Digital Commons Network^™

Data-Driven Techno-Economic Analysis, Optimization, And Uncertainty Quantification Of Integrated Energy Systems In Deregulated Electricity Markets, Jacob A. Bryan

All Graduate Theses and Dissertations, Fall 2023 to Present

Electricity is a ubiquitous energy source in daily life, powering everything from stovetops and cellphones to vehicles and industrial processes. While wind and solar power have become increasingly common sources of electricity, the majority of electricity is still produced by burning fossil fuels, releasing greenhouse gases and propelling climate change. Wind and solar power cannot economically replace these fossil fuel energy sources on their own because they do not produce consistent power; the wind must be blowing, and the sun must be shining for them to make electricity. Nuclear power is a reliable source of energy that does not generate …

Next Steps In Online Courts: Accelerating Access To Justice Through Court Technology, J.J. Prescott

Articles

For more than a decade, state courts have been expanding access to justice by adopting online dispute resolution (ODR) platforms and other outward-facing communication technologies. At a deep level, these reforms aim at improving society by bolstering the rule of law. At a surface level, these innovations recognize that the justice system works better when courts and law are easier and less costly to understand and use. In important respects, these efforts have been a success. The accessibility of many state courts is considerably more robust today than it was ten years ago, at least for small-stakes cases, like traffic …

Smart Credit Card Fraud Detection Using Machine Learning, Aisha Bin Sulaiman, Rowdha Masood Falaknaz

Theses

This thesis addresses the increasing issue of fraud resulting from technological advancements affecting both customers and fraudsters, while law enforcement agencies face challenges of inadequate case prioritization; data overload and slow investigative analysis. The central objective of this thesis revolves around strategies to counter these challenges, emphasizing the urgency of rapid response to major alert cases that can lead to widespread impacts. The authors' experience in financial fraud detection and credit card crime investigation within the police department has inspired this research, guiding the approach toward practical solutions for everyday operational challenges. The significance of this thesis lies in its …

Utilizing Machine Learning For Categorizing Disaster-Related Tweets, Ahmad Alfalasi

Theses

This study presents the development of a machine-learning model that recognizes tweets about disasters in real-time. The fast-paced development of social media, especially Twitter, has drastically changed the field of news transmission during crises. This change creates new challenges for the management of the volume, velocity, and veracity of data that are generated in such situations. The present tools do not have the capabilities of real-time processing of the huge volume of data; hence, new solutions are required. The model we are proposing addresses this problem by using advanced machine learning methods, such as natural language processing, to filter and …

Leveraging Ai To Improve Service Quality For Better Passenger Satisfaction At Airport, Abdulrhman Alsaleh

Theses

The aim of this research is to explore the impact of airport service quality on passenger satisfaction level in Dubai International Airport (DXB) and the study employed machine learning approach to establish the services quality dimensions relationship with passenger satisfaction. However, the initial objective is to analyze patterns and make future forecasts that DXB could use to enhance service delivery. The research focuses on key service quality dimensions: The study investigates the causal relationship between five constructs: reliability, service quality tangibility, assurance, responsiveness, and empathy using machine learning models such as regression and classification. The information data applies to the …

Applying Machine Learning For Crime Trend Analysis, Dana Alsoori

Theses

The analysis of crime rates has always been a critical component in shaping law enforcement strategies and public policy. This study focuses on the U.S. crime rates from 1975 to 2015, as reported by the FBI’s Uniform Crime Reporting (UCR) Program, to explore patterns and trends over four decades. By analyzing this extensive dataset, the project aims to provide insights into the dynamics of criminal activity across different regions and crime categories. The goal is to uncover both visible and hidden trends that can inform better decision-making in crime prevention and resource allocation. With the rise of data-driven methods, this …

Analyzing The Effects Of Economic Factors On Residential Real Estate Market Dynamics Of Dubai: Using Machine Learning Methods, Zarrina Shokirova

