Data Science Commons^™

Online Prediction Of Streaming Data, Aleena Chanda

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

We present two new approaches for point prediction with streaming data based on a) the Count-Min sketch and b) Gaussian Process Priors with random bias. The methods are intended for the most general case where no true model can be usefully formulated for the data stream. In statistical contexts, this is often called the M open problem class. For the Count Min Sketch method we show that the predicted distribution function ^F converges to F under the assumption that the data consists of i.i.d samples from a fixed distribution function F. To implement the Gaussian Process Prior methods, we used …

Estimation Methods For Bayesian Exponential Random Graph Models Under The Horseshoe Prior., Pamela Linares

Electronic Theses and Dissertations

Networks are powerful tools for modeling the complexity of social interactions, biological systems, and information spread. A leading statistical frameworks for analyzing network data are Exponential Random Graph Models (ERGMs), which provide a principled approach to capturing structural dependencies. However, ERGMs remain challenging to estimate, especially in sparse or high-dimensional settings where models suffer from degeneracy and unstable parameter inference. This paper proposes a penalized Bayesian approach to ERGMs that utilizes the horseshoe prior, a sparsity-inducing global-local shrinkage prior. This prior offers robust regularization while preserving important signals, improving estimation by shrinking irrelevant parameters and reducing the impact of extreme …

Predicting Music Origin With Deep Learning, Fruzsina Ladanyi

Electronic Theses, Projects, and Dissertations

This project explores the usage of a late fusion deep learning architecture to predict the geographic origin of music. Mel-Frequency Cepstral Coefficients (MFCCs) and the language of the music sample are used as features. MFCCs were extracted from audio files to capture sound features. The language was identified using OpenAI’s Whisper model to provide additional context. A late fusion neural network architecture combining Long Short-Term Memory (LSTM) layers for sequential MFCC input and dense layers for non-sequential language features were employed to support both classification and regression tasks. The classification model achieved an accuracy of 33.03% across 56 countries or …

Robustness Investigation, Detection, And Defense Of Deep Learning Models Against False Data Injection, Amirhossein Nazeri

All Dissertations

This dissertation addresses the critical challenge of adversarial robustness in deep learning systems, focusing on two fundamental domains: time-series prediction and object detection. As these AI systems become increasingly deployed in safety-critical applications from power grid management to autonomous vehicles their vulnerability to adversarial attacks poses significant risks to infrastructure and human safety.

The first contribution introduces a novel stealthy black-box False Data Injection (FDI) attack specifically designed for quasi-periodic time-series data. Unlike existing attacks that produce easily detectable anomalies, our method generates adversarial perturbations that preserve the underlying periodicity and statistical properties of the data, effectively bypassing traditional anomaly …

Non-Blackbox Robust Design Of Machine Learning In Networks, Venkat Sai Suman Lamba Karanam

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

Networked systems have become increasingly complex, with newer communication technologies and standards being added every day. Machine Learning (ML) and Artificial Intelligence (AI) paradigms have been adopted in networks to not only solve many fundamental problems, but also to allow seamless integration of components comprising them. The saying “let’s not reinvent the wheel” in ML/AI adoption implies that model architecture design be left for pure ML/AI researchers, while network researchers focus on input preprocessing (e.g. formatting the packet data to be fed to a model), hyperparameter fine-tuning and a trial-and-error approach to find the “best” result. …

Authentication And Message Integrity Verification For Emerging Wireless Networks, Ebuka Philip Oguchi

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

This dissertation presents a comprehensive body of research on authentication and message integrity verification for emerging wireless networks, focusing on secret-free and physical layer security techniques across diverse, challenging, and unconventional environments.

It comprises four first-author contributions that span underground wireless systems, over-the-air (OTA) channels, vehicular communications, and nanoscale molecular networks.

The first contribution, Soil-Assisted Trust Establishment for Underground Wireless Networks (STUN), introduces a physical-layer trust bootstrapping protocol that achieves authentication and message integrity without pre-shared secrets. Leveraging underground-to-air propagation laws and trusted relay nodes, STUN resists active signal injection attacks and demonstrates security comparable to the unbalanced oil and …

Experimental Design And Analysis For Decision Making: Methodology And Applications, Yezhuo Li

All Dissertations

This dissertation develops and applies advanced statistical and optimization frameworks to enhance decision-making under uncertainty, particularly in engineering and manufacturing contexts. First, we introduce an approach for the optimal design of controlled experiments that accounts for observational covariates, enabling more precise and personalized decisions. Second, we explore the application of constrained Bayesian optimization, using Gaussian process surrogate models, to optimize composite cure processes, significantly reducing computational effort while maintaining high predictive accuracy. Building on this foundation, we extend Bayesian optimization to bivariate Gaussian process models that capture correlations between objective and constraint functions, offering new insights into multidimensional decision landscapes. …

