Computer Sciences Commons^™

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Machine Learning Crime Prediction Models And The Gap Between Research And Implementation: A Systematic Review, Ricardo Huamantingo, Miguel Cano-Lengua, Ciro Rodriguez

Karbala International Journal of Modern Science

A crime is an illegal or violent act committed by one individual against another. The increasing crime rate has become a major concern as it negatively affects people's quality of life and generates significant social and economic costs. This study aims to identify the most widely used machine learning (ML) models for crime prediction, determine evaluation metrics for assessing model performance, and analyze key data characteristics to enhance real-world implementation. The study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. A search string was formulated using the population, intervention, comparison, and outcomes (PICO) framework and applied …

Seeking Structure In Complex Systems: From Feature Analysis To Space-Time Causal Discovery With Earth Science Applications, Jeffrey J. Nichol

Computer Science ETDs

Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. This body of research presents my investigations into data-driven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that …

Benford's Law In Basic Rnn And Long Short-Term Memory And Their Associations, Farshad Ghassemi Toosi

Department of Computer Science Publications

Benford's Law describes the distribution of numerical patterns, specifically focusing on the frequency of the leading digit in a set of natural numbers. It divides these numbers into nine groups based on their first digit, with the largest category comprising numbers beginning with 1, followed by those starting with 2, and so on. Each neuron within a neural network (NN) is associated with a numerical value called a weight, which is updated according to specific functions. This research examines the Degree of Benford's Law Existence (DBLE) across two language model methodologies: (1) recurrent neural networks (RNNs) and (2) long short-term …

Causal Neuro-Symbolic Artificial Intelligence: Synergy Between Neuro-Symbolic And Causal Artificial Intelligence, Utkarshani Jaimini

Theses and Dissertations

Understanding and reasoning about cause and effect is innate to human cognition. In everyday life, humans continuously engage in causal reasoning and hypothetical retrospection to make decisions, plan actions, and interpret events. This cognitive ability allows us to ask questions such as: “What caused this situation?”, “What will happen if I take this action?”, or “What would have happened had I chosen differently?” This intuitive capacity to form mental models of the world, infer causal relationships, and reason about alternative scenarios, particularly counterfactuals, is central to our intelligence and adaptability. In contrast, current machine learning (ML) and artificial intelligence (AI) …

Process-Grounded Knowledge-Infused Learning And Decision Making, Kaushik Roy

Theses and Dissertations

This dissertation introduces process-grounded knowledge-infused learning and reasoning, a novel framework for integrating domain-expertise-based process knowledge into the learning and reasoning mechanisms of artificial intelligence systems. This approach is designed to produce controlled, transparent, and reliable predictions in critical tasks such as medical diagnosis and recommendation. By focusing on the case study of mental illness diagnosis and recommendation—where decision-making must be grounded in processes such as disorder-specific diagnostic criteria—this work demonstrates methods to embed structured decision-making directly into the system architecture during both training and inference. This integration facilitates end-to-end training and reasoning while ensuring that outputs strictly adhere to …

Performance Comparison Of Quantum And Classical Machine Learning Models For Chronic Kidney Disease Prediction, Parama Sridevi, Paramita Basak Upama, Masud Rabbani, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

In this study, we develop and compare quantum and classical machine learning-based chronic kidney disease prediction models. We used the "Chronic_Kidney_Disease Data Set" of the UCI Machine Learning Repository. We performed data preprocessing and applied feature engineering techniques to select the best features. We developed two quantum machine learning-based models and two classical machine learning-based models. We used a hybrid classical-quantum environment for building quantum machine learning models. Finally, we compared the performances of all four models. We found that the Quantum Support Vector Machine performs best among the quantum models. The model’s accuracy was 95% with a k-fold cross-validation …

A Comparative Study Of Machine Learning And Deep Learning Models In Binary And Multiclass Classification For Intrusion Detection Systems, Ayesha Alharthi, Meera Alaryani, Sanaa Kaddoura