Theses

Dubai’s residential real estate market is known for its rapid growth and dynamic nature, making it an intriguing subject for analyzing the impact of various economic factors. This thesis examines how key economic elements such as GDP growth, inflation rates, and foreign investment influence property dynamics in Dubai. By synthesizing current research, this study aims to understand how these economic conditions affect real estate values, demand, and supply. Additionally, modern analytical methods, including decision trees, logistic regression, and random forest models, are employed to predict market trends and uncover significant patterns. This research contributes to both academic understanding and practical …

Robust And Efficient Active Inference For Perception, Action, And Learning, Zhizhuo Yang

Theses

Active Inference (AIF) is an emerging framework rooted in neuroscience aimed at elucidating human perception, action, and cognitive processes. Recent advances in machine learning have facilitated the non-invasive study of human cognition through the lens of this framework. This dissertation expands upon this theoretical foundation to address practical challenges in robotic control and human cognitive behavior analysis. We initiate our exploration with a review of the eye-tracking studies that underpin the motivation for AIF research. This provides a background for understanding how AIF can model cognitive processes. First, we present a minimal AIF model within a discrete state space, framed …

Improving Understanding Of Fluvial Reach-Scale Solute Transport And Uptake Using A Particle Tracking Model And Random Forest Machine Learning Model, Jiaying Liu

Doctoral Dissertations

In addition to transporting flowing water, river systems carry dissolved nutrients and pollutants, which can experience chemical reactions, biological uptake, or retention in surface or hyporheic zones. This dissertation enhances our understanding of solute transport and uptake in river reaches through three main components. The first component involves the development of a novel curve-fitting model designed to capture the characteristics of pulse-release breakthrough curves (BTCs) from tracer studies with conservative solutes. The model, which was found to be applicable to a wide range of field studies, enables the rapid comparison of transport parameters among diverse field studies obtained under a …

Fiscal Deficit And Human Development: Empirical Evidence From Nigeria, Elijah O. Akanni Dr

CBN Journal of Applied Statistics (JAS)

This study investigates the effects of fiscal deficits on human development in Nigeria from 1990 to 2021, employing standard econometric and machine learning approaches. Specifically, the paper applies autoregressive distributed lag (ARDL) models to examine linear relationships, and multivariate adaptive regression splines (MARS) to capture linear and nonlinear interactions among key variables influencing human development. Results from the ARDL analysis reveal that fiscal deficit does not significantly impact human development in Nigeria both in the short- and long run. However, MARS results indicate that fiscal deficits only enhance human development when kept below 1.34% of GDP but become detrimental beyond …

Density Functional Theory And Machine Learning Analysis Of C—C Reductive Coupling From Terminal Cyanido And Cyaphido Complexes, Roberto Magdiel Escobar

Theses and Dissertations

Carbon–carbon (C–C) bond activation has gained increased attention as a direct method for the synthesis of pharmaceuticals and industrial chemistry. Due to the thermodynamic stability and kinetic inaccessibility of the C–C bonds, however, activation of C–C bonds by homogeneous transition-metal catalysts under mild homogeneous conditions is still a challenge. Most of the systems in which the activation occurs either have aromatization or relief of ring strain as the primary driving force. The activation of unstrained C–C bonds of phosphaalkynes does not have this advantage. This study employs Density Functional Theory (DFT) calculations using the Gaussian16 package to elucidate and compare …

Examining The Use Of Problem Transformation Methods In Multi-Target Regression, Bradley Ryan Smith

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Although the impact of machine learning methods in the educational sciences has been limited, recent opportunities have emerged that can benefit from these flexible methods capable of predicting both linear and non-linear relationships. One emerging area of interest, multi-target regression (MTR), is concerned with the simultaneous prediction of multiple, continuous target variables and is an extension of traditional supervised learning. Problem transformation methods are a subset of MTR methods that seek to exploit the dependencies amongst targets using stacking, chaining, ensembles, or combinations of the three by expanding the Single-Target approach. This is accomplished by using one or more base-learners, …

Safety Through Feedback In Constrained Rl, Shashank Reddy Chirra, Pradeep Varakantham, Praveen Paruchuri

