Digital Commons Network^™

Fuzzy-Virtual Inertia Control To Improve The Frequency Response Of Multi-Area Power Systems, Nourelhouda Djaraf, Yacine Daili, Abderrahim Zemmit, Abdelghani Harrag

Turkish Journal of Electrical Engineering and Computer Sciences

Virtual inertia control (VIC) is essential for power systems dominated by electronic devices to compensate for the lack of inertia and ensure frequency regulation. However, most existing VICs often focus solely on optimizing the virtual inertia parameter to adapt to the high penetration of renewable energy sources (RESs) without considering the damping factor. This oversight can lead to significant fluctuations and power mismatches, especially in interconnected systems where the coordination between MGs is sensitive and essential, and there is a risk of propagation of deviations between MGs, which makes the control more complex. To address these issues, this paper presents …

Conversational Open-Domain Question Answering For Resource-Constrained Languages, Emrah Budur, Tunga Güngör

Turkish Journal of Electrical Engineering and Computer Sciences

The growing interest in Conversational AI has led to the development of Conversational OpenQA systems as a crucial step for meeting users' information needs in real world scenarios. Conversational OpenQA systems enhance standard OpenQA performance by leveraging conversation history of the users. However, building effective Conversational OpenQA systems requires large-scale Conversational OpenQA datasets, often limited to the English language, hindering progress in low-resource languages. We present a robust Conversational OpenQA system enhanced by conversational context, designed for languages with limited resources and exemplified in our case study for Turkish. To address data limitations in a cost-effective way, we repurpose existing …

A Case Study Of Gray-Box Fuzzing With Byte- And Tree-Level Mutation Strategies In Xml-Based Applications For Exposing Security Vulnerabilities, Şerafetti̇n Şentürk, Vahi̇d Garousi, Nejat Yumuşak

Turkish Journal of Electrical Engineering and Computer Sciences

Fuzzing is an automated process for detecting crashes and vulnerabilities in software system and it is classified as grammar- or mutation-based in terms of input generation. While the grammar-based fuzzing generates inputs from a specification and takes highly-structured inputs, mutation-based fuzzing generates inputs by modifying input files and abstract syntax trees randomly. There are not many case studies comparing the crash detection capabilities in the scope of mutation-based fuzzing. To add to the body of empirical evidence in this area, this case study compares fuzzing with different mutation strategies to evaluate their effectiveness in three aspects: fault detection effectiveness, fault …

Solar Flare Prediction Using Multivariate Time Series Of Photospheric Magnetic Field Parameters: A Comparative Analysis Of Vector, Time Series, And Graph Data Representations, Onur Vural, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi

Computer Science Student Research

The purpose of this study is to provide a comprehensive resource for the selection of data representations for machine learning-oriented models and components in solar flare prediction tasks. Major solar flares occurring in the solar corona and heliosphere can bring potential destructive consequences, posing significant risks to astronauts, space stations, electronics, communication systems, and numerous technological infrastructures. For this reason, the accurate detection of major flares is essential for mitigating these hazards and ensuring the safety of our technology-dependent society. In response, leveraging machine learning techniques for predicting solar flares has emerged as a significant application within the realm of …

Artificial Intelligence For Better In-Game Nfl Performance, Christopher Mcmanus

Honors Theses

In this thesis I examined the use of AI modeling for the use in the modern-day NFL, both for improving in-game play calling, and creating better recovery plans for players all around the league. When finding articles detailing these models, I only focused on works involving the current day NFL, and models used widely around the league to this day. The literature detailed in this thesis mainly describes modeling used by Amazon Web Services (AWS, 2024, The NFL’s partner for all things analytics, and data modeling. My main objective for this literature review was to show the impact AI modeling …

“Smart Trap”: A Portable Device For Real-Time Mosquito Capturing And Classification Using Image-Based Analysis, Fahim Rahman

USF Tampa Graduate Theses and Dissertations

Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. …

Examining Intersectional Queer Biases In Large Language Models: A Combined Statistical And Visual-Qualitative Approach For Quantification And Explanation, Huu Duong (Chip) Nguyen

