Computer Sciences Commons^™

Contextual Understanding Of Sequential Data Across Multiple Modalities, Sangwoo Cho

Electronic Theses and Dissertations, 2020-2023

In recent years, progress in computing and networking has made it possible to collect large volumes of data for various different applications in data mining and data analytics using machine learning methods. Data may come from different sources and in different shapes and forms depending on their inherent nature and the acquisition process. In this dissertation, we focus specifically on sequential data, which have been exponentially growing in recent years on platforms such as YouTube, social media, news agency sites, and other platforms. An important characteristic of sequential data is the inherent causal structure with latent patterns that can be …

Fine-Grained Lower Bounds For Problems On Strings And Graphs, Gary Thomas Hoppenworth

Honors Undergraduate Theses

The motivation of this thesis is to present new lower bounds for important computational problems on strings and graphs, conditioned on plausible conjectures in theoretical computer science. These lower bounds, called conditional lower bounds, are a topic of immense interest in the field of fine-grained complexity, which aims to develop a better understanding of the hardness of problems that can be solved in polynomial time. In this thesis, we give new conditional lower bounds for four interesting computational problems: the median and center string edit distance problems, the pattern matching on labeled graphs problem, and the subtree isomorphism problem. These …

Family Communication: Examining The Differing Perceptions Of Parents And Teens Regarding Online Safety Communication, Tara Rutkowski

Honors Undergraduate Theses

The opportunity for online engagement increases possible exposure to potentially risky behaviors for teens, which may have significant negative consequences (Hair et al., 2009). Effective family communication about online safety can help reduce the risky adolescent behavior and limit the consequences after it occurs. This paper contributes a theory of communication factors that positively influence teen and parent perception of communication about online safety and provides design implications based on those findings. Previous work identified gaps in family communication, however, this study seeks to empirically identify factors that would close the communication gap from the perspective of both teens and …

Synchronization And Analysis Of Multimodal Medical Data, Nafisa N. Mostofa

Honors Undergraduate Theses

The United States suffers from a significant disparity in the availability of the medical resources and expertise among different regions of the country. Patients in rural areas may not have the opportunity to consult with a physician until their disease progresses to later stages, resulting in a considerable decrease in quality of life. Advances in telemedicine systems that can provide remote communication, medical data acquisition, and medical data analysis promise a significant improvement to early access to medical care and diagnoses for disadvantaged individuals.

In this thesis, we make several contributions on topics that contribute to the improvement of telemedicine …

Computational Study Of Target Gene Interactions - Enhancers And Micrornas, Amlan Talukder

Electronic Theses and Dissertations, 2020-2023

Gene expression is an essential mechanism for physical and mental development of human. Aberrant regulation of gene expression creates abnormality in human body than can lead to complicated diseases. Gene expression can be regulated at any stage from the chromatin unfolding stage to post-translation stage of protein. In this study, we focused on two important factors of gene expression regulation that participate in the gene expression process at the transcription and the post-transcriptional stages; enhancer-promoter interactions and miRNA-mRNA interactions. The enhancer-promoter interactions are difficult to detect due to the large distance between the enhancer and promoter region and cell-specific activity …

Evaluating Augmented Reality Tools For Physics Education, Corey Pittman

Electronic Theses and Dissertations, 2020-2023

While we are in the midst of a renaissance of interest in augmented reality (AR), there remain a small number of application domains that have seen significant development. One domain that often benefits from additional visualization capabilities is education, specifically physics and other sciences. This paper summarizes interviews with secondary school educators about their experience with AR and their most desired features. Three prototypes were created which were used to collect usability information from students and educators about their preferences for AR applications in their physics courses. Additionally, we introduce the concept of Environmental Integration, a novel method of defining …