Research Collection School Of Computing and Information Systems

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost function can be prohibitively expensive. For instance, in the domain of self-driving, designing a cost function that encompasses all unsafe behaviours (e.g., aggressive lane changes, risky overtakes) is inherently complex, it must also consider all the actors present in the scene making it expensive to evaluate. In such scenarios, the cost function can be learned from feedback collected offline in between training rounds. This …

Artificial Intelligence, Machines, Devices, And Robots: Mobilizing Humanness And Intelligence In The American Techno-Landscape, Carlos A. Batres

Dissertations

This dissertation is an ethnographic inquiry of artificial intelligence (AI) in the techno-landscape of three major metropolitan areas in the United States. It traces the ways in which both experts and non-experts talk about their interactions with AI via machines, robots, and other devices, and how the ways in which people deal with AI-technologies have come to shape how we think about our own ways of going about doing things. The goal is to discern what the social ramifications of this technology may be as relationships and relations are formed betwixt and between people and artificially intelligent things.

Malicious Compliance: Examining Revenge Behaviors In Organizations, Patricia Jewel Emily Morrison

Theses and Dissertations

Revenge is a multifaceted behavior that manifests in various forms. The purpose of this dissertation was to examine a particular form of revenge known as malicious compliance, which has yet to be sufficiently researched. A two-study approach was used to examine malicious compliance. In the first study, qualitative data was collected from an online forum for sharing malicious compliance experiences. In the second study, 352 participants completed a mixed-methods survey online. Data from both studies was analyzed in RStudio and MAXQDA. Study 1 utilized unsupervised machine learning techniques, non-machine learning techniques, and thematic coding techniques to analyze the forum dataset. …

Mechanical Stability Of Body-Centered Cubic Iron At Earth's Core Pressure And Temperature Conditions Using A Molecular Graph Kernel Regression And Gaussian Process., Blaise Awola Ayirizia

Open Access Theses & Dissertations

We used machine learning to study nonmagnetic BCC iron in conditions similar to thosefound in the Earthâ??s core. Our model predicts the stability of BCC iron at high temperatures and pressures by analyzing a dataset from ab initio molecular dynamics simulations. The framework uses Gaussian process regression to make predictions by comparing the similarity between molecules. This comparison is made using the marginalized graph kernel. To use the marginalized graph kernel, the framework applies a spatial adjacency rule to convert molecules into graphs, where the vertices and edges are labeled by elements and interatomic distances, respectively. We can use this …

Artificial Intelligence And Machine Learning In Cancer Pain: A Systematic Review, Vivian Salama, Brandon Godinich, Yimin Geng, Laia Humbert-Vidan, Laura Maule, Kareem A Wahid, Mohamed A Naser, Renjie He, Abdallah S R Mohamed, Clifton D Fuller, Amy C Moreno

Faculty, Staff and Student Publications

Background/objectives: Pain is a challenging multifaceted symptom reported by most cancer patients. This systematic review aims to explore applications of artificial intelligence/machine learning (AI/ML) in predicting pain-related outcomes and pain management in cancer.

Methods: A comprehensive search of Ovid MEDLINE, EMBASE and Web of Science databases was conducted using terms: "Cancer," "Pain," "Pain Management," "Analgesics," "Artificial Intelligence," "Machine Learning," and "Neural Networks" published up to September 7, 2023. AI/ML models, their validation and performance were summarized. Quality assessment was conducted using PROBAST risk-of-bias andadherence to TRIPOD guidelines.

Results: Forty four studies from 2006 to 2023 were included. Nineteen studies used …

Decoding Neural Networks: An Information-Theoretic Guide To Interpretability, Error Analysis And Efficiency, Mackenzie J. Meni

Theses and Dissertations

This dissertation addresses critical challenges in neural network design by leveraging entropy-based techniques to improve model efficiency, interpretability, and bias reduction. Focusing on the unique demands of computer vision applications, particularly object detection and classification for real-time systems, this work introduces a series of innovative methods centered on information theory. At the core of these methods is the Probabilistic Explanations of Entropic Knowledge (PEEK) framework, a tool developed to analyze and visualize entropy distributions across feature maps. PEEK offers insights into information flow within neural networks, making it possible to pinpoint layers that contribute meaningfully to decision-making or identify those …