Computer Science Senior Theses

Despite significant advancements in research on (intersectional) social biases in Large Language Models (LLMs), intersectional biases affecting subgroups within the LGBTQ+ community remain critically understudied. Existing bias detection methodologies often prioritize quantification but lack depth in explaining the specific stereotypes/biases that shape evaluation metrics. To address these gaps, this study proposes a combined statistical and visual-qualitative approach to quantify and identify persistent intersectional queer biases in five recent, state-of-the-art LLMs through a downstream story generation task. Findings from analysis uncover substantial evidence of stereotypes that perpetuate harmful, reductive narratives against intersectionally marginalized groups within the LGBTQ+ community. To promote public …

Neural Visual Synthesis For Graphics, 4d Gaussians And Videos, Zhan Li

Dissertations and Theses

Efficient visual synthesis has played an indirect yet important role in the development of neural networks. Graphics processing units (GPUs) were initially designed for visual synthesis tasks such as rendering graphics. However, their parallel computing capabilities later made GPUs the ideal hardware for training neural networks. Since neural networks have greatly benefited from GPUs, a compelling question arises: How can neural networks, in turn, improve efficient visual synthesis?

Existing visual synthesis methods still require improvement for higher efficiency. For example, Monte Carlo rendering takes over 15 minutes to generate a megapixel frame at a high-quality setting on a GPU, as …

Feature Manifold Transformer For Detection Of Differential Item Functioning: Visual Detection Of Categorical Feature Nonconformity Through Attention-Based Analysis, Derrick A. Cox, Tanvi Banerjee, William L. Romine

Computer Science and Engineering Faculty Publications

Methods for interpreting complex feature interactions in educational assessment data remain a critical challenge, with traditional statistical approaches often creating barriers to accessibility and interpretability. We introduce the Feature Manifold Transformer (FMT), a novel machine learning approach that leverages dimensionality reduction, representation learning, and transformer architectures to visualize and interpret feature relationships in categorical data. Using the Concept Inventory of Natural Selection (CINS) and Concept Assessment of Natural Selection (CANS) datasets as testbeds, we demonstrate the FMT’s ability to capture subtle relationships between student demographics and response patterns. Our methodology enables both global and local pattern analysis, providing interpretable visualizations …

Comprehensive Review On The Application Of Bio-Immunoinformatics In The Development Of Highly Ef-Fective New Candidate Vaccines Against Tuberculosis, Ahyar Ahmad, Andriansjah Rukmana, Miski A. Khairinisa, Dian A. E. Pitaloka, Rosana Agus, Rusdina B. Ladju, Tarwadi Ahmad, Astutiati Nurhasanah, Carina C. D. Joe, Muhammad N. Massi, Harningsih Karim, Irda Handayani, Siti Roszilawati Binti Ramli

Karbala International Journal of Modern Science

Tuberculosis (TB) remains a significant public health challenge worldwide. Currently, Bacillus Calmette-Guerin (BCG) is the only vaccine available for TB prophylaxis. However, the efficacy of the BCG vaccine against adult pulmonary TB is considered inconsistent. This condition encourages researchers to look for more effective options, such as subunit vaccines. This condition requires the development of a more effective subunit vaccine to protect active TB in productive and adult ages. There is an urgent need for more effective vaccines, as the Bacillus Calmette-Guérin (BCG) vaccine currently available has inconsistent efficacy and is only partially effective in adults. Bio-immunoinformatics, an interdisciplinary field …

Leveraging Large Language Models For Knowledge-Free Weak Supervision In Clinical Natural Language Processing, Enshuo Hsu, Kirk Roberts

Faculty, Staff and Student Publications

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled …

Logiclm: Robust Application Of Large Language Models With Logic Programming For Data Analytics, Evgeny Skvortsov, Shayan Mirjafari, Ojaswa Garg, Yilin Xia, Shaun Bowers, Bertram Ludäscher

Computer Science Faculty Scholarship

We present LogicLM, an OLAP-style interactive data analysis system that leverages large language models (LLMs) and is configured using Logica, an enhanced logic programming language with aggregation support that compiles to SQL. LogicLM uses an LLM to translate natural language queries by end users into executable code for automatically generating data visualizations. For each natural-language query, LogicLM provides a verifiable OLAP-based configuration that users can view and modify to help ensure results are reliable and accurate. This configuration, with measures, dimensions, and filters defined as logical predicates, offers a unified and user-friendly approach to naturallanguage data exploration, while keeping end …

Model Explanations For Gender And Ethnicity Bias Mitigation In Ai-Generated Narratives, Martha Otisi Dimgba

Dissertations and Theses

Large Language Models (LLMs) are increasingly utilized in diverse applications, ranging from professional content creation to decision-making systems. However, their outputs often amplify the biases present in their training data, perpetuating stereotypes and reinforcing societal inequities, particularly regarding gender and ethnicity. Such biases can cause tangible harm, especially for underrepresented groups, and require awareness and effective mitigation strategies.

