Digital Commons Network^™

Predictive Ai Models For Phishing Attack Detection: A Data-Driven And Statistical Analysis Approach, Suhail Othman Alfalasi

Theses

Phishing has remained a serious threat to cybersecurity, as this type of attack can easily bypass detection systems that are either rule-based or blacklist-based. The proposed thesis work will present a solution that will make use of both statistical analysis and machine learning to correctly identify a phishing website. The solution will make use of a hybrid approach comprising statistical-based preprocessing methodologies, such as PCA and decision tree-based feature selection, to filter the crucial URL features that a website may possess. A carefully balanced dataset has been utilized, as well as a non-parametric approach utilizing the Mann-Whitney U-test to validate …

The Role Of Ai And Predictive Policing In Crime Prevention, Saif Salem Mohammad Hassan Abdulla

Theses

The current thesis examines the application of Artificial Intelligence (AI) in the arena of predictive policing and crime forecasting using an integrated case study based on the empirical approach supported by a narrative review of literature. Due to the growing use of digital data by the law-enforcement agencies, AI techniques, including machine learning and spatio-temporal modelling, are implemented to detect patterns of crimes, predict high-risk areas, and assist law-enforcement decision-making. Though these technologies have the potential to make the processes of accuracy and resource allocation better, they also bring up the issue of the fairness, transparency, and disproportionate effects on …

Data-Driven Crime Prediction: Toward Smarter Reduction Strategies, Zayed Almarri

Theses

This study explores how machine learning and weather data can be used for the prediction of crime more accurately in the city of Seattle. Predictive policing is a method in law enforcement that uses data and computer algorithms to forecast the locations that crimes are likely to happen. Although many studies focused on using past crime data alone, this research also includes weather conditions like temperature, rainfall, and humidity, which may influence when and where crimes occur. Several machine learning models, including Random Forest (RF) and Support Vector Machines (SVM), were used to classify areas of the city into high-risk …

An Interpretable Machine Learning Framework For Detecting Phishing Urls Based On Lexical Features, Khalid Alrokhaimi

Theses

Phishing attacks represent one of the most significant and persistent threats in the cybersecu- rity landscape, with attackers increasingly using sophisticated URL manipulation techniques to deceive users and steal sensitive information. Traditional detection methods, which rely primarily on blacklists and heuristic rules, struggle to identify zero-day phishing URLs that have not yet been catalogued in security databases. This research addresses this critical gap by developing an interpretable machine learning framework for detecting phishing URLs usingclexical, structural, content-based, and domain metadata features. The study employs a comprehensive dataset of 11,430 labeled URLs (5,715 legitimate and 5,715 phishing) with 87 extracted features, …

Persuasive Pathways In Digital Apologies: The Role Of Persuasion Routes In Engagement With Youtuber Apology Videos, Darrin Majocha

Theses

This study explores how viewers process YouTube apology videos and how those processing methods relate to their judgments of the creator and their willingness to continue engaging with the channel. Guided by the Elaboration Likelihood Model, a single-session online survey experiment randomly assigned 413 adult participants to watch one of five publicly available apology videos from well-known YouTubers. After viewing, participants reported the extent to which they engaged in central versus peripheral processing, rated the creator's credibility and the apology's sincerity, and indicated their intentions to engage. Central processing was positively associated with engagement intentions, whereas peripheral processing was weakly …

Achilles, Sreelekha Samala

Theses

ACHILLES is a speculative design project and conceptual artifact. It is not intended to function as a medically certified or biomechanically operational prosthetic arm. Instead, it operates within the realm of design research, using visual realism and luxury aesthetics to explore how assistive technologies could be perceived differently in cultural, emotional, and commercial contexts. Using 3D software to experiment with color, pattern, and texture, I designed a realistic mockup to demonstrate how Achilles could appear in a high-end commercial setting. Instead of animating the model, I focused on camera motion to highlight the prosthetic from multiple angles, emphasizing its sculptural …

Predicting Employee Attrition With Machine Learning: Data-Driven Strategies For Enhancingworkforce Retention, Ali Almheiri