Long Term Impacts Of Early Social Environment On Chimpanzee White Matter, Michele M. Mulholland, Erin Hecht, Michael J. Wesley, William D. Hopkins

Psychology Faculty Publications

Early adverse rearing conditions are known to have deleterious consequences on social behavior, cognition, and brain development of both human and nonhuman primates. We analyzed archival diffusion tensor imaging (DTI) data from mother- (MR) or nursery-reared (NR) chimpanzees and used support vector machine learning to determine whether we could retrospectively classify chimpanzees as MR or NR based on white matter fractional anisotropy (FA) decades after their rearing experiences. A significant proportion of chimpanzees were correctly classified as MR and NR based on white matter fractional anisotropy (76.32%; p = 0.004). Voxel-based morphometry revealed that MR chimpanzees had increased FA in …

Lova3 : Learning To Visual Question Answering, Asking And Assessment, Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Bai Shou, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. Inspired by the human learning mechanism, we introduce LOVA3 , an innovative framework named “Learning tO Visual question Answering, Asking and Assessment,” designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming …

Sampdetox : Black-Box Backdoor Defense Via Perturbation-Based Sample Detoxification, Yanxin Yang, Chentao Jia, Dengke Yan, Ming Hu, Tianlin Li, Xiaofei Xie, Xian Wei, Mingsong Chen

Research Collection School Of Computing and Information Systems

The advancement of Machine Learning has enabled the widespread deployment of Machine Learning as a Service (MLaaS) applications. However, the untrustworthy nature of third-party ML services poses backdoor threats. Existing defenses in MLaaS are limited by their reliance on training samples or white-box model analysis, highlighting the need for a black-box backdoor purification method. In our paper, we attempt to use diffusion models for purification by introducing noise in a forward diffusion process to destroy backdoors and recover clean samples through a reverse generative process. However, since a higher noise also destroys the semantics of the original samples, it still …

Validation Studies Of The Flash-Tv System To Passively Measure Children’S Tv Viewing, Anil Kumar Vadathya, Tatyana Garza, Uzair Alam, Alex Ho, Salma M A Musaad, Alicia Beltran, Jennette P Moreno, Tom Baranowski, Nimah Haidar, Sheryl O Hughes, Jason A Mendoza, Ashok Veeraraghavan, Joseph Young, Akane Sano, Teresia M O'Connor

Children’s Nutrition Research Center Staff Publications

TV viewing is associated with health risks, but existing measures of TV viewing are imprecise due to relying on self-report. We developed the Family Level Assessment of Screen use in the Home (FLASH)-TV, a machine learning pipeline with state-of-the-art computer vision methods to measure children's TV viewing. In three studies, lab pilot (n = 10), lab validation (n = 30), and home validation (n = 20), we tested the validity of FLASH-TV 3.0 in task-based protocols which included video observations of children for 60 min. To establish a gold-standard to compare FLASH-TV output, the videos were labeled by trained staff …

Automated Fake News Detection System, Saja A. Al-Obaidi, Tuba Çağlıkantar

Iraqi Journal for Computer Science and Mathematics

Online news has been the majority of people’s information source in recent decades. However, a lot of the information that is accessible online is fake and sometimes even designed to mislead. It might be difficult for individuals to distinguish between certain false newspaper items and the real ones since they are so similar. Deep learning (DL) and machine learning (ML) models, among other automated false news detection (FND) techniques, are quickly becoming essential. A comparative study was conducted to analyze the performance of five prominent deep learning models across four distinct datasets, namely ISOT, FakeNewsNet, Dataset1, and Dataset2. Results indicated …

Are You Who Ai Says You Are? Exploring The Role Of Natural Language Processing Algorithms For “Predicting” Personality Traits From Text, Mukhunth Raghavan

USF Tampa Graduate Theses and Dissertations

Advances in text analytic approaches to measuring personality traits from text and speech have shown great promise for automating the assessment of personality. While a lot of effort has gone into developing robust algorithms for predicting personality ratings, more work is needed in understanding the function and theoretical relationships of these algorithmic ratings. This study proposes a novel application of the Trait-Reputation-Identity model (McAbee and Connelly, 2016), wherein, algorithm-generated ratings form the Reputation factor and are assumed to resemble learned observer ratings, the original self-report ratings form the Identity factor, and the total set of ratings form the consensus Trait …

