Recent Submissions

  • Revealing and analyzing the shared structure of deep face embeddings 

    Author(s):McNeely-White, David G.
    Date Issued:2022
    Format:born digital; doctoral dissertations
    Deep convolutional neural networks trained for face recognition are found to output face embeddings which share a fundamental structure. More specifically, one face verification model's embeddings (i.e. last--layer ...
  • Generalizations of comparability graphs 

    Author(s):Xu, Zhisheng
    Date Issued:2022
    Format:born digital; doctoral dissertations
    In rational decision-making models, transitivity of preferences is an important principle. In a transitive preference, one who prefers x to y and y to z must prefer x to z. Many preference relations, including total order, ...
  • Eye've seen this before: building a gaze data analysis tool for déjà vu detection 

    Author(s):Seabolt, Logan K.
    Date Issued:2022
    Format:born digital; masters theses
    In order to expand the understanding of the phenomenon known as déjà vu, an investigation into the use of eyetracking was needed. Through the use of an advanced eyetracking device, open-source software, and previous research ...
  • Automatically detecting task unrelated thoughts during conversations using keystroke analysis 

    Author(s):Kuvar, Vishal Kiran
    Date Issued:2022
    Format:born digital; masters theses
    Task-unrelated thought (TUT), commonly known as the phenomenon of daydreaming or zoning- out, is a mental state where a person's attention moves away from the task-at-hand to self-generated thoughts. This state is extremely ...
  • COVID-19 misinformation on Twitter: the role of deceptive support 

    Author(s):Hashemi Chaleshtori, Fateme
    Date Issued:2022
    Format:born digital; masters theses
    Social media platforms like Twitter are a major dissemination point for information and the COVID-19 pandemic is no exception. But not all of the information comes from reliable sources, which raises doubts about their ...
  • Redundant complexity in deep learning: an efficacy analysis of NeXtVLAD in NLP 

    Author(s):Mahdipour Saravani, Sina
    Date Issued:2022
    Format:born digital; masters theses
    While deep learning is prevalent and successful, partly due to its extensive expressive power with less human intervention, it may inherently promote a naive and negatively simplistic employment, giving rise to problems ...
  • Anteater analysis, The: a comparison of traveling salesman tour construction methods and their global frequencies 

    Author(s):Ourada, Shannon A.
    Date Issued:2022
    Format:born digital; masters theses
    For the Traveling Salesman Problem (TSP), many algorithms have been developed. These include heuristic solvers, such as nearest neighbors and ant colony optimization algorithms. In this work, the ATT48 and EIL101 instances ...
  • Framework for resource efficient profiling of spatial model performance, A 

    Author(s):Carlson, Caleb
    Date Issued:2022
    Format:born digital; masters theses
    We design models to understand phenomena, make predictions, and/or inform decision-making. This study targets models that encapsulate spatially evolving phenomena. Given a model M, our objective is to identify how well the ...
  • GAN you train your network 

    Author(s):Pamulapati, Venkata Sai Sudeep
    Date Issued:2022
    Format:born digital; masters theses
    Zero-shot classifiers identify unseen classes — classes not seen during training. Specifically, zero-shot models classify attribute information associated with classes (e.g., a zebra has stripes but a lion does not). Lately, ...
  • EgoRoom: egocentric 3D pose estimation through multi-coordinates heatmaps 

    Author(s):Jung, Changsoo
    Date Issued:2022
    Format:born digital; masters theses
    Recent head-mounted virtual reality (VR) devices include fisheye lenses oriented to users' bodies, which enable full body pose estimation from video. However, traditional joint detection methods fail under this use case ...
  • Learned perception systems for self-driving vehicles 

    Author(s):Chaabane, Mohamed
    Date Issued:2022
    Format:born digital; doctoral dissertations
    Building self-driving vehicles is one of the most impactful technological challenges of modern artificial intelligence. Self-driving vehicles are widely anticipated to revolutionize the way people and freight move. In this ...
  • Something is fishy! - How ambiguous language affects generalization of video action recognition networks 

    Author(s):Patil, Dhruva Kishor
    Date Issued:2022
    Format:born digital; doctoral dissertations
    Modern neural networks designed for video action recognition are able to classify video snippets with high degrees of confidence and accuracy. The success of these models lies in the complex feature representations they ...
  • Machine learning for computer aided programming: from stochastic program repair to verifiable program equivalence 

    Author(s):Kommrusch, Steve
    Date Issued:2022
    Format:born digital; doctoral dissertations
    Computer programming has benefited from a virtuous cycle of innovation as improvements in computer hardware and software make higher levels of program abstraction and complexity possible. Recent advances in the field of ...
  • Mixing genetic algorithm for traveling salesman problem, The 

    Author(s):Varadarajan, Swetha
    Date Issued:2022
    Format:born digital; doctoral dissertations
    The Traveling Salesman Problem (TSP) is one of the most intensively studied NP-Hard problems. The TSP solvers are well-suited for multi-core CPU-based architectures. With the decline in Moore's law, there is an increasing ...
  • Perception systems for robust autonomous navigation in natural environments 

    Author(s):Trabelsi, Ameni
    Date Issued:2022
    Format:born digital; doctoral dissertations
    As assistive robotics continues to develop thanks to the rapid advances of artificial intelligence, smart sensors, Internet of Things, and robotics, the industry began introducing robots to perform various functions that ...
  • Understanding user interactions in stereoscopic head-mounted displays 

    Author(s):Williams, Adam S.
    Date Issued:2022
    Format:born digital; doctoral dissertations
    Interacting in stereoscopic head mounted displays can be difficult. There are not yet clear standards for how interactions in these environments should be performed. In virtual reality there are a number of well designed ...
  • Applications of topological data analysis to natural language processing and computer vision 

    Author(s):Garcia, Jason S.
    Date Issued:2022
    Format:born digital; masters theses
    Topological Data Analysis (TDA) uses ideas from topology to study the "shape" of data. It provides a set of tools to extract features, such as holes, voids, and connected components, from complex high-dimensional data. ...
  • Compiler for hierarchical task-based programming on distributed-memory, A 

    Author(s):Dubois, Alexandre
    Date Issued:2022
    Format:born digital; masters theses
    Today, computation intensive applications are run on heterogeneous clusters of machines and use the Message Passing Interface (MPI), which provides a library interface for message-passing between non-shared memory computational ...
  • Embedding based clustering of time series data using dynamic time warping 

    Author(s):Mendis, R. A. C. Laksheen
    Date Issued:2022
    Format:born digital; masters theses
    Voluminous time-series observational data impose challenges pertaining to storage and analytics. Identifying patterns in such climate time-series data is critical for many geospatial applications. Over the recent years, ...
  • Classification of P300 from non-invasive EEG signal using convolutional neural network 

    Author(s):Farhat, Nazia
    Date Issued:2022
    Format:born digital; masters theses
    Brain-Computer Interface system is a communication tool for the patients of neuromuscular diseases. The efficiency of such a system largely depends on the accurate and reliable detection of the brain signal employed in its ...

View more