Reviving Mozart With Intelligence Duplication, Jacob E. Galajda

Honors Undergraduate Theses

Deep learning has been applied to many problems that are too complex to solve through an algorithm. Most of these problems have not required the specific expertise of a certain individual or group; most applied networks learn information that is shared across humans intuitively. Deep learning has encountered very few problems that would require the expertise of a certain individual or group to solve, and there has yet to be a defined class of networks capable of achieving this. Such networks could duplicate the intelligence of a person relative to a specific task, such as their writing style or music …

Examining Everyday Literacies: An Autoethnographic Analysis Of Mundane Textualities, Kyle J. Mauter

Honors Undergraduate Theses

As a way of extending perspectives of writing and learning, this thesis explores everyday literacy activities and their role in function in shaping people's activities. Taking up an autoethnographic approach to studying the mundane literacies of everyday life, this thesis offers a fine-grained analysis of the processes and practices involved in two specific literate activities I have engaged in over the two years: creating a mixtape for a friend and streaming my participation in online video games. As key findings, the analysis of these everyday literate activities suggests that the interactions between people and social contexts figure prominently in the …

Recapture: A Virtual Reality Interactive Narrative Experience Concerning Perspectives And Self-Reflection, Indira Avendano

Honors Undergraduate Theses

This project presents a virtual reality (VR) Interactive Narrative aiming to leave users reflecting on the perspectives one chooses to view life through. The narrative is driven by interactions designed using the concept of procedural rhetoric, which explores how rules and mechanics in games can persuade people about an idea, and Shin's cognitive model, which presents a dynamic view of immersion in VR. The persuasive nature of procedural rhetoric in combination with immersion techniques such as tangible interfaces and first-person elements of VR can effectively work together to immerse users into a compelling narrative experience with an intended emotional response …

A Deep Learning Approach For Learning Human Gait Signature, Alexander Matasa

Electronic Theses and Dissertations, 2020-2023

With advancements in biometric securities, focus has increased on utilizing gait as a means of recognition. Gait describes the unique walking pattern present in humans and has shown promising results in person re-identification tasks. Unlike other biometric features, gait is unique in that it is a subconscious behavior minimizing the risk of purposeful obfuscation. In this research, we first cover supervised approaches showing that current methods fail to learn a unique signature that describes the motion of a subject. Rather they extract frame-based feature information which is then aggregated. While these methods have shown to be effective, they do not …

Analyzing The Blockchain Attack Surface: A Top-Down Approach, Muhammad Saad

Electronic Theses and Dissertations, 2020-2023

Blockchains enable secure asset exchange in a distributed system, thereby facilitating innovative applications such as cryptocurrencies and smart contracts. Although the cryptographic constructs of blockchains are highly secure, however, their practical deployments are vulnerable to various attacks due to their application-specific policies, and their peer-to-peer (P2P) network intricacies. In this work, we take a top-down approach towards exploring those attacks, starting with the application-specific abuse of blockchain-based cryptocurrencies and concluding with the network conditions that violate the blockchain consistency. In the top-down approach, we first analyze the application-specific abuse of blockchain-based cryptocurrencies by uncovering (1) covert cryptocurrency mining in the …

Secure And Trustworthy Hardware And Machine Learning Systems For Internet Of Things, Shayan Taheri

Electronic Theses and Dissertations, 2020-2023

The advancements on the Internet have enabled connecting more devices into this technology every day. This great connectivity has led to the introduction of the internet of things (IoTs) that is a great bed for engagement of all new technologies for computing devices and systems. Nowadays, the IoT devices and systems have applications in many sensitive areas including military systems. These challenges target hardware and software elements of IoT devices and systems. Integration of hardware and software elements leads to hardware systems and software systems in the IoT platforms, respectively. A recent trend for the hardware systems is making them …

Evaluating Pmo Sync Implementation For Persistent Memory Object, Faishal Wahiduddin

