Search Constraints

Start Over
Filtering by: Creator Glasheen, Richard Michael Remove constraint Creator: Glasheen, Richard Michael Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science

Search Results

  • Characterizing Server Compromise: Resilience Models, Instantiations, and Impossibilities

    Creator:
    McQuoid, Ian M.
    Abstract:
    One of the pervasive problems arising in our modern, digital world surrounds data breaches where an adversary, through zero-day exploitations, phishing, or old-fashioned social engineering attacks, gains access to a service’s data stores. Our society increasingly relies on these cloud-based services for everything from our taxes to personal communication. As...
    Resource Type:
    Dissertation

  • New constructions and applications for homomorphic secret sharing and function secret sharing

    Creator:
    Singh, Jaspal
    Abstract:
    A secret sharing scheme allows a dealer to distribute a secret with a set of parties, such that only a certain subset of parties can collaborate and learn the shared secret. Traditional secret sharing schemes have been used as building blocks in various subdomains of cryptography. Recently, two new extensions...
    Resource Type:
    Dissertation

  • Distributed OpenCL : a platform for distributed, heterogeneous computing for domain scientists

    Creator:
    Dillon, William H.
    Abstract:
    It is possible to purchase, for as little as $10,000, a cluster of computers with the capability to rival the supercomputers of only a few years ago. Now, users that have little to no experience developing distributed applications or managing a cluster are in a position to do so. To...
    Resource Type:
    Dissertation
    Full Text:
    Abstract approved: __________________________________________ Michael J. Bailey It is possible to

  • Layered rendering model for human teeth

    Creator:
    Shetty, Sudarshanram
    Abstract:
    This study introduces a layered model for rendering human teeth. Human teeth exhibit complex light interaction due to their layered structure. While the lighting responses of teeth have been studied in the dental industry for the production of realistic looking dentures, to our knowledge this is the first study of...
    Resource Type:
    Masters Thesis
    Full Text:
    Model for Human Teeth Abstract approved: Michael J. Bailey This study introduces a layered model for

  • A Multiresolution Analysis of Temporal Logic

    Creator:
    Pelphrey, Richard E.
    Abstract:
    Is it possible to determine whether a signal violates a formula in Signal Temporal Logic (STL), if the monitor only has access to a low-resolution version of the signal? We answer this question affirmatively by demonstrating that temporal logic has a multiresolution structure, which parallels the multiresolution structure of signals....
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Richard Pelphrey

  • Fine-Grained Object Recognition Under Limited Training Data

    Creator:
    Lam, Michael Q.
    Abstract:
    This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Michael Lam for the

  • Object detection in biological images using a search-based framework

    Creator:
    Lam, Michael
    Abstract:
    This thesis addresses a basic problem in computer vision, that of semantic labeling of images. Our work is aimed at object detection in biological images for evolutionary biology research. In particular, our goal is to detect nematocysts in Scanning Electron Microscope (SEM) images. This biological domain presents challenges for existing...
    Resource Type:
    Masters Thesis
    Full Text:
    Framework AN ABSTRACT OF THE THESIS OF Michael Lam for the degree of Master of Science in Computer

  • Understanding Software Development and Testing Practices

    Creator:
    Hilton, Michael
    Abstract:
    A bad software development process leads to wasted effort and inferior products. In order to improve a software process, it must be first understood. In this work I focus on understanding software processes. The first process we seek to understand is Continuous Integration (CI). CI systems automate the compilation, building,...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Michael Hilton for the

  • Part-based and Uncertainty-Aware Few-shot Object Segmentation in Images

    Creator:
    Nguyen, Khoi D.
    Abstract:
    This dissertation addresses few-shot object segmentation in images. The goal of segmentation is to label every image pixel with a class of the object occupying that pixel, where the class may represent a semantic object category or instance. In few-shot segmentation, training and test datasets have different classes. Every new...
    Resource Type:
    Dissertation
    Full Text:
    , Tieqiao Wang, Peng Lei, Dimitrios Trigkakis, Michael Lam, Anirban Roy, and Behrooz Mahasseni. I would

  • A domain-specific embedded language for probabilistic programming

    Creator:
    Kollmansberger, Steven
    Abstract:
    Functional programming is concerned with referential transparency, that is, given a certain function and its parameter, that the result will always be the same. However, it seems that this is violated in applications involving uncertainty, such as rolling a dice. This thesis defines the background of probabilistic programming and domain-specific...
    Resource Type:
    Masters Thesis
    Full Text:
    Committee, namely, Margaret Burnett, Michael Quinn and Tim Budd, for taking time out of their busy

  • Learning to Estimate Multi-Relation Aggregation Functions

    Creator:
    Jadhav, Rashmi Suresh
    Abstract:
    Multi-relation aggregation queries process the join operator before computing the aggregation function. This join is arguably the most costly operation since traditional join algorithms spend majority of their time trying to join the parts of the relations that do not generate any output tuples. This causes slow response times with...
    Resource Type:
    Masters Thesis
    Full Text:
    interesting. I would like to thank my collaborators Mian Xie and Michael Burton since I truly liked working

