdependent properties and relationships in an efficient way to facilitate easy access, retrieval and sharing. With the landscape of medicine rapidly changing, biomedical ontologies and terminologies need to rapidly evolve to support interoperability, medical coding, record keeping, and healthcare activities in general, and to facilitate interdisciplinary research. Extending ontologies by identifying new and missing concepts plays a vital role in the maintenance of ontologies to keep …

Development Of Deep Learning Neural Network For Ecological And Medical Images, Shaobo Liu

Dissertations

Deep learning in computer vision and image processing has attracted attentions from various fields including ecology and medical image. Ecologists are interested in finding an effective model structure to classify different species. Tradition deep learning model use a convolutional neural network, such as LeNet, AlexNet, VGG models, residual neural network, and inception models, are first used on classifying bee wing and butterfly datasets. However, insufficient data sample and unbalanced samples in each class have caused a poor accuracy. To make improvement the test accuracy, data augmentation and transfer learning are applied. Recently developed deep learning framework based on mathematical morphology …

Intelligent And Secure Fog-Aided Internet Of Drones, Jingjing Yao

Dissertations

Internet of drones (IoD), which utilize drones as Internet of Things (IoT) devices, deploys several drones in the air to collect ground information and send them to the IoD gateway for further processing. Computing tasks are usually offloaded to the cloud data center for intensive processing. However, many IoD applications require real-time processing and event response (e.g., disaster response and virtual reality applications). Hence, data processing by the remote cloud may not satisfy the strict latency requirement. Fog computing attaches fog nodes, which are equipped with computing, storage and networking resources, to IoD gateways to assume a substantial amount of …

Impact Of User Traversal On Performance Of Stem Learners In Immersive Virtual Environments, Eric W. Nersesian

Dissertations

The emerging technologies of augmented and virtual reality (AR/VR) may have vast implications to societal communication and representation of information. AR/VR computer interfaces are unique in that they may be placed spatially around the user in three-dimensional (3D) space; this affords new methods of both presentation and user interaction with the target information.

This may be especially impactful in the education of science, technology, engineering, and mathematics (STEM) professionals. Prior research has shown that simulations and visualizations improve the performance of STEM learners compared to live instruction and textbook reading. Yet, research into AR/VR as a learning environment for widespread …

Deep Learning On Image Forensics And Anti-Forensics, Zhangyi Shen

Dissertations

Image forensics protect the authenticity and integrity of digital images. On the contrary, as the countermeasures of digital forensics, anti-forensics is applied to expose the vulnerability of forensics tools. Consequently, forensics researchers could develop forensics tools against possible new attacks. This dissertation investigation demonstrates two image forensics methods based on convolutional neural network (CNN) and two image anti-forensics methods based on generative adversarial network (GAN).

Detecting unsharp masking (USM) sharpened image is the first study in this dissertation. A CNN architecture comprises four convolutional layers and a classification module is proposed to discriminate sharpened images and unsharpened images. The results …

Towards Improving The Security Of The Software Supply Chain, Hammad Afzali

Dissertations

A software supply chain comprises a series of steps performed to develop and distribute a software product. History has shown that each of these steps is vulnerable to attacks that can have serious repercussions and can affect many users at once. To address the attacks against the software supply chain, end users must be provided with verifiable guarantees about the individual steps of the chain and with assurances that the steps are securely chained together.

In this dissertation, the security of several individual steps in the software supply chain is enhanced. The first step of the chain, managing the source …

Improving Multi-Threaded Qos In Clouds, Weiwei Jia

Dissertations

Multi-threading and resource sharing are pervasive and critical in clouds and data-centers. In order to ease management, save energy and improve resource utilization, multi-threaded applications from different tenants are often encapsulated in virtual machines (VMs) and consolidated on to the same servers. Unfortunately, despite much effort, it is still extremely challenging to maintain high quality of service (QoS) for multi-threaded applications of different tenants in clouds, and these applications often suffer severe performance degradation, poor scalability, unfair resource allocation, and so on.

The dissertation identifies the causes of the QoS problems and improves the QoS of multi-threaded execution with three …

Land Cover Image Segmentation Based On Individual Class Binary Segmentation, Sathyanarayanan Somasunder

Theses

Remote sensing techniques have been developed over the past decades to acquire data without being in contact of the target object or data source. Their application on land-cover image segmentation has attracted significant attention in recent years. With the help of satellites, scientists and researchers can collect and store high resolution image data that can be further processed, segmented, and classified. However, these research results have not yet been synthesized to provide coherent guidance on the effect of variant land-cover segmentation processes. In this paper, we present a novel model that augments segmentation using smaller networks to segment individual classes. …

Rm-Net: Rasterizing Markov Signals To Images For Deep Learning, Kajal Gupta

Theses

Statistical machine learning approaches are quite famous for processing Markov signal data. They can model unobserved states and learn certain characteristics particular to a signal with good accuracy. However, with the advent of Deep learning the novice ways of solving a problem has shifted towards this more sophisticated algorithm, which is much better, powerful and more accurate. Specifically, Convolutional Neural Nets (CNN) have shown many promising results on images and videos. Here we illustrate how CNN can be applied to a 1D numeric signal using signal rasterization technique. We start by rasterizing a 1D numeric Markov signal into an image …

Coordination, Adaptation, And Complexity In Decision Fusion, Weiqiang Dong

Dissertations

A parallel decentralized binary decision fusion architecture employs a bank of local detectors (LDs) that access a commonly-observed phenomenon. The system makes a binary decision about the phenomenon, accepting one of two hypotheses (H0 (“absent”) or H1 (“present”)). The k 1 LD uses a local decision rule to compress its local observations yk into a binary local decision uk; uk = 0 if the k 1 LD accepts H0 and uk = 1 if it accepts H1. The k 1 LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center (DFC). The DFC combines the …

Drone-Assisted Emergency Communications, Di Wu

Dissertations

Drone-mounted base stations (DBSs) have been proposed to extend coverage and improve communications between mobile users (MUs) and their corresponding macro base stations (MBSs). Different from the base stations on the ground, DBSs can flexibly fly over and close to MUs to establish a better vantage for communications. Thus, the pathloss between a DBS and an MU can be much smaller than that between the MU and MBS. In addition, by hovering in the air, the DBS can likely establish a Line-of-Sight link to the MBS. DBSs can be leveraged to recover communications in a large natural disaster struck area …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Supporting User Interaction And Social Relationship Formation In A Collaborative Online Shopping Context, Yu Xu

Dissertations

The combination of online shopping and social media allow people with similar shopping interests and experiences to share, comment, and discuss about shopping from anywhere and at any time, which also leads to the emergence of online shopping communities. Today, more people turn to online platforms to share their opinions about products, solicit various opinions from their friends, family members, and other customers, and have fun through interactions with others with similar interests. This dissertation explores how collaborative online shopping presents itself as a context and platform for users' interpersonal interactions and social relationship formation through a series of studies. …

Performance Optimization Of Big Data Computing Workflows For Batch And Stream Data Processing In Multi-Clouds, Huiyan Cao

Dissertations

Workflow techniques have been widely used as a major computing solution in many science domains. With the rapid deployment of cloud infrastructures around the globe and the economic benefits of cloud-based computing and storage services, an increasing number of scientific workflows have migrated or are in active transition to clouds. As the scale of scientific applications continues to grow, it is now common to deploy various data- and network-intensive computing workflows such as serial computing workflows, MapReduce/Spark-based workflows, and Storm-based stream data processing workflows in multi-cloud environments, where inter-cloud data transfer oftentimes plays a significant role in both workflow performance …