Physical Sciences and Mathematics Commons^™

Extracting Social Network Model Parameters From Social Science Literature, Isaac Batts

Theses and Dissertations--Computer Science

When looking at computer modeling of social situations, much of the social science literature does not include ready-to-use statistics or parameters to be included in a social model. I explore studies related to speaking about racism (and other forms of bias), and interventions designed to diminish the occurrence of biased behavior, and use those readings to synthesize plausible parameters for a social computer model.

Nonuniform Sampling-Based Breast Cancer Classification, Santiago Posso

Theses and Dissertations--Electrical and Computer Engineering

The emergence of deep learning models and their success in visual object recognition have fueled the medical imaging community's interest in integrating these algorithms to improve medical diagnosis. However, natural images, which have been the main focus of deep learning models and mammograms, exhibit fundamental differences. First, breast tissue abnormalities are often smaller than salient objects in natural images. Second, breast images have significantly higher resolutions but are generally heavily downsampled to fit these images to deep learning models. Models that handle high-resolution mammograms require many exams and complex architectures. Additionally, spatially resizing mammograms leads to losing discriminative details essential …

Flexible Attenuation Fields: Tomographic Reconstruction From Heterogeneous Datasets, Clifford S. Parker

Theses and Dissertations--Computer Science

Traditional reconstruction methods for X-ray computed tomography (CT) are highly constrained in the variety of input datasets they admit. Many of the imaging settings -- the incident energy, field-of-view, effective resolution -- remain fixed across projection images, and the only real variance is in the detector's position and orientation with respect to the scene. In contrast, methods for 3D reconstruction of natural scenes are extremely flexible to the geometric and photometric properties of the input datasets, readily accepting and benefiting from images captured under varying lighting conditions, with different cameras, and at disparate points in time and space. Extending CT …

On Generative Models And Joint Architectures For Document-Level Relation Extraction, Aviv Brokman

Theses and Dissertations--Statistics

Biomedical text is being generated at a high rate in scientific literature publications and electronic health records. Within these documents lies a wealth of potentially useful information in biomedicine. Relation extraction (RE), the process of automating the identification of structured relationships between entities within text, represents a highly sought-after goal in biomedical informatics, offering the potential to unlock deeper insights and connections from this vast corpus of data. In this dissertation, we tackle this problem with a variety of approaches.

We review the recent history of the field of document-level RE. Several themes emerge. First, graph neural networks dominate the …

Language Models For Rare Disease Information Extraction: Empirical Insights And Model Comparisons, Shashank Gupta

Theses and Dissertations--Computer Science

End-to-end relation extraction (E2ERE) is a crucial task in natural language processing (NLP) that involves identifying and classifying semantic relationships between entities in text. This thesis compares three paradigms for end-to-end relation extraction (E2ERE) in biomedicine, focusing on rare diseases with discontinuous and nested entities. We evaluate Named Entity Recognition (NER) to Relation Extraction (RE) pipelines, sequence-to-sequence models, and generative pre-trained transformer (GPT) models using the RareDis information extraction dataset. Our findings indicate that pipeline models are the most effective, followed closely by sequence-to-sequence models. GPT models, despite having eight times as many parameters, perform worse than sequence-to-sequence models and …

Cross-Layer Design Of Highly Scalable And Energy-Efficient Ai Accelerator Systems Using Photonic Integrated Circuits, Sairam Sri Vatsavai

Theses and Dissertations--Electrical and Computer Engineering

Artificial Intelligence (AI) has experienced remarkable success in recent years, solving complex computational problems across various domains, including computer vision, natural language processing, and pattern recognition. Much of this success can be attributed to the advancements in deep learning algorithms and models, particularly Artificial Neural Networks (ANNs). In recent times, deep ANNs have achieved unprecedented levels of accuracy, surpassing human capabilities in some cases. However, these deep ANN models come at a significant computational cost, with billions to trillions of parameters. Recent trends indicate that the number of parameters per ANN model will continue to grow exponentially in the foreseeable …

Autonomous Shuttle Car Docking To A Continuous Miner Using Rgb-Depth Imagery, Sky Rose

Theses and Dissertations--Mining Engineering

A great deal of research is currently being conducted in automating mining equipment to improve worker health and safety and increase mine productivity. Significant progress has been made in some applications, e.g., autonomous haul trucks for surface mining. However, little progress has been made in autonomous face haulage in underground room-and pillar coal mines. Accordingly, this thesis addresses automating the operation of a shuttle car, focusing on positioning the shuttle car under the continuous miner coal-discharge conveyor during cutting and loading operations. The approach uses a stereo depth camera as the sensor, and machine-learning algorithms are used to identify various …