  • UCT for tactical assault battles in real-time strategy games

    Creator:
    Balla, Radha-Krishna
    Abstract:
    We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics...
    Resource Type:
    Masters Thesis
    Full Text:
    instantaneous effects, whereas actions in the RTS domain are simultaneous and durative. Michael Chung et al

  • Computational Elucidation of the Regulatory SNPs in the Non-Coding Regions of the Human Genome

    Creator:
    Yao, Yao
    Abstract:
    We describe a series of novel computational models, CERENKOV (Computational Elucidation of the REgulatory NonKOding Variome) and its successors CERENKOV2, CERENKOV3, and Convolutional CERENKOV3, for discriminating regulatory single nucleotide polymorphisms (rSNPs) from non-regulatory SNPs within non-coding genetic loci. The CERENKOV models are designed for recognizing rSNPs in the context of...
    Resource Type:
    Dissertation

  • Poisoning machine learning models to increase membership inference risks

    Creator:
    Le, Hoang
    Abstract:
    Deep learning is now being utilized widely in applications where sensitive data is being used for model training, for example, in health care. In this scenario, any data leakage will cause privacy concerns to whose data records are used to train the model. An attacker can actively cause privacy leakage...
    Resource Type:
    Masters Thesis
    Full Text:
    , Michael Moeller, and Tom Goldstein. Witches’ brew: Industrial scale data poisoning via gradient matching

  • Coupled Compressive Sensing : Sequential Reinforcement Approach

    Creator:
    De Silva, Shashini A.
    Abstract:
    We consider multiple Compressive Sensing (CS) problems wherein the supports of signal vectors of CS problems are restricted to satisfy a collection of joint logical constraints, which we refer to as coupling constraints. We consider a case where the coupling constraints are encoded in a graph and present a sequential...
    Resource Type:
    Masters Thesis
    Full Text:
    - bility of network topology given the set of available measurements. 27 Bibliography [1] Richard G

  • Information-theoretic Approach to Design and Evaluate Privacy-preserving and Fair Frameworks for Continuous High-dimensional Data

    Creator:
    Alsulaimawi, Zahir Ahmed Hussein
    Abstract:
    Deep learning is becoming the latest trend in sensitive applications, such as healthcare, criminal justice, and finance. As these new applications emerge, adversaries are circumventing them. Further, there have been concerns about the possibility of bias and discrimination in predictive applications. In order to address these issues, we propose an...
    Resource Type:
    Dissertation

  • A Distributed Scheme for Accelerating and Scaling PSPNet

    Creator:
    Krishna, Ajay
    Abstract:
    Advances in deep learning based image processing have led to their adoption for a wide range of applications, and in tow with these developments is a dramatic increase in the availability of high quality datasets. With this comes the need to accelerate and scale deep learning applications in order to...
    Resource Type:
    Masters Thesis
    Full Text:
    , Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia

  • Algorithms for massive biological datasets

    Creator:
    Bryant, Douglas W. (Douglas Wesley)
    Abstract:
    Within the past several years the technology of high-throughput sequencing has transformed the study of biology by offering unprecedented access to life's fundamental building block, DNA. With this transformation's potential a host of brand-new challenges have emerged, many of which lend themselves to being solved through computational methods. From de...
    Resource Type:
    Dissertation

  • Growth and characterization of zinc ferrite thin films for high frequency applications

    Creator:
    Hu, Jiqing
    Abstract:
    Ferrites have been used for various high frequency applications as bulk materials. These applications, however, are limited to large dimension devices. In this thesis, thin film ferrites were deposited from a low temperature solution-based deposition process that is suitable for micro-scale high frequency applications. The low temperature nature of this...
    Resource Type:
    Dissertation
    Full Text:
    assistance in SEM measurements; Dr. Michael Nesson from Oregon State University for his assistance in TEM

  • Individual Fairness Optimization in Machine Learning with Minimax Loss and an Abstain Option

    Creator:
    Behnoudfar, Ali
    Abstract:
    In this thesis, a new learning algorithm is introduced that is targeted towards individual fairness. In order to be individually fair, mispredictions need to be avoided as each such prediction means the learning algorithm was unfair towards some individual. Therefore, achieving individual fairness implies having a perfect classifier, which is...
    Resource Type:
    Masters Thesis
    Full Text:
    ] Rachel Bellamy, Kuntal Dey, Michael Hind, Samuel Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia

  • Pixel- and Frame-level Video Labeling using Spatial and Temporal Convolutional Networks

    Creator:
    Lei, Peng
    Abstract:
    This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
    Resource Type:
    Dissertation
    Full Text:
    University: Mohamed Amer, Sheng Chen, Liping Liu, Jun Li, Anirban Roy, Behrooz Mahasseni, Michael Lam