Electronic Theses and Dissertations, 2020-2023

Persistent Memory, in the form of byte-addressable Non-Volatile Memories (NVMs), provides a low-cost and high-capacity main memory, and provides the ability to store and retain data even when the system is powered off, along with improved performance over traditional storage. Persistent Memory Direct Access (DAX) enables applications to perform byte-addressable operations such as load and store. Filesystem-DAX can store persistent data in NVMs with system call overheads. In order to reduce filesystem overheads, this study utilizes Persistent Memory Object (PMO) as an abstraction for persistent data containers on Non-Volatile Memory (NVM). Persisting data in Persistent Memory Object requires that the …

Towards Improving The Robustness Of Neural Abstractive Summarization, Kaiqiang Song

Electronic Theses and Dissertations, 2020-2023

Recent deep learning and sequence-to-sequence learning technology have produced impressive results on automatic summarization. However, the models have limited insights on the underlying language and it remains challenging for system-generated summaries to be truthful to the original input or cover the most important information. This is especially the case for generating abstractive summaries using neural models. My work aims for a flexible and controllable summarization system that can be adapted to cater to different scenarios. It is designed to incorporate linguistic structure information into deep neural networks, have the capability to produce abstracts by re-using a varying amount of source …

Unmanned Aerial Vehicles In Opportunistic Networks, Salih Safa Bacanli

Electronic Theses and Dissertations, 2020-2023

This dissertation presents novel algorithms for utilizing unmanned aerial vehicles (UAVs) through various scenarios within opportunistic networks. The opportunistic networks are considered challenging due to the intermittent and unreliable communication between nodes. UAVs can be used for delivering packets within opportunistic networks that can alleviate communication issues. We start examining the UAV usage in opportunistic networks by first investigating their effectiveness and proposing a UAV scanning approach. To validate the usage of UAVs, we evaluated the performance of an opportunistic network with and without using UAVs. The scanning techniques we investigated were random scan, meander scan, and our proposed approach …

Exploring Relationships Between Ground And Aerial Views By Synthesis And Matching, Krishna Regmi

Electronic Theses and Dissertations, 2020-2023

Cross-view images, referring to the images taken from aerial and street views, contain drastically differing representations of the same scene of a given location. Due to the differences in the camera viewpoints of ground and aerial images the same semantic concepts in the two viewpoints look very different. Therefore the problem of relating them is very challenging. Thus, it becomes crucial to explore the cross-view relations and learn appropriate representations such that images from these two domains can be associated. In this dissertation we explore the relationship between ground and aerial views by synthesis and matching. First, we explore supervised …

Test Overfitting In Automated Program Repair: Measurements And Approaches Using Formal Methods, Amirfarhad Nilizadeh

Electronic Theses and Dissertations, 2020-2023

Bugs exist in software systems; unfortunately, manually finding bugs and repairing them is complex, time-consuming, and expensive. Automated Program Repair (APR) techniques have promising results to make the debugging process automatic and dramatically decreasing the cost of developing a software system. Almost all developed APR tools use test suites to bug localization and evaluate generated candidate patches' correctness; thus, it is named dynamic APR. Test overfitting is one of the main challenges of dynamic APR tools, which is evident from several recent studies. Test overfitting means the repaired program is not correct based on the program's expected behavior while the …

Towards Enabling Explanation In Safety-Critical Artificial Intelligence Systems, Andy Michel

Electronic Theses and Dissertations, 2020-2023

With the advancement of accelerated hardware in recent years, there has been a surge in the development and application of intelligent systems. Deep learning systems, in particular, have shown exciting results in a wide range of tasks: classification, detection, and recognition. Despite these remarkable achievements, there remains an active research area that aims to increase the robustness of those systems in critical domains. Deep learning algorithms have proven to be brittle against adversarial attacks. That is, carefully crafted adversarial inputs can consistently trigger an erroneous prediction from a network model. Hence the motivation of this dissertation, we study prominent adversarial …

Spatio-Temporal Representation For Reasoning With Action Genome, Kesar Tumkur Narasimhamurthy