This work explores gender and ethnicity representation in narratives created by generative AI describing 25 occupational fields defined by the U.S. Bureau of Labor Statistics. We examine three large language models (LLMs)--Llama 3.1 70B Instruct, Claude 3.5 Sonnet, and GPT 4.0 Turbo. …

This One Weird Trick Gets Users To Stop Clicking On Clickbait, Ankit Shrestha, Arezou Behfar, Sovantharith Seng, Matthew Wright, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

Clickbait, masked behind interesting headlines and thumbnails, is often used to spread misinformation and trick users into clicking on social media posts or links that direct them to malicious websites. To help users protect against clickbait, we examined interventions based on persuasion theories including designs that used social consequence, personal consequence, and badges. To this end, we first conducted a preliminary study to translate the participants’ feedback into improving our initial designs, followed by a lab study with 20 participants (60% Male, 40% Female; 18-44 years old) aimed at understanding their perceptions of the improved interventions; we further updated our …

From Machine Learning To Human Learning: What Can Pedagogy Learn From Ai Successes, Victor L. Timchenko, Yury P. Kondratenko, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Many machine learning techniques -- including many techniques behind the current AI-based boom in machine learning -- come from the analysis of successful human learning strategies (and researchers expect that other human learning experiences can lead to even more effective AI-based systems). At this moment, so much experience have been accumulated in AI-based machine learning that it is time to start the analysis in the opposite direction -- to see what can human-based pedagogy learn from AI successes. In this chapter, we provide the first results of such an analysis -- some of which go somewhat against the current pedagogical …

Gurevich's Quizani Dialogs As An Example Of Explainable Mathematics, And How This Is Related To Quantum Space-Time Ideas That Can Speed Up Computations, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Everyone talks about the need for Explainable AI -- when, to supplement a long difficult-to-understand sequence of computational steps leading to AI's decision, we are looking for a shorter and understandable more-informal explanation for this decision. In this paper, we argue that this need is a particular case of what we call Explainable Mathematics -- when we want to supplement a long sequence of arguments and/or computations with a shorter and understandable more-informal explanation. Important instances of Explainable Mathematics are Yuri Gurevich's Quizani dialogs that help explain complex results from theoretical computer science and physicists' more-informal explanations of complex physical …

Unfortunately, The Universal Predictor Cannot Be Made Constructive, Julio C. Urenda, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

A recent article in the Notices of the American Mathematical Society reminded the mathematics community that, under the Axiom of Choice, it is possible to have a universal predictor: if we input, into this predictor, the values of a function for all moments t < to for some to, then, for almost all to, this predictor correctly predicts the next values of this function on some interval [to, to + ε). This predictor cannot be used for actual predictions: it is based on the Axiom of Choice and is, therefore, not constructive. A natural question is: maybe it is possible to have another universal predictor, which is constructive? In this paper we show that, unfortunately, it is not possible to have a constructive universal predictor. In other words, the above universal predictor result cannot be used for actual predictions.

The Present And Future Of Ai: Ethical Issues And Research Opportunities, Ankita Srivastava, Marco Marabelli, Danielle Blanch-Hartigan, Jeffrey Moriarty, Evan Carey

Philosophy Faculty Publications

Healthcare is currently a fast-changing industry with AI and generative AI (GenAI) playing a prominent role in the transformation of clinical as well as managerial practices. Clinical practices involve AI to diagnose diseases and develop new drugs and compounds, while managerial practices concern AI-supporting processes such as billing patients and insurance companies, handling electronic medical records, and supporting remote connections with patients, increasingly using virtual and augmented reality. Yet, all these opportunities offered by AI come with challenges involving potential ethical issues, such as discrimination, bias, lack of accessibility, and privacy issues. In March 2024, we organized a panel with …