  • Parsing with Recurrent Neural Networks

    Creator:
    Cross, James Henry, III
    Abstract:
    Machine learning models for natural language processing have traditionally relied on large numbers of discrete features, built up from atomic categories such as word forms and part-of-speech labels, which are considered completely distinct from each other. Recently however, the advent of dense feature representations coupled with deep learning techniques has...
    Resource Type:
    Dissertation
    Full Text:
    Juneki Hong. I am also in eternal debt to my master’s degree advisers Irina Gladkova and Michael

  • High-Dimensional Reinforcement Learning with Human Feedback

    Creator:
    Curran, William
    Abstract:
    State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
    Resource Type:
    Dissertation

  • Structured Neural Models for Natural Language Processing

    Creator:
    Ma, Mingbo
    Abstract:
    Most tasks in natural language processing (NLP) involves structured information from both input (e.g., a sentence or a paragraph) and output (e.g., a tag sequence, a parse tree or a translated sentence). While neural models achieve great successes in other domains such as computer vision, applying those frameworks to NLP...
    Resource Type:
    Dissertation

  • Structured learning with latent variables : theory and algorithms

    Creator:
    Zhao, Kai
    Abstract:
    Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
    Resource Type:
    Dissertation

  • Causal Structure Learning from Experiments and Observations

    Creator:
    Sinha, Meghamala
    Abstract:
    In this research, we address the problem of learning a single causal network structure from multiple dataset generated from different experiments. The experiments can be observational or interventional. We assume that each dataset is generated by an unknown causal network altered under different experimental conditions (interventions, manipulation or perturbation). As...
    Resource Type:
    Masters Thesis

  • Efficient Spectrum Sensing and Sharing Techniques for Dynamic Wideband Spectrum Access

    Creator:
    Khalfi, Bassem
    Abstract:
    Besides enabling an enhanced mobile broadband access, fifth-generation (5G) wireless mobile networks are envisioned to support the connectivity of massive, heterogeneous Internet of Things (IoT) devices. Connecting these devices through 5G systems and providing them with their needed data rates require huge amounts of spectrum and power resources, thus calling...
    Resource Type:
    Dissertation

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
    Resource Type:
    Dissertation

  • Robust and Efficient Classification of Videos in the Wild

    Creator:
    Mahasseni, Behrooz
    Abstract:
    Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...
    Resource Type:
    Dissertation
    Full Text:
    , Anirban Roy, Michael Lam, Sheng Chen, Peng Lei, Christos Margiolas, Alberto Garcia, Suren Jayasuriya and

  • Enabling Virtual Globes for A Visual-Auditory User Experience of Spatial Data

    Creator:
    Gune, Aditya N.
    Abstract:
    Geographical datasets are large, complex, and can be difficult for users to navigate and derive meaning from. These datasets, as well as the unique insights derived from them, provide tremendous opportunity for social change -- many of the global challenges humankind is currently facing can benefit from analytics or visualization...
    Resource Type:
    Masters Thesis

  • Improving User Mental Models of XAI Systems with Inclusive Design Approaches

    Creator:
    Hamid, Md Montaser
    Abstract:
    Explainable Artificial Intelligence (XAI) systems aim to improve users’ understanding of AI but rarely consider the inclusivity aspects of XAI. Without inclusive approaches, improving explanations might not work well for everyone. This study investigates leveraging users’ diverse problem-solving styles as an inclusive strategy to fix an XAI prototype, with the...
    Resource Type:
    Masters Thesis

  • Simulator-Defined MDP Planning with Applications in Natural Resource Management

    Creator:
    Alkaee Taleghan, Majid
    Abstract:
    This work is inspired by problems in natural resource management centered on the challenge of invasive species. Computing optimal management policies for maintaining ecosystem sustainable is challenging. Many ecosystem management problems can be formulated as MDP (Markov Decision Process) planning problems. In a simulator-defined MDP, the Markovian dynamics and rewards...
    Resource Type:
    Dissertation

  • Action Segmentation with Limited Supervision

    Creator:
    Li, Jun
    Abstract:
    In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
    Resource Type:
    Dissertation

  • Classifying and Synthesizing 3D Shapes of Objects using Deep Neural Networks

    Creator:
    Xu, Xu
    Abstract:
    Reasoning about 3D shape of objects is important for successful computer visionapplications in robotics, 3D rendering and modeling. In this thesis, we address twoproblems { First, given an image, we generate 3D shape of the foreground object thatappears in the image. Second, we predict the class label of the input...
    Resource Type:
    Masters Thesis
    Full Text:
    ] Michael Lam, Janardhan Rao Doppa, Sinisa Todorovic, and Thomas G. Dietterich. HC-Search for structured

  • Learning greedy policies for the easy-first framework

    Creator:
    Xie, Jun
    Abstract:
    Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
    Resource Type:
    Masters Thesis

  • Exploitation and Mitigation of CPU Vulnerabilities

    Creator:
    Mestas, Phillip O., III
    Abstract:
    AMD SEV allows for the creation of fully encrypted virtual machines. This allows cloud computing tenants’ data to be secret to the cloud computing provider. However, it has been shown that the encryption scheme used by AMD can easily be broken. The attacker can create a copy of the virtual...
    Resource Type:
    Masters Thesis