Theses

In this research, the dual prediction and prescription model is developed and validated so that this model can not only predict employee turnover risk, but it also proposes the appropriate retention interventions, which apply across industries. On the basis of the IBM HR Analytics Attrition dataset (n=1,470), we preprocessed demography, job and satisfaction variables and trained three machine-learning classifiers, Random Forest, Logistic Regression and XGBoost to predict voluntary turnover. XGBoost model recorded the best discrimination (AUC=0.87), sensitivity (0.76), and specificity (0.81), which signifies strong predictive power. Analysis of feature-importance was conclusive with time, rate of frequent business travel and compensation …

Event-Driven Traffic Management, Abdulla Humaid Alhosani

Theses

Traffic congestion during peak hours and large public events is a persistent challenge in urban areas, affecting mobility, economic productivity, and quality of life. While many cities are moving towards smart, data-driven traffic management, the practical effectiveness of predictive models for event-driven traffic control remains uncertain. This thesis presents an offline, data-driven feasibility study that investigates whether ma- chine learning and time-series models can predict traffic volume patterns under different conditions, including weather and the presence of events. Using a historical traffic dataset with derived trend variables, the study applies exploratory data analysis (EDA) and two predictive approaches: ARIMA for …

Ai-Powered Mobile Phone Activity Insights: Developing Predictive Models For Smarter Decision-Making, Maryam Al Ali

Theses

This study investigates how artificial intelligence can enhance telecom network management by forecasting internet usage, predicting congestion, and identifying user behavior patterns from mobile phone activity data. The study made use of anonymized logs for calls, SMS and internet, and put up a multi-model analytical pipeline, which was composed of time-series forecasting (ARIMA, LSTM), clustering (K-Means), and classification (XGBoost), to perform the analysis. Among the time-series methods, ARIMA ranked first in the forecast performance (RMSE=0.31) and gave LSTM a convincing defeat in the case of this particular short and stable dataset. Based on K-Means segmentation, users were sorted into five …

Optimizing Human Resource Decisions: Predicting Promotions Using Data Analytics, Mohammad Khalid A Mohammad Abdulrahim

Theses

Proper and objective selection of high potential employees to promote them is a major dilemma in the Human Resources (HR) department, more so in sensitive and hierarchal environments in the public sector where subjectivity is likely to take place. This paper is based on this ubiquitous issue, and it seeks to develop, experiment, and examine a clear and equitable machine learning model that can forecast the possibility of an employee to get a promotion according to organized past HR records. The technique was solid preprocessing, alleviation of extreme class imbalances on the basis of the Synthetic Minority Over-sampling Technique (SMOTE), …

Integrated Machine Learning For Smart Home Resource Optimization, Ahmed Almazrouei

Theses

This thesis explores howmachine learning can be used to support better energy management in smart homes. Many smart home systems today collect a large amount of data through sensors and smart meters, but they still depend on simple rules and do not make predictive or automatic decisions. In the academic field, energy forecasting and energy optimization are often studied separately, which creates a gap in understanding how the two components can work together in a real setting. Because of this, there is a need to test an integrated approach that uses both forecasting and optimization in one framework. In this …

Analyzing Airline Customer Experience Challenges And Their Impact On Dubai's Tourism Sector, Suhail Alfalasi

Theses

The paper explores whether there is a connection between operational performance, customer sentiment, and digital administrative complexity among major regional Middle Eastern airlines, such as Flag Carriers (e.g., Emirates) and Low-Cost carriers (LCCs) (e.g., Air Arabia). With the use of a highly detailed dataset of customer review and operations data, the study proves that a large service paradox is present in which, despite the high Net Promoter Scores (NPS: 48.004) of the carriers, which are positively reinforced by delivering world-class soft products, the loyalty is constantly disrupted by low-frequency but high-severe operational delays (Delay_Minutes). Since it has been analyzed that …

Ai-Driven Cyber Threat Detection, Humaid Thani Almheiri

Theses

Bycreating an AI-driven method using deep learning and statistical analysis tools, this study seeks to fill important security holes in conventional intrusion detection systems. Current signature-based systems miss new and complex cyberattacks, which have significant financial and operational consequences for companies. The suggested approach detects unusual network activity in real-time by combining statistical analysis with long short-term memory networks (LSTMs), convolutional neural networks (CNNs), and statistical analysis. This study will create and test hybrid models that can identify both known and zero-day threats while reducing false positives using publicly accessible datasets like UNSW-NB15, CIC-IDS2017, and NSL-KDD. Expected results are a …