Enabling Dapps Data Exchange With Hardware-Assisted Secure Oracle Network, Yue Li

Theses and Dissertations--Computer Science

Decentralized applications (dApps), enabled by the blockchain and smart contract technology, are known for allowing distrustful parties to execute business logic without relying on a central authority. Compared to regular applications, dApps offer a wide range of benefits, including security by design, trustless transactions, and resistance to censorship. However, dApps need to access real-world data to achieve their full potential, relying on the data oracles. Oracles act as bridges between blockchains and the outside world, providing essential data to the smart contracts that power dApps. A significant challenge in integrating oracles into the dApp ecosystem is the Oracle Problem …

Multi-Domain Adaptation For Image Classification, Depth Estimation, And Semantic Segmentation, Yu Zhang

Theses and Dissertations--Computer Science

The appearance of scenes may change for many reasons, including the viewpoint, the time of day, the weather, and the seasons. Traditionally, deep neural networks are trained and evaluated using images from the same scene and domain to avoid the domain gap. Recent advances in domain adaptation have led to a new type of method that bridges such domain gaps and learns from multiple domains.

This dissertation proposes methods for multi-domain adaptation for various computer vision tasks, including image classification, depth estimation, and semantic segmentation. The first work focuses on semi-supervised domain adaptation. I address this semi-supervised setting and propose …

Deep Learning Models For Ct Image Standardization, Md Selim

Theses and Dissertations--Computer Science

Multicentric CT imaging studies often encounter images acquired with scanners from different vendors or using different reconstruction algorithms. This leads to inconsistencies in noise level, sharpness, and edge enhancement, resulting in a lack of homogeneity in radiomic characteristics. These inconsistencies create significant variations in radiomic features and ambiguity in data sharing across different institutions. Therefore, normalizing CT images acquired using non-standardized protocols is vital for decision-making in cross-center large-scale data sharing and radiomics studies. To address this issue, we present four end-to-end deep-learning-based models for CT image standardization and normalization. The first two models require paired training data and can …

Improving Connectivity For Remote Cancer Patient Symptom Monitoring And Reporting In Rural Medically Underserved Regions, Esther Max-Onakpoya

Theses and Dissertations--Computer Science

Rural residents are often faced with many disparities when compared to their urban counterparts. Two key areas where these disparities are apparent are access to health and Internet services. Improved access to healthcare services has the potential to increase residents' quality of life and life expectancy. Additionally, improved access to Internet services can create significant social returns in increasing job and educational opportunities, and improving access to healthcare. Therefore, this dissertation focuses on the intersection between access to Internet and healthcare services in rural areas. More specifically, it attempts to analyze systems that can be used to improve Internet access …

A Secure And Distributed Architecture For Vehicular Cloud And Protocols For Privacy-Preserving Message Dissemination In Vehicular Ad Hoc Networks, Hassan Mistareehi

Theses and Dissertations--Computer Science

Given the enormous interest in self-driving cars, Vehicular Ad hoc NETworks (VANETs) are likely to be widely deployed in the near future. Cloud computing is also gaining widespread deployment. Marriage between cloud computing and VANETs would help solve many of the needs of drivers, law enforcement agencies, traffic management, etc. The contributions of this dissertation are summarized as follows: A Secure and Distributed Architecture for Vehicular Cloud: Ensuring security and privacy is an important issue in the vehicular cloud; if information exchanged between entities is modified by a malicious vehicle, serious consequences such as traffic congestion and accidents can …

Structured Attention For Image Analysis, Xin Xing

Theses and Dissertations--Computer Science

Attention mechanism, an approach to maintain the local and global features over the input, is the crucial element of the Transformer. This dissertation explores structured attention for image analysis, proposing attention-based methods for multi-label learning and Alzheimer’s Disease (AD) diagnosis.
For the multi-label learning task, I present two works under the Vision Transformer (ViT) framework. The first work focuses on supervised learning of multi-label classification. I address the problems of the multi-label classification and propose a model named AssocFormer, which adopts the association module to access the objects’ association relationship to improve the model performance. The second work addresses the …

Small Approximate Pareto Sets With Quality Bounds, William Bailey

Theses and Dissertations--Computer Science

We present and empirically characterize a general, parallel, heuristic algorithm for computing small ε-Pareto sets. The algorithm can be used as part of a decision support tool for settings in which computing points in objective space is computationally expensive. We use the graph clearing problem, a formalization of indirect organ exchange markets, as a prototypical example setting. We characterize the performance of the algorithm through ε-Pareto set size, ε value provided, and parallel speedup achieved. Our results show that the algorithm's combination of parallel speedup and small ε-Pareto sets is sufficient to be appealing in settings requiring manual review (i.e., …