  • A Structural Theorem For Shortest Vertex-Disjoint Paths Computation in Planar Graphs

    Creator:
    Zafarani, Farzad
    Abstract:
    Given k terminal pairs (s₁,t₁),(s₂,t₂),..., (s[subscript k],t[subscript k]) in an edge-weighted graph G, the k Shortest Vertex-Disjoint Paths problem is to find a collection P₁, P₂,..., P[subscript k] of vertex-disjoint paths with minimum total length, where P[subscript i] is an s[subscript i]-to-t[subscript i] path. As a special case of the...
    Resource Type:
    Masters Thesis
    Full Text:
    , 1982. [16] Richard Karp. On the computational complexity of combinatorial problems. Net- works, 5:45

  • A case for application-based linear transformers : applied towards text-to-spectrogram

    Creator:
    Agostinelli, Victor
    Abstract:
    Various natural language processing (NLP) tasks necessitate deep models that are fast, efficient, and small based on their ultimate application at the edge or elsewhere. While significant investigation has furthered the efficiency and reduced the size of these models, reducing their downstream latency without significant trade-offs remains a difficult task....
    Resource Type:
    Masters Thesis

  • Large-Area Nanoplasmonic Structures for Enhanced Fluorescence-Based Biosensing

    Creator:
    Wang, Yi-Chieh
    Abstract:
    An innovative silver nano-dimple arrays (Ag DAs)-integrated microfluidic device was developed to achieve highly sensitive fluorescence-based nucleic acid detection. The Ag DAs were utilized to produce surface plasmon resonance (SPR) for strong fluorescence enhancement. We systematically investigated the plasmon-enhanced fluorescence by controlling the nanostructure dimension of the Ag DA substrate....
    Resource Type:
    Masters Thesis

  • On the limits of mutation analysis

    Creator:
    Gopinath, Rahul
    Abstract:
    Mutation analysis is the gold standard for evaluating test-suite adequacy. It involves exhaustive seeding of all small faults in a program and evaluating the effectiveness of test suites in detecting these faults. Mutation analysis subsumes numerous structural coverage criteria, approximates fault detection capability of test suites, and the faults produced...
    Resource Type:
    Dissertation

  • Uncertainty in Deep Learning with Implicit Neural Networks

    Creator:
    Ratzlaff, Neale
    Abstract:
    The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
    Resource Type:
    Dissertation
    Full Text:
    , Christopher Buss, Lawrence Neal, Matthew Olson, Michael Slater, Robert DeBortoli, Risheek Garrepalli, Saeed

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation

  • Quantum dot plasmon coupling : Fundamental study and applications

    Creator:
    Kannegulla, Akash
    Abstract:
    The dissertation focuses on the engineering of light-matter interaction using plasmonic nanoparticles and metamaterials to achieve enhanced luminescence and based on which to improve the performance of biosensing and light-emitting technologies. We designed and fabricated a spectrum of nanostructures to exhibit particular dispersion relations capable of controlling the spontaneous emission...
    Resource Type:
    Dissertation

  • Investigating the Effect of Using Mobile Touchscreen Device on Children's Tactile Skills

    Creator:
    Almurshed, Rana
    Abstract:
    To users, mobile touchscreen devices have appealing characteristics; among these characteristics is intuitiveness, which leads to mobile devices being used almost everywhere by almost everyone to accomplish almost anything. This statement, to some degree, holds for children too. Despite touchscreen devices’ intuitiveness and popularity, we don’t know much about how...
    Resource Type:
    Dissertation
    Full Text:
    specifically, around 30% allow children to use such devices daily. According to the Michael Cohen Group

  • Improving automated email tagging with implicit feedback

    Creator:
    Sorower, Mohammad Shahed
    Abstract:
    Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
    Resource Type:
    Dissertation
    Full Text:
    thanks to Michael Slater, who is not only the primary devel- oper of the software (TAPE) used in this

  • Efficient Comparative Sequence Analysis Algorithms for RNA Conserved Structure and Region Detection

    Creator:
    Li, Sizhen
    Abstract:
    RNAs play important roles in multiple cellular processes, and many of their functions rely on folding to specific structures. To maintain their functions, secondary structures of RNA homologs are conserved across evolution. These conserved structures provide critical targets for diagnostics and therapeutics. Thus, there is a need for developing fast...
    Resource Type:
    Dissertation

  • Redesigning the Structure and Access Paths of Databases for Effective and Efficient Query Processing

    Creator:
    Ghadakchi, Vahid
    Abstract:
    Many database users are not familiar with formal query languages, the concept of schema, or the exact content of their database. Thus, it is challenging for these users to formulate their information needs over semi-structured and structured databases. To address this problem, researchers have proposed usable query interfaces over which...
    Resource Type:
    Dissertation