All Works

Network infrastructure evolution has significantly expanded the attack surface, leading to increasingly complex and sophisticated cybersecurity threats. Traditional rule-based intrusion detection systems (IDS) often fail to detect emerging attack vectors, prompting the need for intelligent, data-driven approaches. This study evaluates and compares the performance of machine learning (ML) and deep learning (DL) models for network intrusion detection. Two publicly available datasets were utilized: a binary-labeled software-defined networking (SDN) dataset and a multiclass industrial control system dataset based on the IEC 60870-5-104 protocol. Preprocessing steps included normalization, label encoding, and a 70:10:20 train-validation-test split. Seven models, Random Forest, Decision Tree, K-Nearest …

Milpbench: A Large-Scale Benchmark Test Suite For Mixed Integer Linear Programming Problems, Huigen Ye, Yaoyang Cheng, Hua Xu, Zhiguang Cao, Hanzhang Qin

Research Collection School Of Computing and Information Systems

Mixed-integer linear programming (MILP) is a cornerstone of optimization with applications across numerous domains. However, the development and evaluation of MILP-solving algorithms are hindered by existing benchmark datasets, which are often limited in scale, lack diversity, and are poorly structured, making them inadequate for systematic testing across different solving approaches, especially for machine learning (ML)-based methods. To address these issues, we introduce MILPBench, a large-scale benchmark suite comprising 100,000 MILP instances organized into 60 well-categorized classes. Using structural properties and embedding similarity metrics, we developed a novel classification framework to ensure both intra-class homogeneity and inter-class diversity. In addition to …

Classification Of Human Trust In Ai Using Brain Activity Data, Danushka Bandara, Ruhuan Liao, Fatima Chowdhury, Leslie Abbott

Northeast Journal of Complex Systems (NEJCS)

Trust plays a crucial role in human-computer interaction, particularly in scenarios involving artificial intelligence (AI) systems. This study explores the feasibility of using functional near-infrared spectroscopy (fNIRS) data to classify trust levels in human-AI interaction scenarios. A total of 18 participants completed an image classification task with an AI team member while their hemodynamic responses were recorded using fNIRS. Preprocessing of fNIRS data involved motion artifact removal, filtering, and normalization. Exploratory analysis identified significant associations between hemodynamic responses in the prefrontal cortex and trust levels. An across-subject binary trust classification model was developed using machine learning techniques, achieving an F1 …

Machine Learning: Neural Networking With Relu And Optimization, Aidan Redmond Brownell

Undergraduate Theses, Capstones, and Recitals

At its core, learning is an algorithmic process: it begins with input data, undergoes a series of transformations or computations, and yields an output intended to solve a specific task. This output is then compared against a target or desired result, and the internal mechanisms are updated based on how well the output aligns with expectations. While this feedback-driven process occurs almost effortlessly in humans, it is a far more structured, deliberate, and computationally intensive undertaking for machines.

Enhancing Water Scarcity Resilience In Egypt Through Machine Learning-Driven Phenological Crop Mapping And Water Use Efficiency Analysis, Surendra Maharjan, Wenzhao Li, Shahryar Fazli, Aqil Tariq, Rejoice Thomas, Cyril Rakovski, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Agriculture forms the backbone of Egypt’s economy, with the Nile Valley and Delta serving as key production zones for crops like wheat, rice, and clover. However, the sector faces mounting pressure from water scarcity, as it depends almost entirely on the Nile for irrigation, making it necessary to map major crops for assessing Water Use Efficiency (WUE) and informing agricultural planning. In this study, we used machine learning (ML) techniques—specifically Support Vector Machine (SVM) to time-series phenological data and optical indices (Enhanced Vegetation Index (EVI), Bare Soil Index (BSI), Land Surface Water Index (LSWI), Normalized Difference Vegetation Index (NDVI), and …

Multi-Label Classification Of Acoustic And Electronic Drum Sounds Using Machine Learning, Sean Perman

Electronic Theses and Dissertations

This paper presents a system for multi-class classification of drum sounds using audio signal processing and machine learning techniques. The project utilizes a diverse dataset of both acoustic and electronic drum samples and extracts ten distinct audio features to capture the timbral and temporal characteristics of each sound. The methodology includes signal preprocessing, feature extraction, and the application of supervised classification algorithms to distinguish between multiple drum classes. Experimental evaluations demonstrate that the selected features significantly enhance classification accuracy across a varied dataset. These findings underscore the effectiveness of combining traditional audio processing with modern machine learning, offering promising applications …