Symbolic Computation Of Squared Amplitudes In High Energy Physics With Machine Learning, Abdulhakim Alnuqaydan

Theses and Dissertations--Physics and Astronomy

The calculation of particle interaction squared amplitudes is a key step in the calculation of cross sections in high-energy physics. These complex calculations are currently performed using domain-specific symbolic algebra tools, where the computational time escalates rapidly with an increase in the number of loops and final state particles. This dissertation introduces an innovative approach: employing a transformer-based sequence-to-sequence model capable of accurately predicting squared amplitudes of Standard Model processes up to one-loop order when trained on symbolic sequence pairs. The primary objective of this work is to significantly reduce the computational time and, more importantly, develop a model that …

The Basil Technique: Bias Adaptive Statistical Inference Learning Agents For Learning From Human Feedback, Jonathan Indigo Watson

Theses and Dissertations--Computer Science

We introduce a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown parameters. We present both the general framework for our technique and specific algorithms for biases drawn from a normal distribution. We evaluate our approach across various environments and tasks, comparing it to interactive and non-interactive machine learning methods, including deep learning techniques, using human trainers and a synthetic oracle with feedback distorted to varying degrees. …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

Peer-To-Peer Energy Trading In Smart Residential Environment With User Behavioral Modeling, Ashutosh Timilsina

Theses and Dissertations--Computer Science

Electric power systems are transforming from a centralized unidirectional market to a decentralized open market. With this shift, the end-users have the possibility to actively participate in local energy exchanges, with or without the involvement of the main grid. Rapidly reducing prices for Renewable Energy Technologies (RETs), supported by their ease of installation and operation, with the facilitation of Electric Vehicles (EV) and Smart Grid (SG) technologies to make bidirectional flow of energy possible, has contributed to this changing landscape in the distribution side of the traditional power grid.

Trading energy among users in a decentralized fashion has been referred …

Practical Ai Value Alignment Using Stories, Md Sultan Al Nahian

Theses and Dissertations--Computer Science

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally - using only a measure of task performance as feedback--can violate societal norms for acceptable behavior or cause harm. Consequently, it becomes necessary to prioritize task performance and ensure that AI actions do not have detrimental effects. Value alignment is a property of intelligent agents, wherein they solely pursue goals and activities that are non-harmful and beneficial to humans. Current approaches to value alignment largely depend on imitation learning or learning from demonstration methods. However, the dynamic nature …

Novel Architectures And Optimization Algorithms For Training Neural Networks And Applications, Vasily I. Zadorozhnyy

Theses and Dissertations--Mathematics

The two main areas of Deep Learning are Unsupervised and Supervised Learning. Unsupervised Learning studies a class of data processing problems in which only descriptions of objects are known, without label information. Generative Adversarial Networks (GANs) have become among the most widely used unsupervised neural net models. GAN combines two neural nets, generative and discriminative, that work simultaneously. We introduce a new family of discriminator loss functions that adopts a weighted sum of real and fake parts, which we call adaptive weighted loss functions. Using the gradient information, we can adaptively choose weights to train a discriminator in the direction …

The Performance Optimization Of Asp Solving Based On Encoding Rewriting And Encoding Selection, Liu Liu

Theses and Dissertations--Computer Science

Answer set programming (ASP) has long been used for modeling and solving hard search problems. These problems are modeled in ASP as encodings, a collection of rules that declaratively describe the logic of the problem without explicitly listing how to solve it. It is common that the same problem has several different but equivalent encodings in ASP. Experience shows that the performance of these ASP encodings may vary greatly from instance to instance when processed by current state-of-the-art ASP grounder/solver systems. In particular, it is rarely the case that one encoding outperforms all others. Moreover, running an ASP system on …

Determining Power System Fault Location Using Neural Network Approach, Edward O. Ojini

Theses and Dissertations--Electrical and Computer Engineering

Fault location remains an extremely pivotal feature of the electric power grid as it ensures efficient operation of the grid and prevents large downtimes during fault occurrences. This will ultimately enhance and increase the reliability of the system. Since the invention of the electric grid, many approaches to fault location have been studied and documented. These approaches are still effective and are implemented in present times, and as the power grid becomes even more broadened with new forms of energy generation, transmission, and distribution technologies, continued study on these methods is necessary. This thesis will focus on adopting the artificial …

Learning A Scalable Algorithm For Improving Betweenness In The Lightning Network, Vincent Davis

Theses and Dissertations--Computer Science

This paper presents a scalable algorithm for solving the Maximum Betweenness Improvement Problem as it occurs in the Bitcoin Lightning Network. In this approach, each node is embedded with a feature vector whereby an Advantage Actor-Critic model identifies key nodes in the network that a joining node should open channels with to maximize its own expected routing opportunities. This model is trained using a custom built environment, lightning-gym, which can randomly generate small scale-free networks or import snapshots of the Lightning Network. After 100 training episodes on networks with 128 nodes, this A2C agent can recommend channels in the Lightning …