  • Efficient Incremental Panorama Reconstruction from Multiple Videos

    Creator:
    Feng, Zhongyuan
    Abstract:
    Constructing a panorama from a set of videos is a long-standing problem in computer vision. A panorama represents an enhanced still-image representation of an entire scene captured in a set of videos, where each video shows only a part of the scene. Importantly, a panorama shows only the scene background,...
    Resource Type:
    Capstone Project

  • Visual object discovery and understanding

    Creator:
    Yuan, Jialin
    Abstract:
    Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
    Resource Type:
    Dissertation
    Full Text:
    . Strauss, Prof. Yuan Jiang, Prof. Yanming Di, Prof. Daniel Curry, Prof. Tucker Hermans, Dr. Michael Nagle

  • Deep Learning for Human and Biological Languages

    Creator:
    Hong, Junki
    Abstract:
    We explore the application of deep learning to the disparate fields of natural language processing and computational biology. Both the sentences uttered by humans as well as the RNA and protein sequences found within the cells of their bodies can be considered formal languages in computer science, as sets of...
    Resource Type:
    Dissertation

  • Computational Approaches for RNA Structure Prediction with Dynamic Programming and Deep Neural Networks

    Creator:
    Deng, Dezhong
    Abstract:
    Our goal is to build a system to model the RNA sequences that reveals their structural information by using efficient dynamic programming algorithms and deep learning approaches. We aim to 1) achieve linear-time for RNA secondary structure prediction based on existing minimum free energy models; 2) utilize deep neural networks...
    Resource Type:
    Dissertation

  • Efficient training and feature induction in sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction. In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
    Resource Type:
    Dissertation

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation

  • SocioEconomicMag Meets a Platform for SES-Diverse College Students: A Case Study

    Creator:
    Agarwal, Puja
    Abstract:
    Emerging research shows that individual differences in how people use technology sometimes cluster by socioeconomic status (SES) and that when technology is not socioeconomically inclusive, low-SES individuals may abandon it. To understand how to improve technology’s SES-inclusivity, we present a multi-phase case study on SocioEconomicMag (SESMag), an emerging inspection method...
    Resource Type:
    Masters Thesis

  • Identifying Design Discussion Topics in Open Source Software

    Creator:
    Chatterjee, Amreeta
    Abstract:
    When contributing to a software system, developers need to understand the rationale for previous design decisions so that they can adhere to the system’s design. Not doing so can lead to erosion of the overall design quality of the system. However, discussions embedded in a large volume of communication on...
    Resource Type:
    Masters Thesis

  • Deep Convolutional Network on Point Clouds for 3D Scene Understanding

    Creator:
    Wu, Wenxuan
    Abstract:
    As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
    Resource Type:
    Dissertation
    Full Text:
    , Ali, Amin, Hung, Jay, Jialin, Xianfang, Mazen, Michael, Tim, Vijay, Saeed, Xinyao, Zehuan, and Ziwen

  • Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

    Creator:
    Firl, Alrik K.
    Abstract:
    This thesis consists of two major components. The first part is concerned with video object instance segmentation (VOS), which is the task of assigning per-pixel labels perframe of a video sequence to indicate foreground object instance membership, given the first frame ground truth mask. VOS has myriad applications, from video...
    Resource Type:
    Masters Thesis

  • The InclusiveMag Method: A Start Towards More Inclusive Software for Diverse Populations

    Creator:
    Mendez, Christopher
    Abstract:
    How can software practitioners assess whether their software supports diverse users? Although there are empirical processes that can be used to find “inclusivity bugs” piecemeal, what is often needed is a systematic inspection method to assess software’s support for diverse populations. To help fill this gap, this thesis introduces InclusiveMag,...
    Resource Type:
    Masters Thesis

  • How does AAR/AI Support Problem Solvers with Diverse Behaviors and Cognitive Styles?

    Creator:
    Dikkala, Rupika
    Abstract:
    "What’s wrong with this AI?" Explainable AI (XAI) researchers are moving beyond explaining an AI’s actions, to helping users detect an AI’s failures. However this detection may not be enough—for actionability, we often need to pinpoint which part failed. We investigate how AAR/AI, a structured assessment process, supports users with...
    Resource Type:
    Masters Thesis

  • Machine Learning for Precision Medicine: Application to Cancer Chemotherapy Response Prediction and Wound Healing Status Assessment

    Creator:
    Wei, Qi
    Abstract:
    Ph.D. candidate Qi Wei's thesis consists of two projects: Chemotherapy Project: a study based on the research paper "Predicting chemotherapy response of various cancer types using a variational auto-encoder approach" submitted to the bioRxiv preprint archive and accepted by the BMC bioinformatics; and Wound Monitor Project: implementing and assessing analytics...
    Resource Type:
    Dissertation

  • Toward computer vision for understanding American football in video

    Creator:
    Hess, Robin W.
    Abstract:
    In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
    Resource Type:
    Dissertation

  • Exploratory Study to Uncover Student Mental Models of Singly Linked Lists in the C Programming Language