Spatial Gap-Filling Of Himawari-8 Hourly Aod Products Using Machine Learning With Model-Based Aod And Meteorological Data: A Focus On The Korean Peninsula, Youjeong Youn, Seoyeon Kim, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

Given the complex spatiotemporal variability of aerosols, high-frequency satellite observations are essential for accurately mapping their distribution. However, optical remote sensing encounters difficulties in detecting Aerosol Optical Depth (AOD) over cloud-covered regions, creating data gaps that limit comprehensive environmental analysis. This study introduces a spatial gap-filling method for Himawari-8/Advanced Himawari Imager (AHI) hourly AOD data, using a Random Forest (RF) model that integrates meteorological variables and model-based AOD data. Developed and validated over South Korea from 1 January to 31 December 2019, the model effectively improved data coverage from 6% to 100%. The approach demonstrated high performance in blind tests, …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

Applying Machine‐Learning Methods To Laser Acceleration Of Protons: Lessons Learned From Synthetic Data, Ronak Desai, Thomas Zhang, J. J. Felice, Ricky Oropeza, Joseph R. Smith, Alona Kryshchenko, Chris Orban, Michael L. Dexter, Anil K. Patnaik

Faculty Publications

In this study, we consider three different machine-learning methods—a three-hidden-layer neural network, support vector regression, and Gaussian process regression—and compare how well they can learn from a synthetic data set for proton acceleration in the Target Normal Sheath Acceleration regime. The synthetic data set was generated from a previously published theoretical model by Fuchs et al. 2005 that we modified. Once trained, these machine-learning methods can assist with efforts to maximize the peak proton energy, or with the more general problem of configuring the laser system to produce a proton energy spectrum with desired characteristics. In our study, we focus …

Applications Of Computer Vision In Biomechanics And Orthopaedics, William Stewart Burton Ii

Electronic Theses and Dissertations

Machine learning has emerged as a key technology for enabling advanced computer vision systems. These systems now permeate many industries, and have enhanced traditional processes through autonomous interpretation of visual data. In the field of orthopaedics, the increasing prevalence of imaging highlights a need for similar tools. In many cases, however, direct translation of available frameworks fails to resolve the complex problems currently facing this field. Stringent performance requirements, complex visual environments, data scarcity, and implications for patient safety represent domain-specific factors which pose unique challenges to proven techniques. Novel approaches are needed to realize the full benefits of visual …

Natural Language Processing For Precise Identification Of Primary Tumor Histology And Radiation Necrosis In Stereotactic Radiosurgery Patients, Mario Fugal

MUSC Theses and Dissertations

The management of brain metastases and their associated complications, such as radiation necrosis, has long posed significant challenges in radiation oncology. Stereotactic radiosurgery (SRS) is a key treatment modality for patients with brain metastases, yet the complexity of metastatic disease and limitations in diagnostic coding systems, such as the International Classification of Diseases (ICD), often obstruct the accurate extraction of critical information from electronic health records (EHRs). This difficulty especially impacts the identification of primary tumor histology and the detection of post-treatment complications like radiation necrosis (RN), both of which are crucial for improving clinical outcomes and conducting robust observational …

Safe Reinforcement Learning For Intersection Management In Riti Communities Under Rare Extreme Events, Yuanzhang Xiao

CSET Project Reports

The rapid advancement of artificial intelligence (AI) is reshaping the transportation sector, with applications spanning autonomous vehicles, driver injury prevention, and traffic management. Efficient traffic management, particularly through adaptive intersection control, holds significant potential for reducing congestion. This study explores the application of reinforcement learning (RL) to adaptive traffic signal control in rural, isolated, tribal, and indigenous (RITI) communities, which face unique challenges such as rare extreme weather events. Standard RL approaches struggle in these contexts due to limited exposure to these rare events. In our study, we first evaluate several mainstream RL algorithms and identified two most promising approaches. …