Matrix Interpretations And Tools For Investigating Even Functionals, Benjamin Stringer

Theses and Dissertations--Computer Science

Even functionals are a set of polynomials evaluated on the terms of hollow symmetric matrices. Their properties lend themselves to applications such as counting subgraph embeddings in generic (weighted or unweighted) host graphs and computing moments of binary quadratic forms, which occur in combinatorial optimization. This research focuses primarily on counting subgraph embeddings, which is traditionally accomplished with brute-force algorithms or algorithms curated for special types of graphs. Even functionals provide a method for counting subgraphs algebraically in time proportional to matrix multiplication and is not restricted to particular graph types. Counting subgraph embeddings can be accomplished by evaluating a …

Supporting Stylized Language Models Using Multi-Modality Features, Chengxi Li

Theses and Dissertations--Computer Science

As AI and machine learning systems become more common in our everyday lives, there is an increased desire to construct systems that are able to seamlessly interact and communicate with humans. This typically means creating systems that are able to communicate with humans via natural language. Given the variance of natural language, this can be a very challenging task. In this thesis, I explored the topic of humanlike language generation in the context of stylized language generation. Stylized language generation involves producing some text that exhibits a specific, desired style. In this dissertation, I specifically explored the use of multi-modality …

Smart Decision-Making Via Edge Intelligence For Smart Cities, Nathaniel Hudson

Theses and Dissertations--Computer Science

Smart cities are an ambitious vision for future urban environments. The ultimate aim of smart cities is to use modern technology to optimize city resources and operations while improving overall quality-of-life of its citizens. Realizing this ambitious vision will require embracing advancements in information communication technology, data analysis, and other technologies. Because smart cities naturally produce vast amounts of data, recent artificial intelligence (AI) techniques are of interest due to their ability to transform raw data into insightful knowledge to inform decisions (e.g., using live road traffic data to control traffic lights based on current traffic conditions). However, training and …

Don't Give Me That Story! -- A Human-Centered Framework For Usable Narrative Planning, Rachelyn Farrell

Theses and Dissertations--Computer Science

Interactive or branching stories are engaging and can be embedded into digital systems for a variety of purposes, but their size and complexity makes it difficult and time-consuming for humans to author them. Narrative planning algorithms can automatically generate large branching stories with guaranteed causal consistency, using a hand-authored library of story content pieces. The usability of such a system depends on both the quality of the narrative model upon which it is built and the ability of the user to create the story content library.

Current narrative planning algorithms use either a limited or no model of character belief, …

High Performance Data Acquisition And Analysis Routines For The Nab Experiment, David Mathews

Theses and Dissertations--Physics and Astronomy

Probes of the Standard Model of particle physics are pushing further and further into the so-called “precision frontier”. In order to reach the precision goals of these experiments, a combination of elegant experimental design and robust data acquisition and analysis is required. Two experiments that embody this philosophy are the Nab and Calcium-45 experiments. These experiments are probing the understanding of the weak interaction by examining the beta decay of the free neutron and Calcium-45 respectively. They both aim to measure correlation parameters in the neutron beta decay alphabet, a and b. The parameter a, the electron-neutrino correlation coefficient, is …

Multi-Stream Longitudinal Data Analysis Using Deep Learning, Sajjad Fouladvand

Theses and Dissertations--Computer Science

Longitudinal healthcare data encompasses all tasks where patients information are collected at multiple follow-up times. Analyzing this data is critical in addressing many real world problems in healthcare such as disease prediction and prevention. In this thesis, technical challenges in analyzing longitudinal administrative claims data are addressed and novel deep learning based models are proposed for multi-stream data analysis and disease prediction tasks. These algorithms and frameworks are assessed mainly on substance use disorders prediction tasks and specifically designed to tackled these disorders. Substance use disorder is a public health crisis costing the US an estimated $740 billion annually in …

Neural Representations Of Concepts And Texts For Biomedical Information Retrieval, Jiho Noh

Theses and Dissertations--Computer Science

Information retrieval (IR) methods are an indispensable tool in the current landscape of exponentially increasing textual data, especially on the Web. A typical IR task involves fetching and ranking a set of documents (from a large corpus) in terms of relevance to a user's query, which is often expressed as a short phrase. IR methods are the backbone of modern search engines where additional system-level aspects including fault tolerance, scale, user interfaces, and session maintenance are also addressed. In addition to fetching documents, modern search systems may also identify snippets within the documents that are potentially most relevant to the …