    Creator:
    Almadhoun, Eman
    Abstract:
    In computer science, learning abstract fundamental programming concepts requiring students to understand memory management can be very difficult and lead to misunderstandings that carry on into advanced topics. This is especially true in data structures with abstract data types. Understanding how novice students think and reason about data structures is...
    Resource Type:
    Dissertation

  • Dimensionality Reduction Techniques for Compositional Data : An Empirical Study

    Creator:
    George, Rogen
    Abstract:
    Compositional data is a type of data where the features are non-negative and always sum to a constant. This type of data is frequently encountered in many fields such as microbiology, geology, economics and natural language processing. Compositional data has unique statistical properties that makes it difficult to apply standard...
    Resource Type:
    Masters Thesis

  • Network Coding, Random Matrices, and Their Applications to Communication Systems

    Creator:
    Nguyen-Huu, Duong
    Abstract:
    In this work, we study network coding technique, its relation to random matrices, and their applications to communication systems. The dissertation consists of three main contributions. First, we propose efficient algorithms for data synchronization via a broadcast channel using random network coding. Second, we study the resiliency of network coding...
    Resource Type:
    Dissertation

  • Incorporating labeled features into image classification using generalized expectation

    Creator:
    Moore, Travis
    Abstract:
    Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
    Resource Type:
    Masters Thesis

  • A channelized digital receiver design for UWB sytems in a multipath indoor environment

    Creator:
    Chang, Yuhao
    Abstract:
    This thesis presents a channelized digital receiver design for UWB sytems in a multipath indoor environment. The UWB technology has been used for commercial and military purposes due to a number of advantages such as low-power consumption, noise-like and carrier free. The energy of UWB signal is spread over a...
    Resource Type:
    Masters Thesis

  • Relational Learning over Dirty Data Using Data Constraints

    Creator:
    Lee, Ga Young
    Abstract:
    Real-world datasets are dirty and contain many errors. Examples of these issues are violations of integrity constraints, duplicates, and inconsistencies in representing data values and entities. Applying machine learning on dirty databases may lead to inaccurate results. Users have to spend a lot of time and effort repairing data errors...
    Resource Type:
    Masters Thesis

  • Domain-Independent Planning for Markov Decision Processes with Factored State and Action Spaces

    Creator:
    Raghavan, Aswin
    Abstract:
    Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
    Resource Type:
    Dissertation

  • Generative Models Meet Explainable AI and Long-Tail Learning: from Attribution Maps to Image Synthesis

    Creator:
    Khorram, Saeed
    Abstract:
    The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
    Resource Type:
    Dissertation

  • Two Sides of a Coin: Adversarial-Based Image Privacy and Defending Against Adversarial Perturbations for Robust CNNs

    Creator:
    Rajabi, Arezoo
    Abstract:
    Emergence of highly accurate Convolutional Neural Networks (CNNs) with the capability to process large datasets, has led to their popularity in many applications, including safety/security-sensitive (e.g. disease recognition, self-driving cars). Despite the high accuracy of convolutional neural networks, they have been found to be susceptible to adversarial noise added to...
    Resource Type:
    Dissertation

  • Incorporating and Learning Behavior Constraints for Sequential Decision Making

    Creator:
    Pinto, Jervis
    Abstract:
    Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
    Resource Type:
    Dissertation

  • Deep Segmentation in Plant Phenomics

    Creator:
    Kaur, Damanpreet
    Abstract:
    The abilities of plant biologists to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation and mainly to collect this data on a high-throughput scale at low cost. Deep learning-based methods have demonstrated unprecedented potential to automate...
    Resource Type:
    Masters Thesis

  • A Novel CCRW Receiver with Variable Width Window for Mitigating Multipath and Ambiguity in GNSS Positioning

    Creator:
    Alhussein, Fahad
    Abstract:
    This work presents a novel CCRW receiver that utilizes a window of variable width, for e˙ectively mitigating multipath and ambiguity in both civil and military positioning applica-tions using Global Navigation Satellite Systems (GNSS). This CCRW receiver incorporates a single stroboscopic window, whose width is iteratively reduced until the e˙ect of...
    Resource Type:
    Dissertation

  • An analysis of training methodologies for deep visual trackers

    Creator:
    Fiez, Trevor
    Abstract:
    This thesis considers the problem of training convolutional neural networks for online visual tracking. A major challenge for single object visual tracking is that most training sets with frame-level track annotations are quite small, due to the prohibitive cost of manual annotation. Current training approaches either supplement the annotations with...
    Resource Type:
    Masters Thesis

  • Multi-criteria average reward reinforcement learning

    Creator:
    Natarajan, Sriraam
    Abstract:
    Reinforcement learning (RL) is the study of systems that learn from interaction with their environment. The current framework of Reinforcement Learning is based on receiving scalar rewards, which the agent aims to maximize. But in many real world situations, tradeoffs must be made among multiple objectives. This necessitates the use...
    Resource Type:
    Masters Thesis