Application Of Artificial Neural Network Algorithms For Irrigation Scheduling, Lisa Umutoni

All Dissertations

Neural networks have been extensively used in predicting soil water tension for improved irrigation scheduling and management. However, their lack of interpretability constrains their efficacy in grasping the nuanced patterns prevalent in soil water tension time series data. The first goal of this research was to develop interpretable deep neural network models for soil water tension prediction across multiple soil depths (0.15m, 0.3m, 0.46m and 0.6m) and prediction horizons (1h, 6h, and 12h). The Neural Hierarchical Interpolation for Time Series (N-HiTS) and Neural Basis Expansion Analysis Time Series (N-BEATS) models were used in this research. Historical soil water tension data …

Unsupervised Deep Learning For Video Restoration, Mary Damilola Aiyetigbo

All Dissertations

In today's digital era, visual data is vital across several domains such as medical diagnostics, scientific imaging, surveillance, and entertainment. However, video data often suffers from degradations like noise, blur, compression artifacts, and low resolution, which degrade quality and downstream usability. Video restoration aims to recover clean, high-fidelity video from such corrupted inputs. Unlike static images, video restoration must maintain temporal consistency across frames, making it a significantly more complex problem. While supervised deep learning methods have achieved state-of-the-art results, they typically require large datasets of paired noisy-clean video datasets that are scarce or impractical to obtain in real-world settings …

Study Of Ai Applications In Biomedical Data Acquisition, Communication, And Analysis: Cest Mri Acceleration And Ecg Transmissions, Adarsha Bhattarai

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

This dissertation investigates the application of artificial intelligence in biomedical data acquisition, communication, and analysis to advance neurological research and to enable the early detection of cardiovascular conditions. Despite significant advances in imaging and physiological modalities, challenges persist. Imaging modalities, such as the chemical exchange saturation transfer magnetic resonance imaging (CEST MRI) technique are challenged by a prolonged data acquisition time and high operational costs. In addition, physiological modalities such as electrocardiogram (ECG) sensors face constraints in providing uninterrupted signal monitoring which is crucial for the timely detection of premature cardiac abnormalities. The primary goal of this work is to …

Graph-Based Machine Learning: Higher-Order Interactions, Guided Generation, And Knowledge-Graph Tools, Thomas J. Kerby

All Graduate Theses and Dissertations, Fall 2023 to Present

This dissertation brings the power of graph thinking to three key challenges in modern AI, making complex data more transparent, generative design more controllable, and scholarly exploration more intuitive. First, we introduce Local CorEx, a new machine learning technique that uncovers hidden relationships among variables, making it easier to understand complex datasets without heavy computation. Next, we show how to guide the creation of new molecules by viewing the generation process itself as a walk through a "state graph," letting researchers steer outcomes toward desired chemical properties—without any extra model training. Finally, we deliver an open-source toolkit that builds interactive …

Tackling Data Quality Challenges In Remote Sensing: Solutions For Reliable Urban Heat Island Analysis, Wei Xia, Aqil Tariq, Hesham El-Askary, Rana Waqar Aslam, Elgar Barboza, Dmitry E. Kucher, Youssef M. Youssef, Habib Kraiem

Mathematics, Physics, and Computer Science Faculty Articles and Research

Urban heat islands (UHIs) pose critical challenges to public health, energy demand, and environmental sustainability, particularly in rapidly expanding urban regions. This study examines the complex relationship between building configurations and integrated green spaces, as well as their combined impact on thermal regulation. It focuses on addressing data quality issues commonly encountered in remote sensing applications. Using high-resolution multispectral and thermal imagery, we developed an integrated modeling approach that captures the collective influence of built form and green infrastructure on urban microclimates. A key finding is the significant linear inverse relationship between green space coverage and land surface temperature, underscoring …

Discovering And Designing Novel Perovskite Photovoltaic Materials Via Machine Learning, Junyeong Ahn

Discovery Undergraduate Interdisciplinary Research Internship

Perovskite semiconductors are promising materials for high-efficiency photovoltaics due to their outstanding optoelectronic properties, emerging as a sustainable energy source through solar cell applications. Perovskites with the ABX₃ composition (A, B = metal or organic cations with varying oxidation states; X = chalcogen or halogen anions) have gained interest for their excellent phase stability and compositional tunability. However, combinatorial possibilities arising from the many choices of A, B, and X site species, and their respective mixing fractions, a large number of possible ABX₃ perovskites remain undiscovered. In this work, we used machine learning (ML) methods to design new stable and …

Multiclass Cyberbullying Detection Using Advanced Neural Network Architectures: A Comparative Study Amidst The Covid-19 Pandemic, Mahyar Alinejad