Smoothed Particle Hydrodynamics For Free-Surface Flows And Time Series Forecasting Approach For Computational Fluid Dynamics, Huali Ye

Doctoral Dissertations

With the increase in computing power, numerical simulation has become an essential approach to solving problems in engineering and science. Numerical simulations provide a platform for theoretical validation and facilitate novel discovery. Even though extensive mesh-based numerical methods are utilized, significant limitations exist, particularly in Computational Fluid Dynamics (CFD). Because of the grid distortion, issues related to large deformations, moving interfaces, and free surfaces may lead to considerable computational errors, constraining their efficacy in numerous applications. As a mesh-free method, Smoothed Particle Hydrodynamics (SPH) was introduced in 1977 and has been widely applied in many fields such as astrophysics and …

Best Strategies For Bilingual Education: How Can We Explain Their Success?, Claudia Cabrera, Olga Kosheleva, Christian Servin, Vladik Kreinovich

Departmental Technical Reports (CS)

When designing AI-based tools for education, it is important to take into account the experience of human teachers. In this, it is necessary to distinguish between the education features that are justified by the general features of the corresponding education task -- these features should be taken into account in AI-based learning as well -- and features which are specific for traditional non-AI teaching. In this paper, on the important example of bilingual education, we show that several empirically successful teaching strategies can be explained in the general context -- and thus, should be implemented in AI-based teaching as well.

Smart Highway Construction Site Monitoring Using Artificial Intelligence, Mehran Mazari, Yahaira Nava-Gonzalez, Ly Jacky N. Nhiayi, Mohamad H. Saleh

Mineta Transportation Institute

Construction is a large sector of the economy and plays a significant role in creating economic growth and national development,and construction of transportation infrastructure is critical. This project developed a method to detect, classify, monitor, and track objects during the construction, maintenance, and rehabilitation of transportation infrastructure by using artificial intelligence and a deep learning approach. This study evaluated the performance of AI and deep learning algorithms to compare their performance in detecting and classifying the equipment in various construction scenes. Our goal was to find the optimized balance between the model capabilities in object detection and memory processing requirements. …

Real-Time Prediction Of Dynamical Systems Using A Hybrid Analog Computer: Network Traffic Modeling, Majd Zuhair Tahat

Doctoral Dissertations

As the number of online users grows exponentially, the number and severity of cyber threats escalate, urgently requiring advancements in real-time network modeling and response. Swiftly predicting and analyzing network traffic is crucial for effective network monitoring and control, preventing cyber breaches, and maintaining healthy network functionality. This research presents a novel approach to real-time modeling based on analyzing evolving properties and patterns in a dynamical network system using a hybrid analog-digital computer. An analog computer was utilized as a co-processor to compute differential equations that model the Transmission Control Protocol (TCP) window size. A comparative analysis was conducted between …

A Human-In-The-Loop Framework For Scalable And Interpretable Event Triaging In Large-Scale Systems, Ibrahim Khaled Al-Agha

Doctoral Dissertations

This dissertation presents a comprehensive and scalable framework for real-time fault detection and event triage in industrial systems, addressing critical challenges such as class imbalance, ambiguous feature boundaries, and the prioritization of complex, high-dimensional event data. The proposed framework integrates advanced methodologies, including micro-batch processing, retrospective divergence-based event detection (DB-RED), association rule mining (ARM), clustering, and Dempster-Shafer Theory (DST) for conflict resolution. Together, these components enable the systematic stratification of events into actionable priority levels, ensuring robust and interpretable decision-making in real-time environments. DB-RED forms the cornerstone of the framework, leveraging KL-divergence and PE-divergence metrics to detect subtle and transient …

Evaluating Educational Benefits Of A Custom Cyber Game: ‘Hvac Attack!’, Jillian S. Valente

Theses and Dissertations

Cyber competition and conflict remain an enduring concern for the Department of Defense (DoD). Positive control of cyberspace is crucial across the vast diversity of military operations and supporting activities. Military members play an important role in cyber prevention, detection, and remediation, but most receive relatively little training outside of the annual Cyber Awareness Challenge. Particular career fields within the DoD may benefit from specialized training in cybersecurity, in particular the civil engineering (CE) community supporting critical infrastructure protection. Prior research has suggested that game-based learning (GBL) can be beneficial for teaching cyber concepts.