  • Facilitating Code Comprehension by Annotations in Canvas-Based IDE

    Creator:
    Adeli, Marjan
    Abstract:
    Developers spend a considerable amount of time comprehending code and building accurate mental models of the code. Understanding the relationships between software features within IDEs is difficult, with information split across different visual hierarchies making navigation cumbersome. Canvas-based IDEs mitigate some of the navigation costs by allowing relevant information to...
    Resource Type:
    Masters Thesis

  • Learning Based Anomaly Detection for Industrial Arm Applications

    Creator:
    Narayanan, Vedanth
    Abstract:
    Smart Manufacturing (SM) is envisioned to make manufacturing processes more efficient through automation and integration of networked information systems. Robotic arms are integral to this vision. However the benefits of SM, enabled by automation and networking, also come with cyber risks. In this work, we propose an anomaly detection framework...
    Resource Type:
    Capstone Project

  • Identifiability-Aware Joint Sparse Error Correction For Robust State Estimation

    Creator:
    Kibria, Sharmin
    Abstract:
    We study joint nonlinear state estimation with multi-period measurement vectors that are potentially corrupted by sparse gross errors. The identifiability-aware approach is proposed to leverage common characteristics of fundamentally identifiable gross errors to enhance error correction performance. First, we derive a necessary rank condition that the sparsity pattern of any...
    Resource Type:
    Dissertation

  • Formative Work Toward a Mixed-Initiative Programming Language

    Creator:
    Abbott, Keeley
    Abstract:
    Mixed-initiative programming entails collaboration between a computer system, and a human to achieve some desired goal or set of goals. Often these goals change or are amended in real time during the course of program execution. As such, the plans these programs are based on must adapt and evolve to...
    Resource Type:
    Masters Thesis

  • Theory and Implementation of a Variational Database Management System

    Creator:
    Ataei, Parisa S.
    Abstract:
    In this thesis, I present the variational database management system, a formal framework and its implementation for representing variation in relational databases and managing variational information needs. A variational database is intended to support any kind of variation in a database. Specific kinds of variation in databases have already been...
    Resource Type:
    Dissertation

  • Efficient Private Matching for Private Databases

    Creator:
    Trieu, Thi Ni Ni
    Abstract:
    Private matching (PM) is a key cryptographic primitive in secure computation that allows several parties to jointly compute some functions depending on their private inputs. Indeed, this primitive has many practical applications. For instance, in online advertising, two companies may wish to find their common customers for a joint marketing...
    Resource Type:
    Dissertation

  • Sensor Interface Circuit Design towards CMOS Scaling

    Creator:
    Liu, Jialin
    Abstract:
    Sensor system plays an important role in connecting everything including human body to the electrical information systems that we have built and that we are going to build, to make the world more intelligent and efficient. One of the key propulsive forces behind these emerging techniques is CMOS scaling that...
    Resource Type:
    Dissertation

  • Formal Verification of the Variational Database Management System

    Creator:
    Khan, Fariba
    Abstract:
    Variation in data is abundant and ubiquitous in real-world applications. Managing variation in databases is, however, difficult and has been extensively studied by the database community. Schema evolution, data integration, and database versioning are examples of well-studied forms of database variation with effective context-specific solutions. However, variation appears in different...
    Resource Type:
    Masters Thesis

  • Learning with Limited Labeled Data in Natural Language Processing

    Creator:
    Obeidat, Rasha
    Abstract:
    The advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks, achieving state-of-art performances without any hand-crafted features. However, training deep models requires a massive amount of labeled data. Labeling new data as a new task or domain emerges consumes time and efforts...
    Resource Type:
    Dissertation

  • Building Self Adaptive Software Systems via Test-based Modifications

    Creator:
    Christi, Arpit M.
    Abstract:
    Building software systems that adapt to the changing environment is challenging. Developers cannot anticipate all the changes in advance, and even if they could, the effort required to handle such situations is too onerous for practical purposes. Self Adaptive Software (SAS) adapts itself as per changing environment. The area of...
    Resource Type:
    Dissertation

  • Optimal load and resource balance in internet distributed systems

    Creator:
    Nishida, Hiroshi
    Abstract:
    A distributed system is a network of multiple autonomous computational nodes designed primarily for performance scalability and robustness. The performance of a distributed system depends critically on how tasks and resources are distributed among the nodes. Thus, a main thrust in distributed system research is to design schemes for distributing...
    Resource Type:
    Dissertation

  • Investigating the Effects of Design Quality in OSS Projects

    Creator:
    Mannan, Umme Ayda
    Abstract:
    Software systems are becoming an essential part of the lives of both individuals and organizations, and as a consequence, these systems are getting bigger and more complex. Because of this, the tasks of maintaining the quality in these complex software systems are becoming increasingly difficult. Furthermore, these systems are subject...
    Resource Type:
    Dissertation