Electronic Theses and Dissertations, 2020-2023

Representing Spatio-temporal information in videos has proven to be a difficult task compared to action recognition in videos involving multiple actions. A single activity consists many smaller actions that can provide a better understanding of the activity. This paper tries to represent the varying information in a scene-graph format in order to answer temporal questions to obtain improved insights for the video, resulting in a directed temporal information graph. This project will use the Action Genome dataset, which is a variation of the charades dataset, to capture pairwise relationships in a graph. The model performs significantly better than the benchmark …

Learning Accurate And Robust Deep Visual Models, Yandong Li

Electronic Theses and Dissertations, 2020-2023

Over the last decade, we have witnessed the renaissance of deep neural networks (DNNs) and their successful applications in computer vision. There is still a long way to build intelligent and reliable machine vision systems, but DNNs provide a promising direction. The goal of this thesis is to present a few small steps along this road. We mainly focus on two questions: How to design label-efficient learning algorithms for computer vision tasks? How to improve the robustness of DNN based visual models? Concerning label-efficiency, we investigate a reinforced sequential model for video summarization, a background hallucination strategy for high-resolution image …

Implication Of Manifold Assumption In Deep Learning Models For Computer Vision Applications, Marzieh Edraki

Electronic Theses and Dissertations, 2020-2023

The Deep Neural Networks (DNN) have become the main contributor in the field of machine learning (ML). Specifically in the computer vision (CV), there are applications like image and video classification, object detection and tracking, instance segmentation and visual question answering, image and video generation are some of the applications from many that DNNs have demonstrated magnificent progress. To achieve the best performance, the DNNs usually require a large number of labeled samples, and finding the optimal solution for such complex models with millions of parameters is a challenging task. It is known that, the data are not uniformly distributed …

Visual Learning Beyond Human Curated Datasets, Muhammad Abdullah Jamal

Electronic Theses and Dissertations, 2020-2023

The success of deep neural networks in a variety of computer vision tasks heavily relies on large- scale datasets. However, it is expensive to manually acquire labels for large datasets. Given the human annotation cost and scarcity of data, the challenge is to learn efficiently with insufficiently labeled data. In this dissertation, we propose several approaches towards data-efficient learning in the context of few-shot learning, long-tailed visual recognition, and unsupervised and semi-supervised learning. In the first part, we propose a novel paradigm of Task-Agnostic Meta- Learning (TAML) algorithms to improve few-shot learning. Furthermore, in the second part, we analyze the …

Spatial-Temporal Representation Learning: Concepts, Algorithms And Applications, Pengyang Wang

Electronic Theses and Dissertations, 2020-2023

Recent years have witnessed the flourish of Internet-of-Things (IoT), in which sensors connect spatial entities to constitute complex Cyber-Physical Systems (CPSs). In this setting, spatial-temporal data becomes increasingly available. Mining spatial-temporal data can reveal holistic user and system structures, dynamics, and semantics of the underlying CPSs, including identifying trends, forecasting future behavior, and detecting anomalies. However, obtaining effective representations over spatial-temporal data remains a big challenge for the following reasons: (1) on the one hand, traditional manual feature design is labor-intensive and time-consuming facing the complex and huge volumes of spatial-temporal data; (2) on the other hand, as an emerging …

Lulling Waters: A Poetry Reading For Real-Time Music Generation Through Emotion Mapping, Ashley Muniz, Toshihisa Tsuruoka

Electronic Literature Organization Conference 2020

Through a poetic narrative, “Lulling Waters” tells the story of a whale overcoming the loss of his mother, who passed away from ingesting plastic, as he attempts to escape from the polluted oceanic world. The live performance of this poem utilizes a software system called Soundwriter, which was developed with the goal of enriching the oral storytelling experience through music. This video demonstrates how Soundwriter’s real-time hybrid system was able to analyze “Lulling Waters” through its lexical and auditory features. Emotionally salient words were given ratings based on arousal, valence, and dominance while the emotionally charged prosodic features of the …

Poetry For Seers Or The Peruvian Visual Poetic Tradition In Front Of New Media, Michael Hurtado, Pamela Medina, Enrique García, Michael Prado