Enhancing Multi-Step Stock Price Forecasting With Social Media Sentiment And Engagement Metrics, Damilare Olaniyan

Electronic Theses and Dissertations

This thesis investigates whether social media sentiment can improve the accuracy of stock price prediction beyond traditional historical data. While financial markets have long relied on structured numerical indicators, the growing influence of public discourse on platforms like Twitter has introduced new opportunities for extracting market-relevant signals from unstructured text. The study focuses on four major technology firms and combines sentiment features derived from Twitter with historical stock prices in a hybrid machine learning framework. Engagement-weighted sentiment, linguistic complexity, and polarity intensity were extracted using natural language processing techniques and incorporated into classification and regression models. Results show that including …

A Stacking Ensemble Model For Food Demand Forecasting: A Preventative Approach To Food Waste Reduction, Asmaa Seyam, Sujith Samuel Mathew, Bo Du, May El Barachi, Jun Shen

All Works

Building effective demand forecasting is crucial for better planning and ensuring sustainability within food supply chain systems. The food industry has received the least attention for building demand forecasting approaches, with a noticeable lack of utilizing ensemble stacking models. Additionally, while some models have achieved accurate predictions, they do not consider freshness variables and are not assessed for their impact on waste reduction. This paper develops a demand forecasting framework that is considered as a preventative approach to reduce food waste by enabling food retailers to better manage inventory and balance supply with demand. The paper first develops an ensemble …

Predicting Consumers’ Purchase Intention Of Browsed Products: A Study Based On Eye‑Tracking, Feiyan Jia, Choon Ling Sia, Yani Shi, Fiona Fui-Hoon Nah, Keng Siau

Research Collection School Of Computing and Information Systems

Predicting consumers’ purchase intention of browsed products enables sellers to implement nuanced promotion strategies to stimulate purchase. But how can we predict consumers’ purchase intention of browsed products? Our research demonstrates that consumers’ eye movement data collected when they browse products can serve this aim. We train and test the prediction model using logistic regression and random forest algorithms. Using data collected in a laboratory experiment, our empirical results show that both algorithms perform much better than a random guess, and the logistic regression performs slightly better than the random forest. Our findings imply that eye movement data enable sellers …

Towards Explainable Ai On Graph Neural Networks: Xaig, Jiaxing Zhang

Dissertations

In the evolving landscape of artificial intelligence (AI), Graph Neural Networks (GNNs) have garnered growing prominence for their adeptness in processing graph-structured data. Despite this, the interpretability of their predictions often remains elusive. The demand for transparency and explainability in complex prediction models has reached unprecedented levels. To address this, post-hoc instance-level explanation techniques have emerged, aiming to unveil the rationale behind GNN predictions. These techniques endeavor to unearth substructures that elucidate the predictive behavior of trained GNNs.

This dissertation embarks on an exploration of Explainable AI (XAI) technologies within the realm of GNNs. Amid the challenges posed by the …

Application Of Pu Learning In Detection Of Ddos Attacks, Gagana Sathya Narayana Prasad

Theses and Dissertations

The gcore radar 2024 says, the number of DDoS attacks has been increased by 46% in 12 months. Supervised and unsupervised techniques struggle detecting DDoS attacks due to the scarcity of labeled attack samples and an overwhelming presence of benign traffic. In contrast PU- Learning offers a promising solutions by dividing the data into positive and unlabeled data. This study explores the effectiveness of PU-learning in detecting DDoS attacks by comparing it with unsupervised methods. This method employs PU Bagging, Two Step method and auto-encoder based models to extract meaningful patters from network traffic data, utilizing CICDDoS2017 dataset for evaluation. …

Efficient Eeg Epilepsy Classification And Feature Selections Based On Hellinger Distance, Muhammed Sadiq