  • Elucidating Computational Narratives to Facilitate Code Comprehension

    Creator:
    Chattopadhyay, Souti
    Abstract:
    Programming is integrated across the workflow of multiple domains where end-user programmers, those who need to program as a means to an end, regularly need to code. In the modern setting of collaborative development, end-user programmers have to interpret the intentions behind existing code to contribute and build solutions to...
    Resource Type:
    Dissertation

  • Advances in Simultaneous Translation

    Creator:
    Zheng, Renjie
    Abstract:
    Simultaneous translation, which translates concurrently with the source language speech, is widely used in many scenarios including multilateral organizations. However, it is well known to be one of the most challenging tasks for humans due to the simultaneous perception and production in two languages. On the other hand, simultaneous translation...
    Resource Type:
    Dissertation

  • Leveraging Generated Tests

    Creator:
    Alipour, Mohammad Amin
    Abstract:
    The main goal of automated test generation is to improve the reliability of a program by exposing faults to developers. To this end, testing should cover the largest possible portion of the program given a test budget (i.e., time and resources) as frequently as possible. Coverage of a program entity...
    Resource Type:
    Dissertation
    Full Text:
    Brindescu, Chris Chambers, Souti Chattopadhyay, Mihai Codoban, Rahul Gopinath, Michael Hilton, Rafael Leano

  • Machine Learning Techniques to Model Species Interactions and Distributions Under Imperfect Detection

    Creator:
    Seo, Eugene
    Abstract:
    Ecological domains seeking to understand the environment and the behavior of species have received little attention in machine learning (ML), despite the fact that environmental changes have a significant impact on humans as well as ecosystems. Some ecological problems can be formulated similarly to other common ML applications, but there...
    Resource Type:
    Dissertation

  • Action Segmentation in Videos: Deep Models, Prediction Diffusion, and Deep-Temporal Augmentations

    Creator:
    Aziere, Nicolas
    Abstract:
    This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
    Resource Type:
    Dissertation

  • Weak-supervision Time-series Analysis

    Creator:
    You, Zeyu
    Abstract:
    Efficient time-series analysis can impact multiple application domains such as motif discovery in gene analysis or music data, extracting spectro-temporal patterns in acoustic scene analysis, or annotating and classifying electrical bio-signals (such as ECG, EEG, and EMG) for medical applications. Time-series analysis involves a variety of tasks. To predict future...
    Resource Type:
    Dissertation

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation

  • Machine learning methods for public policy : simulation, optimization, and visualization

    Creator:
    McGregor, Sean
    Abstract:
    Society faces many complex management problems, particularly in the area of shared public resources such as ecosystems. Existing decision making processes are often guided by personal experience and political ideology rather than state-of-the-art scientific understanding. This dissertation envisions a future in which multiple stakeholders are provided with computational tools for...
    Resource Type:
    Dissertation

  • Meeting End-to-End Deadlines in Real-Time Networks Using Software Defined Networking (SDN)

    Creator:
    Almahdi, Rafid M.
    Abstract:
    Network flows in Real-Time (RT) systems need to meet stringent end-to-end deadlines in order for such systems to operate safely and reliably. Today, such systems use custom or domain specific network system designs to meet end-to-end deadlines and other constraints of real-time flows. In this work we explore the design...
    Resource Type:
    Dissertation

  • The Analysis of First Year Computer Science Design Documents

    Creator:
    Ernst, Shannon S.
    Abstract:
    Computer science is, at its core, about solving problems. The "Carry out the Plan" portion of problem solving is often examined and emphasized in CS 1 and CS 2, forgetting to emphasize the other important aspects of the problem solving process. This study focuses on the other problem-solving steps, which...
    Resource Type:
    Masters Thesis

  • Executable semantics for PLEXIL : simulating a task-scheduling language in Haskell

    Creator:
    Strauss, Paul J.
    Abstract:
    An interdisciplinary study into the theory of design decisions has yielded a model for tracking design changes in hardware/software systems, but it still needs to be applied to a larger system to test its efficiency at tracking important data. This thesis creates an implementation of PLEXIL, a language in development...
    Resource Type:
    Masters Thesis

  • Interactive visualization of diversity in multivariate data sets unified across fields of study

    Creator:
    Pham, Tuan N. T.
    Abstract:
    The study of the diversity of multivariate objects shares common characteristics across disciplines, including ecology and organizational management. Nevertheless, experts in these two disciplines have adopted somewhat separate diversity concepts and analysis techniques, limiting the ability of potentially sharing and cross comparing these concerns. Moreover, while complex diversity data may...
    Resource Type:
    Dissertation

  • Interpretable Machine Learning: Applications in Biology and Genomics

    Creator:
    Danaee, Padideh
    Abstract:
    Machine learning (ML) and deep learning (DL) models impact our daily lives with applications in natural language modeling, image analysis, healthcare, genomics, and bioinformatics. The exponential growth of biological sequence data necessitates accompanying advances in computational methods. Although deep learning is highly effective for detecting and classifying biological sequences, challenges...
    Resource Type:
    Dissertation