Improving Smartphone Gnss Jammer Localization With Cloud-Based Environmental Occlusion Modeling, Glenn H. Jones

Theses and Dissertations

The advancement of Global Navigation Satellite System (GNSS) technology in modern smartphones has made these devices pervasive in both civilian and military applications. Although smartphone GNSS chipsets are more susceptible to jamming and spoofing than military grade hardware, smartphone networks offer an underutilized opportunity to detect and mitigate threats to position, navigation, and timing (PNT) services essential to the Department of Defense (DoD) and civilian first responders. Traditional methods for geolocating ground-based jamming sources using smartphone GNSS often fail in environments with dense vegetation or significant occlusions, resulting in substantial localization errors.

Hyperparameter Tuning For Robust Autonomous Vehicle Vision, Nico D. De Ros

Theses and Dissertations

Classification “flickering,” where the classification of an object changes inconsistently between consecutive video frames, remains a persistent issue in modern object classification algorithms. This problem undermines the reliability of autonomous vision systems and poses significant risks in high-stakes applications such as autonomous vehicles. This thesis explores the use of response surface methodology, a statistical design of experiments technique, to optimize hyperparameters across three object classification pipelines. The first pipeline combines YOLOv8 with SORT to establish a benchmark. The second integrates a Bayesian back-end, while the third employs an exponential smoothing back-end. Hyperparameter tuning was conducted using a two-step process: an …

Spatiotemporal Prediction Of Atmospheric Events Through Recurrent Deep Learning Model, Brian W. F. Popick

Theses and Dissertations

The main contributions of this research is to add to the growing library of literature on the use of deep learning algorithms for the spatiotemporal prediction of dangerous atmospheric and hydrologic phenomena. Specifically, we develop novel attention-based and non-attention-based recurrent neural network frameworks to produce short-range sequential forecasts for lightning and tornado occurrences. Additionally, we introduce methods that account for and include error in the model tuning process to generate more reliable models. Furthermore, we have created a lightweight spatiotemporal tornadic prediction dataset that we plan to make publicly available. The first component of this research develops three novel spatiotemporal …

Uranium Particle Classification Using Statistical Machine Learning And Deep Neural Networks For Nuclear Forensics, Lee C. Lambert

Theses and Dissertations

The classification of uranium particles from scanning electron microscopy (SEM) imagery is critical to nuclear forensics, but has traditionally relied solely on skilled analysts whose classification accuracy and procedures may vary widely. Existing morphology lexicology [1] provides standardization guidelines to aid analysts but cannot fully address analyst variability. Using a dataset of 1,906 SEM images across 13 unevenly distributed particle classes and 73 magnification levels, final accuracy between statistical and deep learning methods were compared to find the best classification techniques. Ultimately, the deep learning model achieved an impressive 82% accuracy (80% balanced accuracy) on a withheld test set. This …

Hypergame Models For Cyber Defense In A Purple Team Setting, Thomas N. Whitney

Theses and Dissertations

Hypergame theory and purple teaming are two fields that can support an increased cybersecurity posture. This research investigates a hypergame theory framework that incorporates fittingly into the purple team feedback loop. Additionally, this research integrates empirical data into the hypergames. The data and the hypergames are supported by the MITRE ATT&CK framework. This research also includes a review of available game theory and hypergame theory software, five different hypergame models, a comparison of the two hypergame formats, and an innovative analysis technique using a multi-stage hypergame to represent the cyber kill chain. One finding of this research is that a …

Jamming-Tolerant Low-Rate Wireless Personal Area Network For Detection Sensor Networks, Michael A. Eddy

Theses and Dissertations

This research evaluates the impact of electronic warfare, particularly jamming, on an audio-based drone detection wireless sensor network (WSN) using Monte Carlo simulations. A six-node IEEE 802.15.4 network, with five edge nodes and a central sink, is tested against jamming probabilities ranging from 0-100% in 5% increments across 30 iterations per configuration. Results show that packet delivery ratio (PDR) degrades linearly at approximately 20% per jammed node, while detection performance often exceeds PDR. Even at 80% jamming, detection success rates remain above 57%, highlighting resilience despite network degradation. The study reveals that jamming effectiveness depends on node placement relative to …