Data Science and Data Mining

Amidst the COVID-19 pandemic, the digital communication landscape has seen an unprecedented rise in cyberbullying incidents. Addressing this critical issue, our study develops and evaluates a novel multiclass cyberbullying detection framework employing several advanced neural network architectures—namely Neural Networks (NN), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Gated Recurrent Units (GRU). Utilizing a balanced dataset created through Dynamic Query Expansion, this research benchmarks the performance of these models in accurately classifying cyberbullying according to specific victim attributes such as age, ethnicity, gender, and religion. Our results demonstrate that LSTM and GRU models, in particular, exhibit superior performance …

Multiclass Cyberbullying Detection Using Advanced Neural Network Architectures: A Comparative Study Amidst The Covid-19 Pandemic, Mahyar Alinejad

Data Science and Data Mining

Amidst the COVID-19 pandemic, the digital communication landscape has seen an unprecedented rise in cyberbullying incidents. Addressing this critical issue, our study develops and evaluates a novel multiclass cyberbullying detection framework employing several advanced neural network architectures—namely Neural Networks (NN), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Gated Recurrent Units (GRU). Utilizing a balanced dataset created through Dynamic Query Expansion, this research benchmarks the performance of these models in accurately classifying cyberbullying according to specific victim attributes such as age, ethnicity, gender, and religion. Our results demonstrate that LSTM and GRU models, in particular, exhibit superior performance …

Transforming Recruitment: The Power Of Data-Driven Decision Making, Dylan Klim

Faculty and Staff Publications & Presentations

Dylan Klim, senior assistant director in Admission presented at the National Small College Enrollment Conference (NSCEC) in Charlotte, North Carolina. Klim's presentation was titled, "Transforming Recruitment: The Power of Data-Driven Decision Making."

The NSCEC conference focuses on small colleges and universities that provide essential education and networking opportunities for small college professionals.

Towards Scalable Taxi Demand Prediction, Yifei Shen

Lingnan Theses (MPhil & PhD)

Accurate taxi demand prediction is essential for optimizing urban mobility systems across varying spatial-temporal resolutions and data conditions. Scalable taxi demand prediction refers to the capability of forecasting models to adapt to different granularities of spatial and temporal data while maintaining prediction accuracy, a critical requirement for practical urban applications ranging from fleet management to transportation planning. However, two fundamental challenges impede this scalability: data sparsity and multi-resolution forecasting requirements. Data sparsity, particularly pronounced in high-resolution predictions where numerous regions exhibit minimal activity, significantly compromises model performance. Concurrently, different urban applications necessitate predictions at varying temporal and spatial granularities, requiring …

Policy-Based Redactable Set Signatures, Zachary A. Kissel

Computer and Data Science Faculty Publications

A redactable set signature scheme is a signature scheme that allows a redactor, without possessing the signing key, to convert a signature on set S to a signature on set S' if S' ⊂ S. This paper introduces a new form of redactable set signature scheme called a policy-based redactable set signature scheme. These redactable set signatures allow for a signer to provide a redaction policy at signing time that limits the possible redactions that can be made by a redactor. In particular, a signature on set S can only be redacted to a signature on if S' ⊂ …

Three-Stage Latent Dynamics Forecasting (T-Ldf) Framework For Shenzhen Metro Passenger Flow Prediction, Tianze Zhang

Lingnan Theses (MPhil & PhD)

Accurate forecasting of metro passenger flow is vital for efficient urban transportation management and optimal resource allocation in modern cities. Traditional ARIMA-based models effectively capture regular, cyclical patterns but struggle with sudden, nonlinear fluctuations caused by random events such as weather disruptions, special events, or service interruptions. Moreover, existing research predominantly focuses on individual stations, overlooking the complex cross-station interactions inherent in networked metro systems where passenger flows are interconnected across the entire network.

To address these critical limitations, we propose the Three-Stage Latent Dynamics Forecasting (T-LDF) Framework, a novel approach that systematically integrates temporal decomposition, latent dynamics extraction, and …

A Cancer Education Needs Assessment: Informing Middle-Aged Female Patients About The Relationships Between Obesity And Women’S Health Concerns In The Reproductive System, Breast, And Endometrial Health, Batul Mirza

MUSC Theses and Dissertations

Obesity significantly impacts women’s health, particularly among middle-aged women, by increasing the risk of hormone-sensitive cancers such as breast, endometrial, and reproductive system cancers. This study examines the educational needs of this demographic group regarding obesity-related cancer risks and explores effective intervention strategies. Obesity-induced mechanisms – hormonal imbalances, chronic inflammation, and insulin resistance – drive cancer susceptibility, emphasizing the need for targeted health education. The study employs a qualitative design, which includes interviews with subject matter experts (SMEs) and surveys of middle-aged women. The goal is to assess awareness, perceived barriers, and preferred learning methods. Findings suggest that with many …