Optimizing Delivery Time Predictions Using Machine Learning: A Data-Driven Approach To Last-Mile Logistics, Mohamed Burqaiba

Theses

This paper addresses how machine learning can be utilized to improve the prediction of delivery times during the last mile, specifically in Dubai urban logistics issues whereby the traffic congestion and weather circumstances usually contribute to unpredictable delivery times. The main goal was to evolve machine learning models that can predict properly delivery time depending on several parameters, i.e., speed of traffic, weather, length of delivery, and geography. The reason why three machine learning models were chosen [Random Forest, Gradient Boosting, and XGBoost] in this analysis is that they have the opportunity to work with non-linear relationships in the data. …

A Ux Approach To Improving Patient Experience In Healthcare, Lingxin Sun

Theses

Doc Ease is a UX research and design project that addresses the emotional and functional difficulties patients experience before visiting a doctor. Through user interviews, competitive analysis, and design iteration, this project identified key user pain points such as unclear appointment processes, lack of trust, and pre-visit anxiety. The resulting mobile app offers clear booking tools, visual doctor information, medication reminders, and an emotional wellness module to help patients prepare with confidence. The project contributes to the field of healthcare UX by integrating functional usability with emotional care, proposing a design framework that centers patient experience in both logic and …

Assessing The Impact Of Codec-Induced Audio Degradation On Voice Biometric Systems, Suhil Ali Almuhaisni

Theses

This study examines the robustness of voice biometrics when speech signals undergo audio codec transformations and sampling rate variations, conditions common in telecommunication networks. Speaker verification systems such as ECAPA-TDNN perform well on clean datasets, but their accuracy declines when low-bitrate codecs compress speech or when signals are resampled at reduced frequencies. In real-world deployments, systems adapt audio to bandwidth and storage limitations, often removing subtle acoustic details that support consistent speaker recognition. The research will analyse how codec settings and sampling rates, particularly those optimized for efficiency in bandwidth-limited systems, influence the stability of speaker embeddings. Instead of ranking …

Beyond Detection: A Batch-Based Ai Framework For Temporal And Event-Correlated Trend Analysis Of Misinformation On Social Media, Vishnu Tejas Vijayaraghavan

Theses

The rapid spread of misleading information on social media influences public behaviour and complicates crisis communication. Although transformer models such as BERT accurately detect misinformation at the post level, most studies analyse posts in isolation and overlook howmisinformation fluctuates over time or responds to major events. This study addresses that gap by developing an end-to-end analytical workflow that integrates BERT-based classification with temporal aggregation, topic clustering, anomaly detection, and event alignment. The analysis uses 10,700 COVID-19–related tweets (6,420 training, 2,140 validation, and 2,140 testing). Because timestamps were unavailable, synthetic timestamps were assigned using an evenly spaced date range between 1 …

An Examination Of High-Entropy Alternatives Of Connectionist Temporal Classification Loss For Optical Music Recognition Using Convolutional Recurrent Neural Networks, Hritik Saynganthone

Theses

The Connectionist Temporal Classification (CTC) loss function is the most commonly used loss function in the field of Optical Music Recognition (OMR). However, OMR suffers from a massive class imbalance problem, exacerbated by the fact that CTC loss is subject to the spiky distribution problem, wherein the blank token introduced by CTC is vastly overpredicted and appears in timesteps where it would make more sense to predict a non-blank token, since CTC will collapse repeated tokens into a single token. This work posits that alternative loss functions to CTC that optimize for an increase in entropy of the prior probability …

Assessing Large Language Models As An Interpretive Layer In Marketing Mix Modeling: Implications For Marketing Analytics, Mohammad Bin Haider

Theses

Marketing mix modelling (MMM) remains a core technique for guiding budget allocation, yet its outputs are often difficult for non-technical planners to interpret and govern. At the same time, large language models (LLMs) offer new possibilities for translating complex model artefacts into narrative guidance, but raise concerns about hallucination, reproducibility, and alignment with model-risk governance. This thesis examines whether an open-source MMM framework can be engineered as a repro- ducible, governance-ready pipeline and then augmented with a tightly constrained LLM interpretive layer. The empirical setting is a multi-brand, multi-country retail portfolio with several years of digital marketing and outcome data …