Theses and Dissertations

Accurate and efficient detection of epileptic seizures from EEG signals remains a critical challenge due to high-dimensional data, class imbalance, and the limitations of standard classifiers. This thesis introduces two novel models to address these challenges. The first model presents a new classifier based on the Hellinger Distance, specifically designed to enhance discriminative capability and robustness against imbalanced datasets. By integrating the Hellinger Distance Classifier with Particle Swarm Optimization (PSO) for feature selection, this model significantly improves classification performance while reducing computational complexity. Experimental evaluations on the Bonn dataset demonstrate an accuracy of 96.25%, an F1-score of 97.74%, a recall …

Computational Complexity Of Soundness Verification For Neural Networks, Scott Sirri

McKelvey School of Engineering Graduate Student Theses & Dissertations

Neural networks are an increasingly ubiquitous tool in systems of varying complexity across a range of domains. While these tools can be used to learn and predict complex functions, their opaque nature limits the scope of their acceptable applications. In particular, a lack of performance guarantees means that they are unsuitable for safety-critical applications such as self-driving cars and scheduling systems. Neural networks trained to solve NP-complete problems, in particular, are unlikely to be able to solve the problem exactly. However, a weaker soundness guarantee may be sufficient for some systems, e.g., that positive instances of the problem may be …

Machine Learning - Driven Solar Forecasting In Dust-Prone Regions For Sustainable Energy Systems, Kadhim Hayawi, Husna Maliakkal, Neethu Venugopal, Thanveer Musthafa Hussain, Gomathi Bhavani Rajagopalan

All Works

This research focuses on improving solar energy forecasting in dust-affected regions such as the UAE, where frequent dust storms reduce photovoltaic (PV) efficiency by scattering and absorbing sunlight. Many existing models overlook the impact of dust events, leading to inaccurate forecasts during such conditions. To address this, the study develops machine learning models—including LSTM, GRU, and hybrid LSTM-GRU architectures—that incorporate solar, weather, and dust-related features. The models were evaluated across multiple forecasti24 hoursons (1, 6, 12, and 24 hours), demonstrating that including dust-related variables significantly enhances prediction accuracy, particularly for short-term forecasts. Temporal and seasonal analyses revealed that dust events, …

Identification Of Subtypes Of Post-Stroke And Neurotypical Gait Behaviors Using Neural Network Analysis Of Gait Cycle Kinematics, Andrian Kuch, Nicolas Schweighofer, James M. Finley, Alison Mckenzie, Yuxin Wen, Natalia Sánchez

Physical Therapy Faculty Articles and Research

Gait impairment post-stroke is highly heterogeneous. Prior studies classified heterogeneous gait patterns into subgroups using peak kinematics, kinetics, or spatiotemporal variables. A limitation of this approach is the need to select discrete features in the gait cycle. Using continuous gait cycle data, we accounted for differences in magnitude and timing of kinematics. Here, we propose a machine-learning pipeline combining supervised and unsupervised learning. We first trained a Convolutional Neural Network and a Temporal Convolutional Network to extract features that distinguish impaired from neurotypical gait. Then, we used unsupervised time-series k-means and Gaussian Mixture Models to identify gait clusters. We tested …

Satellite Reorientation Using Reinforcement Learning Under Unknown Attitude Failure, Matthew Willoughby

Doctoral Dissertations and Master's Theses

This study presents a reinforcement learning (RL) approach for reestablishing communication with deep-space satellites under unknown attitude determination and control system (ADCS) failures. When traditional fault-tolerant control methods cannot restore signal, the proposed RL controller acts as a last-resort measure by autonomously reorienting the satellite’s antenna toward Earth while charging the battery via solar panels. A generic reward function, designed for the RL-based method, enables the controller to adapt to diverse failure scenarios, including severe actuator noise, misalignment, and complete actuator failure. Simulations are conducted in the Basilisk environment and trained with the tonic framework and demonstrate ranging capabilities of …