Electronic Literature Organization Conference 2020

Since the first decades of the twentieth century, Peruvian poetic tradition has been characterized by experimental uses of language. Among these possibilities, some records tensioned this medium from the link with the plastic arts, as in the case of the poetry of José María Eguren, while others opted for the playing with the spatiality and visuality of the blank sheet, such as in the case of the work of Carlos Oquendo de Amat. However, it is not until the appearance of the poetry of César Vallejo, specifically with a poems like Trilce in 1922, that these breakages force us to …

From Ai With Love: Reading Big Data Poetry Through Gilbert Simondon’S Theory Of Transduction, Andrew Klobucar

Electronic Literature Organization Conference 2020

Computation initiated a far-reaching re-imagination of language, not just as an information tool, but as a social, bio-physical activity in general. Modern lexicology provides an important overview of the ongoing development of textual documentation and its applications in relation to language and linguistics. At the same time, the evolution of lexical tools from the first dictionaries and graphs to algorithmically generated scatter plots of live online interaction patterns has been surprisingly swift. Modern communication and information studies from Norbert Weiner to the present-day support direct parallels between coding and linguistic systems. However, most theories of computation as a model of …

Why Are We Like This?: Exploring Writing Mechanics For An Ai-Augmented Storytelling Game, Max Kreminski, Melanie Dickinson, Michael Mateas, Noah Wardrip-Fruin

Electronic Literature Organization Conference 2020

Why Are We Like This? (WAWLT) is a playful, co-creative, AI-augmented, improvisational storytelling game in which one or more players explore and influence an ongoing simulation which they then glean for narrative material. It uses the recently developed simulation technology of story sifting (the recognition of microstories in a chronicle of simulation events), via the Felt library, to afford a new kind of playful, social, and creative writing experience. In this paper, we discuss our primary design goals: (1) using computation and interaction design to support casual player creativity, and (2) foregrounding character subjectivity as a driver for …

Autopia And The Truelist: Language Combined In Two Computer-Generated Books, Nick Montfort

Electronic Literature Organization Conference 2020

Autopia (Troll Thread, 2016) and The Truelist (Counterpath, 2017) are computer-generated literary books. I reported at ELO 2014 on two of my text-generating “novel machines” (Montfort 2014). The two projects discussed in this paper are about novel-size, but are different sorts of projects. Autopia’s text consists of headline-style sentences made entirely of the singular and plural names of cars. This project manifests not only as a print-on-demand book from a post-digital publisher, but also as a web project and a gallery installation. The Truelist’s 140 pages of verse are available in offset printed book form and also as a …

Mind The Gap: Understanding Stakeholder Reactions To Different Types Of Data Security, Audra Diers-Lawson, Amelia Symons

International Crisis and Risk Communication Conference

Data security breaches are an increasingly common problem for organizations, yet there are critical gaps in our understanding of how different stakeholders understand and evaluate organizations that have experienced these kinds of security breaches. While organizations have developed relatively standard approaches to responding to security breaches that: (1) acknowledge the situation; (2) highlight how much they value their stakeholders’ privacy and private information; and (3) focus on correcting and preventing the problem in the future, the effectiveness of this response strategy and factors influencing it have not been adequately explored. This experiment focuses on a 2 (type of organization) x …

Learning Transferable Representations For Visual Recognition, Yang Zhang

Electronic Theses and Dissertations, 2020-2023

In the last half-decade, a new renaissance of machine learning originates from the applications of convolutional neural networks to visual recognition tasks. It is believed that a combination of big curated data and novel deep learning techniques can lead to unprecedented results. However, the increasingly large training data is still a drop in the ocean compared with scenarios in the wild. In this literature, we focus on learning transferable representation in the neural networks to ensure the models stay robust, even given different data distributions. We present three exemplar topics in three chapters, respectively: zero-shot learning, domain adaptation, and generalizable …