The Influence Of Task Type And Learner Language Background On Writing Production And Anxiety: A Bayesian Linear Mixed-Effects Analysis, Mahmoud Abdi Tabari, Xinya Liang, Agnes Albert

Counseling, Leadership, and Research Methods Faculty Publications and Presentations

Despite growing interest in task-based language teaching (TBLT), limited empirical work has examined how different rhetorical task types influence second language (L2) writing development, especially in relation to affective variables, such as writing anxiety. Existing research in TBLT has largely focused on cognitive dimensions, often neglecting individual differences in learners' emotional responses. Moreover, Long's (2014) call to use first language (L1) data as a benchmark in TBLT remains underexplored, complicating the interpretation of L2 performance patterns. To address these gaps, we examined the impact of task type and writing anxiety on the written performance of 140 university students (70 L1 …

Desiccation Tolerance In Tetradesmus Green Algae, Kristen Patten

Theses

In the face of the global climate change threat, understanding the adaptations that organisms have evolved to handle environmental variation is of particular interest to scientists. With climate change impacting global water availability and increasing the risk of drought for many traditional agricultural areas in the United States (IPCC, 2014, IPCC, 2021, and Kuwayama et al., 2019), desiccation tolerance in vegetative states is one adaptation that is currently receiving a lot of attention. Green algae are particularly useful organisms for understanding this adaptation due to their ubiquity across environments, which has given rise to independently evolved organisms displaying different levels …

Balancing Earth Science Careers In An Unequal World, Nadia Testani, Lucía M. Cappelletti, Leandro B. Díaz, Camila Prudente, Valentina Rabanal, Julia Mindlin, Reyk Börner, Divya David T, Ismaila Diallo, Inés M. Leyba, Marisol Osman, Andrés Tangarife-Escobar

Faculty Research, Scholarly, and Creative Activity

Unequal research experiences among Earth scientists from around the world are an obstacle to achieving sustainability. We assess challenges and propose ways to balance the careers of early- and mid-career researchers in the Global South with those in the Global North.

Educational Experiences And Educational Attainment Of Elementary Students From Low Socioeconomic Status Backgrounds: Sequential Mixed Methods Evidence From Texas, Morgann L. Hawkins

Electronic Theses and Dissertations

Students from low socio-economic status (SES) backgrounds face significant challenges in their educational experiences and educational attainment, and this is due to barriers related to their identity and background, inadequate support systems, and a lack of understanding of the traumas they experience. This sequential mixed methods study contains the perceptions of teachers, teacher leaders, counselors, and campus leaders in four high-poverty elementary schools in one Texas school district about the educational experiences and educational attainment of students from low SES backgrounds. The informal literature review focused on six spaces: 1) child, family, and community; 2) students from low SES backgrounds; …

The Educational Experiences Of Low Socioeconomic, Hispanic, Emergent Bilingual, Elementary Students: A Sequential Mixed Methods Study From Texas, Kiley Schumacher

Electronic Theses and Dissertations

The number of Hispanic students in Texas public schools has significantly increased over the past 20 years, yet their level of academic success continues to lag. Hispanic, emergent bilingual, low-socioeconomic, early elementary students face educational challenges related to barriers surrounding language and culture differences, limited resources, unmet needs, feelings of isolation, and an underprepared educational support system. This sequential mixed methods study reported on the perceptions of parents, teachers, and campus leaders in two Texas elementary schools regarding these students’ educational experiences. Guided by existence, relatedness, and growth theory, bioecological systems theory, and culturally responsive leadership theory, the study collected …

Glacial Deposits, Vol. 50, 2025, Illinois State University

Glacial Deposits

Newsletter of the Illinois State University Department of Geography, Geology, and the Environment

Fractional Order Hierarchical Decompositions Using Multigrid Components, Panayot S. Vassilevski

Mathematics and Statistics Faculty Publications and Presentations

Motivated by the fractional order multilevel decompositions of finite element spaces developed previously, we exploit additive representations of popular multigrid (MG) cycles to design fractional order MG decompositions. The additive representations enable us to scale the individual hierarchical components thus ending up with fractional order hierarchical decompositions that are based on the readily available MG components. This results in a highly efficient and scalable (in terms of high-performance) fractional order hierarchical MG decompositions that we tested in the setting of finite element white noise sampling as an alternative to PDE-based white noise sampling using fractional order shifted Laplacians.