Improving The Reproducibility Of Deep Learning Software: An Initial Investigation Through A Case Study Analysis, Nikita Ravi, Abhinav Goel, James C. Davis, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns about reproducing the results of these deep learning methods. This is significant because reproducibility is the foundation of reliability and validity in software development, particularly in the rapidly evolving domain of deep learning. The difficulty of reproducibility may arise due to several reasons, including having differences from the original execution environment, incompatible software libraries, proprietary data and source code, lack of transparency, and the stochastic nature in some software. A study conducted by …

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …

Analyzing Unmanned Aircraft System (Uas) Incidents From Nasa Asrs Data Using Unsupervised Machine Learning, Kacey Haws

Electrical Engineering and Computer Science Undergraduate Honors Theses

The NASA Aviation Safety Reporting System (ASRS) assembles voluntarily submitted aviation safety incident reports in their database to act on the information provided. This database allows the government, companies, and citizens to submit incident or situational reports to its database to discern recurring issues in the National Aviation System (NAS) so that the proper officials can act [1]. The narratives provided in these reports are text-based, resulting in large amounts of data to process. Previous work in the University of Arkansas Aerospace Systems Engineering and Transportation Laboratory (ASYST) lab involved parsing unmanned aircraft system (UAS) incident reports manually. While these …

Using Machine Learning To Detect Vault (Anti-Forensic) Apps, Michael N. Johnstone, Wencheng Yang, Mohiuddin Ahmed

Research outputs 2022 to 2026

Content hiding, or vault applications (apps), are designed with a secondary, often concealed purpose, such as encrypting and storing files. While these apps may serve legitimate functions, they unequivocally present significant challenges for law enforcement. Conventional methods for tackling this issue, whether static or dynamic, prove inadequate when devices—typically smartphones—cannot be modified. Additionally, these methods frequently require prior knowledge of which apps are classified as vault apps. This research decisively demonstrates that a non-invasive method of app analysis, combined with machine learning, can effectively identify vault apps. Our findings reveal that it is entirely possible to detect an Android vault …

Achieving Fairness In Zoning Laws With Machine Learning, William Schimitsch

College Honors Program

Zoning is a powerful regulatory tool that determines how municipalities use and develop land. The goal of zoning is to classify land use (e.g., residential, commercial, industrial) to maximize compatibility among neighboring parcels. Local zoning decisions, however, are made by small-sized boards, often through an opaque process, which raises concerns about bias and fairness. In the United States, zoning has historically prioritized single-family housing and thus created economic barriers that limit access to certain communities. Given the task of classifying land use and the wealth of geographical, demographic, and infrastructural data describing each parcel, the problem of bias in zoning …

Phoneme Recognition For Pronunciation Improvement, Matthew Heywood

Theses/Capstones/Creative Projects

This project aims to improve English pronunciation by investigating speech errors and developing a tool to provide precise feedback. The study focuses on creating a new pronunciation tool that offers localized feedback, identifies specific errors, and suggests corrective measures. By addressing the shortcomings of current methods, this research seeks to enhance pronunciation refinement.

Utilizing cutting-edge technology, the tool leverages speech-to-phoneme AI models and modified lazy string matching algorithms to compare the user's spoken input with the intended pronunciation. This allows for a detailed analysis of discrepancies, providing users actionable insights into their phonetic errors. The speech-to-phoneme AI models mark a …

A Machine Learning Framework For Packet Anomaly Detection In Smartgrid Substation Networks, Sowmya Bandari

School of Computing: Dissertations, Theses, and Student Research

The increasing reliance on Smart Grid Substation Networks for efficient electricity distribution has amplified cybersecurity vulnerabilities, particularly within Supervisory Control and Data Acquisition (SCADA) systems. The IEC 60870-5-104 (IEC-104) protocol, widely adopted for communication between Remote Terminal Units (RTUs) and Human-Machine Interfaces (HMIs), lacks inherent encryption and authentication mechanisms, rendering it susceptible to sophisticated cyberattacks. Threats such as False Data Injection Attacks (FDIAs), command injection, covert attacks and replay attacks pose significant risks by manipulating grid control signals, potentially leading to undetected operational disruptions, cascading failures, or system-wide instability. Conventional signature-based Intrusion Detection Systems (IDS) often fail to identify zero-day …