Surgical Removal Of Implanted Microchips To Correct Mri Susceptibility Artifacts In Mice, Elizabeth Hipskind, Nicole Hernandez, Sydney Fox, Tina Manirambona, Rita Schack, Brian Gibson, Robia G Pautler

Center on Aging Staff Publications

Purpose: Implanted microchips are becoming increasingly common in research for animal identification and have been adopted by commercial vendors for some mouse strains. However, they often contain metal components, which generate magnetic susceptibility artifacts on MR images. Despite this, some microchips are marketed as MR-compatible, even though they are likely to affect image quality.

Methods: We assessed the impact of a radiofrequency identification microchip on MR images of the mouse brain and present a method for precise surgical removal. A handheld magnet was used to locate and stabilize the microchips during removal. Mice were imaged before and after microchip removal. …

Differential Microrna Profiling Of Blood L1cam And Bulk Extracellular Vesicles In Bipolar Disorder, Gabriel R Fries, Salahudeen Mirza, Jun Wang, Camila N C Lima, Wei Zhang, Marcela Carbajal Tamez, Giselli Scaini, Jair C Soares, Joao Quevedo

Faculty, Staff and Student Publications

Objective: This preliminary study aimed to identify microRNA (miRNA) signatures associated with bipolar disorder (BD) by profiling blood-derived extracellular vesicles (EVs) of both putative neuronal origin and from all sources.

Method: In two parallel studies of individuals with BD and controls (CON), we characterized miRNA expression profiles of blood EVs selected for L1CAM, a putative marker of neuronal origin (n = 20 BD/20 CON), as well as bulk EVs (n = 21 BD/20 CON). For each study, analyses identified miRNAs differentially expressed between groups, followed by functional interrogation and testing for associations with clinical features.

Results: Results of …

Loss Of The Lysosomal Protein Cln3 Triggers C-Abl-Dependent Yap1 Pro-Apoptotic Signaling, Neuza Domingues, Alessia Calcagni', Sofia Freire, Joana Pires, Ricardo Casqueiro, Ivan L Salazar, Niculin Joachim Herz, Tuong Huynh, Katarzyna Wieciorek, Tiago Fleming Outeiro, Henrique Girão, Ira Milosevic, Andrea Ballabio, Nuno Raimundo

Duncan NRI Faculty and Staff Publications

Batten disease is characterized by early-onset blindness, juvenile dementia and death within the second decade of life. The most common genetic cause are mutations in CLN3, encoding a lysosomal protein. Currently, no therapies targeting disease progression are available, largely because its molecular mechanisms remain poorly understood. To understand how CLN3 loss affects cellular signaling, we generated human CLN3 knock-out cells (CLN3-KO) and performed RNA-seq analysis. Our multi-dimensional analysis reveals the transcriptional regulator YAP1 as a key factor in remodeling the transcriptome in CLN3-KO cells. YAP1-mediated pro-apoptotic signaling is also increased as a consequence of CLN3 functional loss in retinal pigment …

Fast And Accurate Measurement Of Small Field Dosimetry Using A Novel Scintillation Detector, Yiding Han, Jingzhu Xu, Yao Hao, Baozhou Sun

Faculty, Staff and Students Publications

Background: The most used instruments for small-field dosimetry have notable limitations, including the need for correction of output factors, limited scanning speeds, and challenges in alignment for percentage depth dose (PDD) measurements, particularly for extremely small fields. However, plastic scintillation detectors (PSDs) are an attractive alternative for small-field dosimetry due to their correction-free nature, linear dose response, and fast response time.

Purpose: This study evaluates the robustness and accuracy of the dosimetric measurements using a new water-equivalent PSD in small-field dosimetry. The study also aims to report accurate measurements of output factors, profiles, and an indirect method for measuring PDD …